{
"markdown": "# Claude Code Skills Marketplace\n\n\n\n[](./README.md)\n[](./README.zh-CN.md)\n\n[](https://opensource.org/licenses/MIT)\n[](https://claude.com/code)\n[](./CONTRIBUTING.md)\n[](https://github.com/daymade/claude-code-skills/graphs/commit-activity)\n\n
\n\nProfessional Claude Code skills marketplace featuring production-ready skills for enhanced development workflows.\n\n## 📑 Table of Contents\n\n- [🌟 Essential Skill: skill-creator](#-essential-skill-skill-creator)\n- [🚀 Quick Installation](#-quick-installation)\n- [🇨🇳 Chinese User Guide](#-chinese-user-guide)\n- [📦 Other Available Skills](#-other-available-skills)\n- [🎬 Interactive Demo Gallery](#-interactive-demo-gallery)\n- [🎯 Use Cases](#-use-cases)\n- [📚 Documentation](#-documentation)\n- [🛠️ Requirements](#️-requirements)\n- [❓ FAQ](#-faq)\n- [🤝 Contributing](#-contributing)\n- [📄 License](#-license)\n\n---\n\n## 🌟 Essential Skill: skill-creator\n\n**⭐ Start here if you want to create your own skills!**\n\nThe `skill-creator` is the **meta-skill** that enables you to build, validate, and package your own Claude Code skills. It's the most important tool in this marketplace because it empowers you to extend Claude Code with your own specialized workflows.\n\n### Why This skill-creator?\n\nThis is a **production-hardened fork** of [Anthropic's official skill-creator](https://github.com/anthropics/skills/tree/main/skills/skill-creator), born from building real skills and hitting every wall the official version doesn't warn you about.\n\n**The official skill-creator tells you _what_ to build. Ours also tells you _what not to try_ — and why.**\n\n| You're trying to... | Official | This Fork |\n|---------------------|----------|-----------|\n| Research before building | \"Check available MCPs\" | Ordered search protocol with decision matrix: Adopt / Extend / Build |\n| Create a skill interactively | Prose-based instructions | Structured AskUserQuestion checkpoints — user never loses context |\n| Avoid common mistakes | No guidance | Cache edit warnings, prerequisite checks, security scan gate |\n| Know the architecture options | Not mentioned | Inline vs Fork decision guide with examples (choosing wrong silently breaks your skill) |\n| Validate before shipping | Basic YAML check | Expanded structural validator plus provenance-checked old-vs-new capability audit; packaging re-verifies the completed review instead of trusting a marker |\n| Match validation cost to risk | One full create-test-review loop | Risk tier and evaluation spend are separate: targeted checks first; paired benchmarks require explicit authorization or a decision-bearing evidence plan plus opt-in |\n| Catch security issues | No tooling | `security_scan.py` with gitleaks integration — hard gate before packaging |\n| Learn from real failures | No failure cases | Battle-tested methodology with documented failure patterns and gotchas |\n| Distill past conversations safely | Not covered | Explicit local manifest, message-level time window, redaction, opaque source IDs, ignored `.enrich/` staging, and manual promotion into references/scripts |\n| Turn approved artifacts into skill behavior | Not covered | Artifact-corpus distillation workflow: script-measured pattern extraction (≥3-artifact threshold), cataloging≠distillation gate, invariant-vs-register boundary, independent completeness audit |\n| Survive concurrent sessions on one skill repo | Not covered | git-ref baselines, re-read-before-write, HEAD check before commit, own-paths-only staging, one-bump-per-outcome versioning |\n| Ground knowledge skills in evidence | General advice | Authority ladder from real calls and machine-readable specs through production code, plus executable-example smoke checks and evidence-boundary rules |\n| Have both installed at once | Coin flip — the two descriptions are near-identical | Detects the clash on trigger and offers a one-command, reversible SessionStart routing hook (only ever installed when both coexist); the official plugin stays usable by explicit request |\n| Your own skill collides with an installed plugin | Not covered | `generate_supersede_kit.py` stamps the same conditional routing kit into your skill, plus a measured precedence decision guide (rename → description tiebreaker → hook → disable) |\n\n> Full methodology: [skill-creator/references/skill-development-methodology.md](./daymade-skill/skill-creator/references/skill-development-methodology.md)\n\n### Quick Install\n\n**In Claude Code (in-app):**\n```text\n/plugin marketplace add daymade/claude-code-skills\n```\n\nThen:\n1. Select **Browse and install plugins**\n2. Select **daymade/claude-code-skills**\n3. Select **skill-creator**\n4. Select **Install now**\n\n**From your terminal (CLI):**\n```bash\nclaude plugin marketplace add https://github.com/daymade/claude-code-skills\n# Marketplace name: daymade-skills (from marketplace.json)\nclaude plugin install daymade-skill@daymade-skills\n```\n\n### What You Can Do\n\nAfter installing skill-creator, simply ask Claude Code:\n\n```\n\"Create a new skill called my-awesome-skill in ~/my-skills\"\n\n\"Validate my skill at ~/my-skills/my-awesome-skill\"\n\n\"Package my skill at ~/my-skills/my-awesome-skill for distribution\"\n```\n\nClaude Code, with skill-creator loaded, will guide you through the entire skill creation process - from understanding your requirements to packaging the final skill.\n\n📚 **Full documentation**: [daymade-skill/skill-creator/SKILL.md](./daymade-skill/skill-creator/SKILL.md)\n\n### Live Demos\n\n**📝 Initialize New Skill**\n\n\n\n**✅ Validate Skill Structure**\n\n\n\n**📦 Package Skill for Distribution**\n\n\n\n---\n\n## 🚀 Quick Installation\n\n### Install Inside Claude Code (In-App)\n\n```text\n/plugin marketplace add daymade/claude-code-skills\n```\n\nThen:\n1. Select **Browse and install plugins**\n2. Select **daymade/claude-code-skills**\n3. Select the plugin you want\n4. Select **Install now**\n\n### Automated Installation (Recommended)\n\n**macOS/Linux:**\n```bash\ncurl -fsSL https://raw.githubusercontent.com/daymade/claude-code-skills/main/scripts/install.sh | bash\n```\n\n**Windows (PowerShell):**\n```powershell\niwr -useb https://raw.githubusercontent.com/daymade/claude-code-skills/main/scripts/install.ps1 | iex\n```\n\n### Manual Installation\n\nAdd the marketplace:\n```bash\nclaude plugin marketplace add https://github.com/daymade/claude-code-skills\n```\n\nMarketplace name is `daymade-skills` (from marketplace.json). Use `@daymade-skills` when installing plugins.\nDo not use the repo path as a marketplace name (e.g. `@daymade/claude-code-skills` will fail).\nIn Claude Code, use `/plugin ...` slash commands. In your terminal, use `claude plugin ...`.\n\n**Essential Skill** (recommended first install):\n```bash\n# skill-creator ships inside the daymade-skill suite\nclaude plugin install daymade-skill@daymade-skills\n```\n\n**Documentation Suite** (shared namespace for document workflows):\n```bash\nclaude plugin install daymade-docs@daymade-skills\n```\n\nThis suite exposes related skills under one namespace, including:\n\n```text\n/daymade-docs:doc-to-markdown\n/daymade-docs:mermaid-tools\n/daymade-docs:pdf-creator\n/daymade-docs:ppt-creator\n/daymade-docs:docs-cleaner\n/daymade-docs:excel-automation\n/daymade-docs:read-docx-review\n```\n\nThese skills ship as a bundle — there are no separate single-skill plugins. All documentation skills live under `daymade-docs/` and install together from the suite.\n\n**Apple Platform Suite** (shared namespace for macOS and iOS development/operations):\n```bash\nclaude plugin install daymade-macos@daymade-skills\n```\n\n```text\n/daymade-macos:capture-screen\n/daymade-macos:developing-ios-apps\n/daymade-macos:macos-cleaner\n/daymade-macos:macos-watchdog\n```\n\nThese skills are bundle-only under `daymade-macos`.\n\n**Codex Suite** (shared namespace for Codex workstation setup, assisted coding, and visual exploration):\n```bash\nclaude plugin install daymade-codex@daymade-skills\n```\n\nCodex CLI and Desktop users can install the same suite through Codex's plugin\nmarketplace:\n\n```bash\ncodex plugin marketplace add daymade/claude-code-skills\ncodex plugin add daymade-codex@daymade-skills\n```\n\n```text\n/daymade-codex:codex-image-gallery\n/daymade-codex:local-codex\n/daymade-codex:design-style-picker\n/daymade-codex:interaction-design-board\n/daymade-codex:codex-1m-context-window-setup\n```\n\nThese skills are bundle-only under `daymade-codex`.\n\n**Claude Code Operations Suite** (shared namespace for Claude Code power-user workflows):\n```bash\nclaude plugin install daymade-claude-code@daymade-skills\n```\n\nThis suite bundles the skills that extend Claude Code itself — cross-project prior-work retrieval across code, docs, Skills, meetings, WeChat archives, and conversation history; fast local conversation discovery across Claude Code and Codex; session recovery; CLAUDE.md tuning; version-synced Lark CLI routing; troubleshooting; statusline configuration; export repair; marketplace development and suite consolidation; terminal screenshot rendering; usage analysis; and multi-provider model switching:\n\n```text\n/daymade-claude-code:local-conversation-history\n/daymade-claude-code:read-claude-code-history\n/daymade-claude-code:read-codex-history\n/daymade-claude-code:continue-claude-code-work\n/daymade-claude-code:continue-codex-work\n/daymade-claude-code:claude-skills-troubleshooting\n/daymade-claude-code:claude-md-progressive-disclosurer\n/daymade-claude-code:statusline-generator\n/daymade-claude-code:claude-export-txt-better\n/daymade-claude-code:marketplace-dev\n/daymade-claude-code:terminal-screenshot\n/daymade-claude-code:claude-usage-analyst\n/daymade-claude-code:claude-switch-models-setup\n/daymade-claude-code:read-claude-web-conversation\n/daymade-claude-code:claude-migrate-memory-to-doc\n/daymade-claude-code:claude-code-hooks\n/daymade-claude-code:prior-work-retrieval\n/daymade-claude-code:lark-cli-router\n/daymade-claude-code:claude-code-ping-start-5h-quota\n```\n\nInstalled names render as `daymade-claude-code:` under a single shared namespace. These skills are bundle-only — install the suite to get all members.\n\n**Financial Data Suite** (shared namespace for investment-research and financial data workflows):\n```bash\nclaude plugin install daymade-financial@daymade-skills\n```\n\nThis suite bundles the skills that fetch and analyze financial data — Bigdata.com (RavenPack) structured financials and sentiment, US equity fundamentals via yfinance, Gangtise (岗底斯) OpenAPI research suite orchestration, A-share news and policy aggregation, A-share pharmaceutical sector daily reporting, structured devil's-advocate pressure-testing of investment theses, and adversarial due diligence on inflated benchmark claims:\n\n```text\n/daymade-financial:bigdata-skill\n/daymade-financial:financial-data-collector\n/daymade-financial:gangtise-copilot\n/daymade-financial:ashare-news-fetcher\n/daymade-financial:daymade-sector-research\n/daymade-financial:pharma-daily-report\n/daymade-financial:devils-advocate\n/daymade-financial:benchmark-due-diligence\n```\n\nInstalled names render as `daymade-financial:` under a single shared namespace. These skills are bundle-only — install the suite to get all members.\n\n**Install Other Skills:**\n```bash\n# GitHub operations\nclaude plugin install github-ops@daymade-skills\n\n# Teams communication\nclaude plugin install teams-channel-post-writer@daymade-skills\n\n# Local Claude/Codex agent messaging\nclaude plugin install peer-message@daymade-skills\n\n# Repomix extraction\nclaude plugin install repomix-unmixer@daymade-skills\n\n# AI/LLM icons\nclaude plugin install llm-icon-finder@daymade-skills\n\n# CLI demo generation\nclaude plugin install cli-demo-generator@daymade-skills\n\n# Cloudflare diagnostics\nclaude plugin install cloudflare-troubleshooting@daymade-skills\n\n# UI design system extraction\nclaude plugin install ui-designer@daymade-skills\n\n# YouTube video/audio downloading\nclaude plugin install youtube-downloader@daymade-skills\n\n# Secure repomix packaging\nclaude plugin install repomix-safe-mixer@daymade-skills\n\n# Full audio suite (ASR + transcript correction + meeting minutes + TTS)\nclaude plugin install daymade-audio@daymade-skills\n\n# Video comparison and quality analysis\nclaude plugin install video-comparer@daymade-skills\n\n# QA testing infrastructure with autonomous execution\nclaude plugin install qa-expert@daymade-skills\n\n# Prompt optimization using EARS methodology\nclaude plugin install prompt-optimizer@daymade-skills\n\n# CCPM skill registry search and management\nclaude plugin install daymade-skill@daymade-skills\n\n# Promptfoo LLM evaluation framework\nclaude plugin install promptfoo-evaluation@daymade-skills\n\n# Twitter/X content fetching\nclaude plugin install twitter-reader@daymade-skills\n\n# Skill quality review and improvement\nclaude plugin install daymade-skill@daymade-skills\n\n# GitHub contribution strategy\nclaude plugin install github-contributor@daymade-skills\n\n# Windows Remote Desktop / AVD connection diagnosis\nclaude plugin install windows-remote-desktop-connection-doctor@daymade-skills\n\n# Product analysis and optimization\nclaude plugin install product-analysis@daymade-skills\n\n# Scrapling CLI extraction and troubleshooting\nclaude plugin install scrapling-skill@daymade-skills\n\n# Tencent IMA knowledge base companion and installer\nclaude plugin install ima-copilot@daymade-skills\n\n# Export Douban (豆瓣) book/movie/music/game collections to CSV\nclaude plugin install douban-skill@daymade-skills\n\n# Terraform operational traps and multi-environment reliability patterns\nclaude plugin install terraform-skill@daymade-skills\n\n# Evaluate any LLM endpoint across speed, concurrency, protocol, and quality\nclaude plugin install llm-eval-harness@daymade-skills\n```\n\nStandalone plugins can be installed independently; suite members install together with their suite.\n\n---\n\n## 🇨🇳 Chinese User Guide\n\n**For Chinese users:** We highly recommend using [CC-Switch](https://github.com/farion1231/cc-switch) to manage Claude Code API provider configurations.\n\nCC-Switch enables you to:\n- ✅ Quickly switch between different API providers (DeepSeek, Qwen, GLM, etc.)\n- ✅ Test endpoint response times to find the fastest provider\n- ✅ Manage MCP server configurations\n- ✅ Auto-backup and import/export settings\n- ✅ Cross-platform support (Windows, macOS, Linux)\n\n**Setup:** Download from [Releases](https://github.com/farion1231/cc-switch/releases), install, add your API configs, and switch via UI or system tray.\n\n### Complete Chinese Documentation\n\nFor full documentation in Chinese, see [README.zh-CN.md](./README.zh-CN.md).\n\n---\n\n## 📦 Other Available Skills\n\n### **github-ops** - GitHub Operations Suite\n\nGitHub operations through gh CLI and GitHub APIs, with explicit targets, impact previews, and\nindependent state verification.\n\n**When to use:**\n- Creating, viewing, or managing pull requests\n- Managing issues and repository settings\n- Managing collaborators, teams, organization permissions, and 2FA enforcement\n- Querying GitHub API endpoints\n- Working with GitHub Actions workflows\n- Automating GitHub operations\n\n**Key features:**\n- Verified mutation workflow for PRs, issues, repositories, and Actions\n- Parallel and superseded PR convergence\n- Organization access, member privileges, and 2FA preflight\n- REST, GraphQL, and documented UI-path selection\n- Enterprise GitHub support\n\n**🎬 Live Demo**\n\n\n\n---\n\n### **doc-to-markdown** - Document Conversion Suite\n\n> **Install**: `claude plugin install daymade-docs@daymade-skills` (suite-only — invoked as `daymade-docs:doc-to-markdown`)\n\nConverts documents to markdown with Windows/WSL path handling and PDF image extraction.\n\n**When to use:**\n- Converting .doc/.docx/PDF/PPTX to markdown\n- Extracting images from PDF files\n- Processing Confluence exports\n- Handling Windows/WSL path conversions\n\n**Key features:**\n- Multi-format document conversion\n- PDF image extraction using PyMuPDF\n- Windows/WSL path automation\n- Confluence export processing\n- Helper scripts for path conversion and image extraction\n\n**🎬 Live Demo**\n\n\n\n---\n\n### **mermaid-tools** - Diagram Generation\n\n> **Install**: `claude plugin install daymade-docs@daymade-skills` (suite-only — invoked as `daymade-docs:mermaid-tools`)\n\nExtracts Mermaid diagrams from markdown and generates high-quality PNG images.\n\n**When to use:**\n- Converting Mermaid diagrams to PNG\n- Extracting diagrams from markdown files\n- Processing documentation with embedded diagrams\n- Creating presentation-ready visuals\n\n**Key features:**\n- Automatic diagram extraction\n- High-resolution PNG generation\n- Smart sizing based on diagram type\n- Customizable dimensions and scaling\n- WSL2 Chrome/Puppeteer support\n\n**🎬 Live Demo**\n\n\n\n---\n\n### **statusline-generator** - Statusline Customization\n\n> **Install**: `claude plugin install daymade-claude-code@daymade-skills` (suite-only — invoked as `daymade-claude-code:statusline-generator`)\n\nConfigures Claude Code statuslines with multi-line layouts and cost tracking.\n\n**When to use:**\n- Customizing Claude Code statusline\n- Adding cost tracking (session/daily)\n- Displaying git status\n- Multi-line layouts for narrow screens\n- Color customization\n\n**Key features:**\n- Multi-line statusline layouts\n- ccusage cost integration\n- Git branch status indicators\n- Customizable colors\n- Portrait screen optimization\n\n**🎬 Live Demo**\n\n\n\n---\n\n### **teams-channel-post-writer** - Teams Communication\n\nCreates educational Teams channel posts for internal knowledge sharing.\n\n**When to use:**\n- Writing Teams posts about features\n- Sharing Claude Code best practices\n- Documenting lessons learned\n- Creating internal announcements\n- Teaching effective prompting patterns\n\n**Key features:**\n- Post templates with proven structure\n- Writing guidelines for quality content\n- \"Normal vs Better\" example patterns\n- Emphasis on underlying principles\n- Ready-to-use markdown templates\n\n**🎬 Live Demo**\n\n\n\n---\n\n### **peer-message** - Local Claude/Codex Agent Communication\n\n> **Install**: `claude plugin install peer-message@daymade-skills`\n\nDiscovers, messages, broadcasts to, and independently verifies local Claude Code sessions and Codex threads through each product's own transport.\n\n**When to use:**\n- Asking one terminal's Claude or Codex agent to coordinate with another\n- Sending a dependency, pause, handoff, or completion notice across sessions\n- Reaching a Claude inbox from a third-party profile or Codex process\n- Unblocking messages held for per-message manual approval on an unattended endpoint (`crossSessionInbound`)\n- An inbound peer message asserting facts about your session or shared state, or asking you to pause/release — verify the premise against its own authority before acting\n- Another session's uncommitted edits, lock, or branch is in your way on a shared checkout — verify it is live, then ask the owner before waiting or working around it\n- Broadcasting one explicit coordination message to a reviewed target list\n\n📚 **Documentation and commands**: [peer-message/SKILL.md](./peer-message/SKILL.md) owns routing, stable runtime prerequisites, and the peer-cannot-authorize boundary; `peer-message/scripts/peer.py --help` owns CLI syntax; [protocol-and-discovery.md](./peer-message/references/protocol-and-discovery.md) owns addressing, envelopes, and delivery evidence; [official-feature.md](./peer-message/references/official-feature.md) owns volatile product-specific requirements and mechanics; [coordination-and-learning-loop.md](./peer-message/references/coordination-and-learning-loop.md) owns reply addressing, payload and delivery-status language, what to do when you find another session's in-flight work on a shared resource, what an inbound peer assertion and a set of peer denials are each worth, and the evidence-gated improvement loop.\n\n---\n\n### **repomix-unmixer** - Repository Extraction\n\nExtracts files from repomix-packed repositories and restores directory structures.\n\n**When to use:**\n- Unmixing repomix output files\n- Extracting packed repositories\n- Restoring file structures\n- Reviewing repomix content\n- Converting repomix to usable files\n\n**Key features:**\n- Multi-format support (XML, Markdown, JSON)\n- Auto-format detection\n- Directory structure preservation\n- UTF-8 encoding support\n- Comprehensive validation workflows\n\n**🎬 Live Demo**\n\n\n\n---\n\n### **llm-icon-finder** - AI/LLM Brand Icon Finder\n\nAccess 100+ AI model and LLM provider brand icons from lobe-icons library.\n\n**When to use:**\n- Finding brand icons for AI models/providers\n- Downloading logos for Claude, GPT, Gemini, etc.\n- Getting icons in multiple formats (SVG/PNG/WEBP)\n- Building AI tool documentation\n- Creating presentations about LLMs\n\n**Key features:**\n- 100+ AI/LLM model icons\n- Multiple format support (SVG, PNG, WEBP)\n- URL generation for direct access\n- Local download capabilities\n- Searchable icon catalog\n\n**🎬 Live Demo**\n\n\n\n---\n\n### **cli-demo-generator** - CLI Demo Generation\n\nGenerate professional animated CLI demos and terminal recordings with VHS automation.\n\n**When to use:**\n- Creating demos for documentation\n- Recording terminal workflows as GIFs\n- Generating animated tutorials\n- Batch-generating multiple demos\n- Showcasing CLI tools\n\n**Key features:**\n- Automated demo generation from command lists\n- Batch processing with YAML/JSON configs\n- Interactive recording with asciinema\n- Smart timing based on command complexity\n- Multiple output formats (GIF, MP4, WebM)\n- VHS tape file templates\n\n**🎬 Live Demo**\n\n\n\n---\n\n### **cloudflare-troubleshooting** - Cloudflare Diagnostics\n\nInvestigate and resolve Cloudflare configuration issues using API-driven evidence gathering.\n\n**When to use:**\n- Site shows ERR_TOO_MANY_REDIRECTS\n- SSL/TLS configuration errors\n- DNS resolution problems\n- Cloudflare-related issues\n\n**Key features:**\n- Evidence-based investigation methodology\n- Comprehensive Cloudflare API reference\n- SSL/TLS mode troubleshooting (Flexible, Full, Strict)\n- DNS, cache, and firewall diagnostics\n- Agentic approach with optional helper scripts\n\n**🎬 Live Demo**\n\n\n\n---\n\n### **ui-designer** - UI Design System Extractor\n\nExtract design systems from reference UI images and generate implementation-ready design prompts.\n\n**When to use:**\n- Have UI screenshots/mockups to analyze\n- Need to extract color palettes, typography, spacing\n- Building MVP UI matching reference aesthetics\n- Creating consistent design systems\n- Generating multiple UI variations\n\n**Key features:**\n- Systematic design system extraction from images\n- Color palette, typography, component analysis\n- Interactive MVP PRD generation\n- Template-driven workflow (design system → PRD → implementation prompt)\n- Multi-variation UI generation (3 mobile, 2 web)\n- React + Tailwind CSS + Lucide icons\n\n**🎬 Live Demo**\n\n\n\n---\n\n### **ppt-creator** - Professional Presentation Creation\n\n> **Install**: `claude plugin install daymade-docs@daymade-skills` (suite-only — invoked as `daymade-docs:ppt-creator`)\n\nCreate persuasive, audience-ready slide decks from topics or documents with data-driven charts and dual-format PPTX output.\n\n**When to use:**\n- Creating presentations, pitch decks, or keynotes\n- Need structured content with professional storytelling\n- Require data visualization and charts\n- Want complete PPTX files with speaker notes\n- Building business reviews or product pitches\n\n**Key features:**\n- Pyramid Principle structure (conclusion → reasons → evidence)\n- Assertion-evidence slide framework\n- Automatic data synthesis and chart generation (matplotlib)\n- Dual-path PPTX creation (Marp CLI + document-skills:pptx)\n- Complete orchestration: content → data → charts → PPTX with charts\n- 45-60 second speaker notes per slide\n- Quality scoring with auto-refinement (target: 75/100)\n\n**🎬 Live Demo**\n\n\n\n---\n\n### **youtube-downloader** - YouTube Video & Audio Downloader\n\nDownload YouTube videos and audio using yt-dlp with robust error handling and automatic workarounds for common issues.\n\n**When to use:**\n- Downloading YouTube videos or playlists\n- Extracting audio from YouTube videos as MP3\n- Experiencing yt-dlp download failures or nsig extraction errors\n- Need help with format selection or quality options\n- Working with YouTube content in regions with access restrictions\n\n**Key features:**\n- Auto PO Token provider (Docker-first, browser fallback) for high-quality access\n- Browser-cookie verification for “not a bot” prompts (privacy-friendly)\n- Audio-only download with MP3 conversion\n- Format listing and custom format selection\n- Output directory customization\n- Proxy-aware downloads for restricted environments\n\n**🎬 Live Demo**\n\n\n\n---\n\n### **repomix-safe-mixer** - Secure Repomix Packaging\n\nSafely package codebases with repomix by automatically detecting and removing hardcoded credentials before packing.\n\n**When to use:**\n- Packaging code with repomix for distribution or sharing\n- Creating reference packages from proprietary codebases\n- Security concerns about accidentally exposing credentials\n- Pre-commit security checks for hardcoded secrets\n- Auditing codebases for credential exposure\n\n**Key features:**\n- Detects 20+ credential patterns (AWS, Supabase, Stripe, OpenAI, etc.)\n- Scan → Report → Pack workflow with automatic blocking\n- Standalone security scanner for pre-commit hooks\n- Environment variable replacement guidance\n- JSON output for CI/CD integration\n- Exclude patterns for false positive handling\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n---\n\n### **transcript-fixer** - ASR Transcription Correction\n\n> **Install**: `claude plugin install daymade-audio@daymade-skills` (suite-only — invoked as `daymade-audio:transcript-fixer`)\n\nCorrect speech-to-text (ASR/STT) errors with a Stage 1 dictionary pre-filter, a required Native AI whole-transcript pass, and an audio-backed human gate for unresolved wording, names, numbers, and entities.\n\n**When to use:**\n- Correcting meeting notes, lecture recordings, or interview transcripts\n- Fixing Chinese/English homophone errors and technical terminology\n- Reviewing one exact transcript with its original audio instead of searching a global queue\n- Improving future transcripts without turning one-off fixes into broad dictionary rules\n- Collaborating with teams on shared correction knowledge bases\n\n**Key features:**\n- Stage 1 + Native AI correction pipeline; Stage 1 alone is never completion\n- Exact-file review queue, deep-linked dashboard, timestamped audio playback, and machine-readable zero-pending readback\n- Conservative pattern learning: file-only, dictionary, roster, and context have separate admission rules\n- Domain-specific dictionaries (general, embodied_ai, finance, medical)\n- SQLite-based correction repository\n- Team collaboration with import/export\n- GLM API integration for AI corrections\n- Cost optimization through dictionary promotion\n\n**Example workflow:**\n```bash\n# Initialize and add corrections\nuv run scripts/fix_transcription.py --init\nuv run scripts/fix_transcription.py --add \"错误词\" \"正确词\" --domain general\n\n# Run full correction pipeline\nuv run scripts/fix_transcription.py --input meeting.md --stage 3\n\n# Open only this transcript's unresolved items and listen before deciding\nuv run scripts/review-dashboard/server.py --file \"/absolute/meeting.md\"\n\n# Read the human verdicts back; pending_total must be 0 before final delivery\nuv run scripts/fix_transcription.py \\\n --list-review --review-file \"/absolute/meeting.md\" \\\n --review-status all --json\n```\n\n📚 **Documentation**: See [daymade-audio/transcript-fixer/references/](./daymade-audio/transcript-fixer/references/) for workflow guides, SQL queries, troubleshooting, best practices, team collaboration, and API setup.\n\n**Requirements**: Python 3.10+ and uv. Native AI correction uses the active agent; an external API key is needed only for the optional agent-less API route.\n\n---\n\n### **video-comparer** - Video Comparison and Quality Analysis\n\nCompare two videos and generate interactive HTML reports with quality metrics and frame-by-frame visual comparisons.\n\n**When to use:**\n- Comparing original and compressed videos\n- Analyzing video compression quality and efficiency\n- Evaluating codec performance or bitrate reduction impact\n- Assessing before/after compression results\n- Quality analysis for video encoding workflows\n\n**Key features:**\n- Quality metrics calculation (PSNR, SSIM)\n- Frame-by-frame visual comparison with three viewing modes:\n - Slider mode: Drag to reveal differences\n - Side-by-side mode: Simultaneous display\n - Grid mode: Compact 2-column layout\n- Video metadata extraction (codec, resolution, bitrate, duration, file size)\n- Self-contained HTML reports (no server required, works offline)\n- Security features (path validation, resource limits, timeout controls)\n- Multi-platform FFmpeg support (macOS, Linux, Windows)\n\n**Example usage:**\n```bash\n# Basic comparison\npython3 scripts/compare.py original.mp4 compressed.mp4\n\n# Custom output and frame interval\npython3 scripts/compare.py original.mp4 compressed.mp4 -o report.html --interval 10\n\n# Batch processing\nfor original in originals/*.mp4; do\n compressed=\"compressed/$(basename \"$original\")\"\n output=\"reports/$(basename \"$original\" .mp4).html\"\n python3 scripts/compare.py \"$original\" \"$compressed\" -o \"$output\"\ndone\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [video-comparer/references/](./video-comparer/references/) for quality metrics interpretation, FFmpeg commands, and configuration options.\n\n**Requirements**: Python 3.8+, FFmpeg/FFprobe (install via `brew install ffmpeg`, `apt install ffmpeg`, or `winget install ffmpeg`)\n\n---\n\n### **qa-expert** - Comprehensive QA Testing Infrastructure\n\nEstablish world-class QA testing processes with autonomous LLM execution, Google Testing Standards, and OWASP security best practices.\n\n**When to use:**\n- Setting up QA infrastructure for new or existing projects\n- Writing standardized test cases following Google Testing Standards (AAA pattern)\n- Implementing security testing (OWASP Top 10 coverage)\n- Executing comprehensive test plans with automatic progress tracking\n- Filing bugs with proper P0-P4 severity classification\n- Calculating quality metrics and enforcing quality gates\n- Enabling autonomous LLM-driven test execution (100x speedup)\n- Preparing QA documentation for third-party team handoffs\n\n**Key features:**\n- **One-command initialization**: Complete QA infrastructure with templates, CSVs, and documentation\n- **Autonomous execution**: Master prompt enables LLM to auto-execute all tests, auto-track results, auto-file bugs\n- **Google Testing Standards**: AAA pattern compliance, 90% coverage targets, fail-fast validation\n- **OWASP security testing**: 90% Top 10 coverage with specific attack vectors\n- **Quality gates enforcement**: 100% execution, ≥80% pass rate, 0 P0 bugs, ≥80% code coverage\n- **Ground Truth Principle**: Prevents doc/CSV sync issues (test docs = authoritative source)\n- **Bug tracking**: P0-P4 classification with detailed repro steps and environment info\n- **Day 1 onboarding**: 5-hour guide for new QA engineers\n- **30+ LLM prompts**: Ready-to-use prompts for specific QA tasks\n- **Metrics dashboard**: Test execution progress, pass rate, bug analysis, quality gates status\n\n**Example usage:**\n```bash\n# Initialize QA project (creates full infrastructure)\npython3 scripts/init_qa_project.py my-app ./\n\n# Calculate quality metrics and gates status\npython3 scripts/calculate_metrics.py tests/TEST-EXECUTION-TRACKING.csv\n\n# For autonomous execution, copy master prompt from:\n# references/master_qa_prompt.md → paste to LLM → auto-executes 342 tests over 5 weeks\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [qa-expert/references/](./qa-expert/references/) for:\n- `master_qa_prompt.md` - Single command for autonomous execution (100x speedup)\n- `google_testing_standards.md` - AAA pattern, coverage thresholds, OWASP testing\n- `day1_onboarding.md` - 5-hour onboarding timeline for new QA engineers\n- `ground_truth_principle.md` - Preventing doc/CSV sync issues\n- `llm_prompts_library.md` - 30+ ready-to-use QA prompts\n\n**Requirements**: Python 3.8+\n\n**💡 Innovation**: The autonomous execution capability (via master prompt) enables LLM to execute entire test suites 100x faster than manual execution, with zero human error in tracking. Perfect for third-party QA handoffs - just provide the master prompt and they can start testing immediately.\n\n---\n\n### **prompt-optimizer** - Prompt Engineering with EARS Methodology\n\nTransform vague prompts into precise, well-structured specifications using EARS (Easy Approach to Requirements Syntax) - a methodology created by Rolls-Royce for converting natural language into testable requirements.\n\n**Methodology inspired by:** [阿星AI工作室 (A-Xing AI Studio)](https://mp.weixin.qq.com/s/yUVX-9FovSq7ZGChkHpuXQ), which pioneered combining EARS with domain theory grounding for practical prompt enhancement.\n\n**When to use:**\n- Converting loose requirements into structured specifications\n- Optimizing prompts for AI code generation or content creation\n- Breaking down vague feature requests into atomic, testable statements\n- Adding domain theory grounding to technical requirements\n- Transforming \"build X\" requests into detailed implementation specs\n- Learning prompt engineering best practices with proven frameworks\n\n**Key features:**\n- **EARS transformation**: 5 sentence patterns (ubiquitous, event-driven, state-driven, conditional, unwanted behavior)\n- **6-step optimization workflow**: Analyze → Transform → Identify theories → Extract examples → Enhance → Present\n- **Domain theory catalog**: 40+ frameworks mapped to 10 domains (productivity, UX, gamification, learning, e-commerce, security)\n- **Structured prompt framework**: Role/Skills/Workflows/Examples/Formats template\n- **Advanced techniques**: Multi-stakeholder requirements, non-functional specs, complex conditional logic\n- **Complete examples**: Procrastination app, e-commerce product page, learning dashboard, password reset\n- **Theory grounding**: GTD, BJ Fogg Behavior Model, Gestalt Principles, AIDA, Zero Trust, and more\n- **Progressive disclosure**: Bundled references (ears_syntax.md, domain_theories.md, examples.md)\n\n**Example usage:**\n```markdown\n# Before (vague)\n\"Build me a password reset feature\"\n\n# After EARS transformation (7 atomic requirements)\n1. When user clicks \"Forgot Password\", the system shall display email input field\n2. When user submits valid email, the system shall send password reset link valid for 1 hour\n3. When user clicks reset link, the system shall verify token has not expired\n4. When token is valid, the system shall display password creation form requiring minimum 12 characters, 1 uppercase, 1 number, 1 special character\n5. When user submits new password meeting requirements, the system shall hash password with bcrypt and invalidate reset token\n6. When user attempts password reset more than 3 times in 1 hour, the system shall block further attempts for 1 hour\n7. If reset token has expired, the system shall display error message and option to request new link\n\n# Enhanced with domain theories\n- Zero Trust Architecture (verify at each step)\n- Defense in Depth (rate limiting + token expiration + password complexity)\n- Progressive Disclosure (multi-step UX flow)\n\n# Full prompt includes Role, Skills, Workflows, Examples, Formats\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [prompt-optimizer/references/](./prompt-optimizer/references/) for:\n- `ears_syntax.md` - Complete EARS patterns and transformation rules\n- `domain_theories.md` - 40+ theories mapped to domains with selection guidance\n- `examples.md` - Full transformation examples with before/after comparisons\n\n**💡 Innovation**: EARS methodology eliminates ambiguity by forcing explicit conditions, triggers, and measurable criteria. Combined with domain theory grounding (GTD, BJ Fogg, Gestalt, etc.), it transforms \"build a todo app\" into a complete specification with behavioral psychology principles, UX best practices, and concrete test cases - enabling test-driven development from day one.\n\n---\n\n### **local-conversation-history** - Cross-Provider History Entry Point\n\n> **Install**: `claude plugin install daymade-claude-code@daymade-skills` (suite-only — invoked as `daymade-claude-code:local-conversation-history`)\n\nThe entry point above the four provider-and-action-specific history skills. It\nroutes a request to whichever one owns it — by platform (Claude Code, OpenAI\nCodex, Kimi CLI) and action (read evidence vs continue interrupted work) — and\nowns the one job none of them own alone: a single inventory spanning all three\nproviders.\n\n**When to use:**\n- The provider is unknown or plural — \"our history\", \"what have I been working on\"\n- Listing Kimi CLI sessions, which has no dedicated skill of its own\n- It is unclear whether the need is evidence or resumption\n- You remember this entry point by name\n\n**When not to use:** the platform *and* the action are both already clear. Load\nthat executor skill directly instead — this router adds a hop, not information.\n\n**Design**: a thin routing layer. It carries no parsing, no provider-specific\nflags beyond `--source`, and no copies of the executors' commands, so it cannot\ndrift into teaching a stale invocation.\n\n---\n\n### **read-claude-code-history** - Read Local Claude Code History\n\n> **Install**: `claude plugin install daymade-claude-code@daymade-skills` (suite-only — invoked as `daymade-claude-code:read-claude-code-history`)\n\nRead, search, and export Claude Code history across all active config homes and\nthe long-term archives registered in `~/.claude/history-sources.json`, without\nresuming or modifying the old task.\n\n**When to use:**\n- Recovering deleted or lost files from previous Claude Code sessions\n- Reconstructing one known Session as a chronological user/assistant handoff\n- Listing what the human actually typed, including queued mid-turn corrections\n- Searching for specific code across conversation history\n- Tracking file modifications across multiple sessions\n- Finding sessions containing specific keywords or implementations\n- Verifying date-bounded topics after a machine migration without trusting mtime\n\n**Key features:**\n- **Complete source set**: Search active homes and registered archives by default\n- **Provider boundary**: Claude-only by default; Codex requests route to `read-codex-history`\n- **Cross-project sweep**: `--all-projects` searches every Claude project when the project is unknown; `--exclude-session` skips self-matches\n- **Copy-safe union**: Search distinct records from every copy of a session ID without double-counting identical records\n- **Internal-time search**: Filter matching records by JSONL timestamps, never file mtime\n- **Structured search**: Cover messages, thinking, tools, results, queues, attachments, summaries, and original file-history paths\n- **Exact checkpoint recovery**: Union same-session copies and companion roots, then restore captured bytes after Write/Edit/shell changes, including binaries and pre-deletion checkpoints\n- **Fail-visible fidelity**: Label Write-only checkpoints as lower fidelity and abort when exact metadata points to missing bytes instead of silently guessing\n- **Statistics analysis**: Message counts, tool usage breakdown, file operations\n- **Batch operations**: Process multiple sessions with keyword filtering\n- **Streaming processing**: Handle large session files (>100MB) efficiently\n- **Read/continue separation**: Produces an evidence receipt and never resumes work itself\n\n**Example usage:**\n```bash\n# List recent sessions for a project\npython3 scripts/analyze_sessions.py list /path/to/project\n\n# Read one Session chronologically, preserving queued human input\npython3 scripts/read_claude_session.py --session --project /path/to/project --full\n\n# Export recent human wording grouped by Session\npython3 scripts/extract_user_messages.py ./user-words --days 7 --group-by session\n\n# Search sessions for keywords\npython3 scripts/analyze_sessions.py search /path/to/project \\\n \"ComponentName\" \"featureX\" --from-date 2026-03-01 --to-date 2026-04-30\n\n# Recover deleted files from the exact path printed by search\npython3 scripts/recover_content.py -k DeletedComponent -o ./recovered/\n\n# Search every project for multiple vanished job artifacts\npython3 scripts/analyze_sessions.py search --all-projects \\\n artifact-a.html artifact-b.html \\\n --exclude-session \n\n# Get session statistics\npython3 scripts/analyze_sessions.py stats /path/to/session.jsonl --show-files\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [daymade-claude-code/read-claude-code-history/references/](./daymade-claude-code/read-claude-code-history/references/) for:\n- `session_file_format.md` - JSONL structure and extraction patterns\n- `workflow_examples.md` - Detailed recovery and analysis workflows\n\n---\n\n### **docs-cleaner** - Documentation Consolidation\n\n> **Install**: `claude plugin install daymade-docs@daymade-skills` (suite-only — invoked as `daymade-docs:docs-cleaner`)\n\nConsolidate redundant documentation while preserving all valuable content.\n\n**When to use:**\n- Cleaning up documentation bloat across projects\n- Merging redundant docs covering the same topics\n- Reducing documentation sprawl after rapid development\n- Consolidating multiple files into authoritative sources\n\n**Key features:**\n- **Content preservation**: Never lose valuable information during cleanup\n- **Redundancy detection**: Identify overlapping documentation\n- **Smart merging**: Combine related docs while maintaining structure\n- **Validation**: Ensure consolidated docs are complete and accurate\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n---\n\n### **skills-search** - CCPM Skill Registry Search\n\nSearch, discover, install, and manage Claude Code skills from the CCPM (Claude Code Plugin Manager) registry.\n\n**When to use:**\n- Finding skills for specific tasks (e.g., \"find PDF skills\")\n- Installing skills by name\n- Listing currently installed skills\n- Getting detailed information about a skill\n- Managing your Claude Code skill collection\n\n**Key features:**\n- **Registry search**: Search CCPM registry with `ccpm search `\n- **Skill installation**: Install skills with `ccpm install `\n- **Version support**: Install specific versions with `@version` syntax\n- **Bundle installation**: Install pre-configured skill bundles (web-dev, content-creation, developer-tools)\n- **Multiple formats**: Supports registry names, GitHub owner/repo, and full URLs\n- **Skill info**: Get detailed skill information with `ccpm info `\n\n**Example usage:**\n```bash\n# Search for skills\nccpm search pdf # Find PDF-related skills\nccpm search \"code review\" # Find code review skills\n\n# Install skills\nccpm install skill-creator # From registry\nccpm install daymade/skill-creator # From GitHub\nccpm install skill-creator@1.0.0 # Specific version\n\n# List and manage\nccpm list # List installed skills\nccpm info skill-creator # Get skill details\nccpm uninstall pdf-processor # Remove a skill\n\n# Install bundles\nccpm install-bundle web-dev # Install web development skills bundle\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [daymade-skill/skills-search/SKILL.md](./daymade-skill/daymade-skill/skills-search/SKILL.md) for complete command reference\n\n**Requirements**: CCPM CLI (`npm install -g @daymade/ccpm`)\n\n---\n\n### **pdf-creator** - PDF Creation with Chinese Font Support\n\n> **Install**: `claude plugin install daymade-docs@daymade-skills` (suite-only — invoked as `daymade-docs:pdf-creator`)\n\nCreate professional PDF documents from markdown with proper Chinese typography using WeasyPrint.\n\n**When to use:**\n- Converting markdown to PDF for sharing or printing\n- Generating formal documents (legal filings, reports)\n- Ensuring correct Chinese font rendering\n\n**Key features:**\n- pandoc + WeasyPrint conversion pipeline (dual backend: WeasyPrint or headless Chrome)\n- Built-in Chinese/Japanese/Korean (CJK) font fallbacks with auto CJK code-block rendering\n- Theme system (default for formal docs, cjk-auto for content-driven tables, warm-terra for training materials, mobile for phone reading)\n- A4 layout defaults with print-friendly margins\n- Batch conversion scripts\n\n**Example usage:**\n```bash\nuv run --with weasyprint scripts/md_to_pdf.py input.md output.pdf\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [daymade-docs/pdf-creator/SKILL.md](./daymade-docs/pdf-creator/SKILL.md) for setup and workflow details.\n\n**Requirements**: Python 3.8+, `pandoc` (system install), `weasyprint` (or Chrome as fallback backend)\n\n---\n\n### **claude-md-progressive-disclosurer** - CLAUDE.md Optimization\n\n> **Install**: `claude plugin install daymade-claude-code@daymade-skills` (suite-only — invoked as `daymade-claude-code:claude-md-progressive-disclosurer`)\n\nOptimize user CLAUDE.md files using progressive disclosure to reduce context bloat while preserving critical rules.\n\n**When to use:**\n- CLAUDE.md is too long or repetitive\n- Need to move detailed procedures into references\n- Want to extract reusable workflows into skills\n\n**Key features:**\n- Section classification (keep/move/extract/remove)\n- Before/after line-count reporting\n- Reference file and pointer formats\n- Best-practice optimization workflow\n\n**Example usage:**\n```\n\"Optimize my ~/.claude/CLAUDE.md using progressive disclosure and propose a plan.\"\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [claude-md-progressive-disclosurer/SKILL.md](./daymade-claude-code/claude-md-progressive-disclosurer/SKILL.md).\n\n---\n\n### **promptfoo-evaluation** - Promptfoo LLM Evaluation\n\nConfigure and run LLM evaluations with Promptfoo for prompt testing and model comparisons.\n\n**When to use:**\n- Setting up prompt tests and eval configs\n- Comparing LLM outputs across providers\n- Adding custom assertions or LLM-as-judge grading\n\n**Key features:**\n- promptfooconfig.yaml templates\n- Python custom assertions\n- llm-rubric scoring guidance\n- Built-in preview (echo provider) workflows\n\n**Example usage:**\n```bash\nnpx promptfoo@latest init\nnpx promptfoo@latest eval\nnpx promptfoo@latest view\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [promptfoo-evaluation/references/promptfoo_api.md](./promptfoo-evaluation/references/promptfoo_api.md).\n\n**Requirements**: Node.js (Promptfoo via `npx promptfoo@latest`)\n\n---\n\n### **developing-ios-apps** - iOS App Development\n\n> **Install**: `claude plugin install daymade-macos@daymade-skills` (suite-only — invoked as `daymade-macos:developing-ios-apps`)\n\nBuild, configure, and debug iOS apps with XcodeGen, SwiftUI, and Swift Package Manager.\n\n**When to use:**\n- Setting up XcodeGen `project.yml`\n- Fixing SPM dependency or embed issues\n- Handling code signing and device deployment errors\n- Debugging camera/AVFoundation problems\n\n**Key features:**\n- XcodeGen project templates\n- SPM dynamic framework embedding fixes\n- Code signing and provisioning guidance\n- Device deployment and troubleshooting checklists\n\n**Example usage:**\n```bash\nxcodegen generate\nxcodebuild -destination 'platform=iOS Simulator,name=iPhone 17' build\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [developing-ios-apps/references/xcodegen-full.md](./daymade-macos/developing-ios-apps/references/xcodegen-full.md).\n\n**Requirements**: macOS + Xcode, XcodeGen\n\n---\n\n### **twitter-reader** - Twitter/X Content Fetching\n\nFetch Twitter/X post and article content. Single-post text goes through the\nfxtwitter mirror API (login-free, key-free, full long-form body); X Articles\nwith images go through `fetch_article.py`; the Jina API path remains as a\nfallback with a known intermittent-ban risk.\n\n**When to use:**\n- Retrieving tweet content for analysis or documentation\n- Fetching X Articles (long-form) with all images downloaded locally\n- Extracting images and media from posts\n- Batch downloading multiple tweets for reference\n\n**Key features:**\n- Single posts: fxtwitter mirror — no key, no login, full `tweet.text` body including note_tweet long-form\n- No JavaScript rendering or browser automation needed\n- No Twitter authentication required\n- Returns markdown-formatted content with metadata\n- Supports both individual and batch fetching\n- Includes author, timestamp, post text, images, and replies\n- Environment variable configuration for secure API key management\n\n**Example usage:**\n```bash\n# Single post text (preferred): fxtwitter mirror, no key needed\ncurl -sS \"https://api.fxtwitter.com/USER/status/TWEET_ID\" \\\n | python3 -c \"import json,sys; t=json.load(sys.stdin)['tweet']; print(t['text'])\"\n\n# X Article with images (full mode)\nuv run --with pyyaml python scripts/fetch_article.py \\\n \"https://x.com/USER/status/TWEET_ID\" ./Clippings\n\n# Jina fallback (intermittent — see SKILL.md risk note)\nexport JINA_API_KEY=\"your_api_key_here\"\ncurl \"https://r.jina.ai/https://x.com/USER/status/TWEET_ID\" \\\n -H \"Authorization: Bearer ${JINA_API_KEY}\"\n\n# Batch fetch multiple tweets\nscripts/fetch_tweets.sh \\\n \"https://x.com/user/status/123\" \\\n \"https://x.com/user/status/456\"\n\n# Fetch to file using Python script\npython scripts/fetch_tweet.py https://x.com/user/status/123 output.md\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [twitter-reader/SKILL.md](./twitter-reader/SKILL.md) for full details and URL format support.\n\n**Requirements**:\n- **curl** (pre-installed on most systems) — single-post path needs nothing else\n- **Python 3.6+** (for Python scripts)\n- **Jina.ai API key** (only for the Jina fallback; intermittent-ban risk, and the shared repo key is currently out of balance / 402)\n\n---\n\n### **macos-cleaner** - Intelligent macOS Disk Space Recovery\n\n> **Install**: `claude plugin install daymade-macos@daymade-skills` (suite-only — invoked as `daymade-macos:macos-cleaner`)\n\n**The safest way to reclaim disk space on macOS.** Start with targeted read-only diagnosis when a subsystem is already suspect—including Apple Content Caching—then analyze caches, application remnants, large files, and development environments only as needed.\n\n**Why macos-cleaner stands out:**\n- **Safety-First Philosophy**: Never deletes without explicit user confirmation. Every operation includes risk assessment (🟢 Safe / 🟡 Caution / 🔴 Keep).\n- **Intelligence Over Automation**: Analyzes first, explains thoroughly, then lets you decide. Unlike one-click cleaners that blindly delete, we help you understand what you're removing and why.\n- **Developer-Friendly**: Deep analysis of Docker, Homebrew, npm, pip caches - tools that generic cleaners miss.\n- **Transparent & Educational**: Every recommendation includes an explanation of what the file is, why it's safe (or not), and what happens if you delete it.\n- **Professional Quality**: Built by developers who know the pain of accidentally deleting important files. Includes comprehensive safety checks and Time Machine backup recommendations.\n\n**Our design principles:**\n1. **User Control First**: You make the decisions, we provide the insights\n2. **Explain Everything**: No mysterious deletions - full transparency on impact\n3. **Conservative Defaults**: When uncertain, we preserve rather than delete\n4. **Developer Context**: Understand development tool caches, not just system files\n5. **Hybrid Approach**: Combine script precision with visual tools (Mole integration)\n\n**When to use:**\n- Your Mac is running out of disk space (>80% full)\n- You're a developer with Docker/npm/pip/Homebrew caches piling up\n- Apple Content Caching reports `Caching needs more space`, an unlimited cache, or unexpectedly high `ActualCacheUsed`\n- You want to understand what's consuming space, not just delete blindly\n- You need to clean up after uninstalled applications\n- You prefer understanding over automation\n\n**Key features:**\n- **Smart Cache Analysis**: Categorizes system caches, app caches, logs by safety level\n- **Apple Content Caching**: Separates logical `CacheUsed` from physical `ActualCacheUsed`, verifies peers and protected services, and uses Apple's supported limit/deactivate/flush controls\n- **Application Remnant Detection**: Finds orphaned data from uninstalled apps with confidence scoring\n- **Large & Duplicate File Discovery**: Intelligent categorization plus optional read-only `fdupes` scans inside exact approved paths\n- **Development Environment Cleanup**: Docker images/containers/volumes, OrbStack, Homebrew, npm, and pip; Docker build cache is measured but prune-based deletion is out of scope\n- **Interactive Safe Deletion**: Batch confirmation, selective deletion, undo-friendly (uses Trash when possible)\n- **Before/After Reports**: Track space recovery with detailed breakdown\n- **Mole Integration**: Seamless workflow with visual cleanup tool for GUI preferences\n- **Risk Categorization**: Every item labeled with safety level and explanation\n- **Time Machine Awareness**: Recommends backups before large deletions (>10 GB)\n\n**What makes us different:**\n- ✅ **Trust Through Transparency**: Other cleaners hide what they delete. We show everything and explain why.\n- ✅ **Developer-Centric**: We clean Docker, not just browser caches. We understand `.git` directories, `node_modules`, and build artifacts.\n- ✅ **Safety Checks Built-In**: Protection against deleting system files, user data, credentials, active databases, or files in use.\n- ✅ **Educational**: Learn what's safe to delete and why, so you can maintain your Mac confidently.\n- ❌ **Not a One-Click Solution**: Nothing changes until you approve a scoped command plan. When you ask Claude to execute it, only those confirmed actions run, followed by before/after verification.\n\n**Example usage:**\n```bash\n# Install the Apple platform suite\nclaude plugin install daymade-macos@daymade-skills\n\n# Ask Claude Code to analyze your Mac\n\"My Mac is running out of space, help me analyze what's using storage\"\n\n# Claude will:\n# 1. Route a named suspect to targeted read-only diagnosis; scan broadly only if the source is unknown\n# 2. Present categorized findings with safety levels\n# 3. Explain each category (caches, remnants, large files, dev tools)\n# 4. Recommend cleanup approach\n# 5. Execute ONLY what you confirm\n\n# Example analysis output:\n📊 Disk Space Analysis\n━━━━━━━━━━━━━━━━━━━━━━━━\nTotal: 500 GB\nUsed: 450 GB (90%)\nAvailable: 50 GB (10%)\n\n🟢 Safe to Clean (95 GB):\n - System caches: 45 GB (apps regenerate automatically)\n - Homebrew cache: 5 GB (reinstalls when needed)\n - npm cache: 3 GB (safe to clear)\n - Old logs: 8 GB (diagnostic data only)\n - Trash: 34 GB (already marked for deletion)\n\n🟡 Review Recommended (62 GB):\n - Large downloads: 38 GB (may contain important files)\n - App remnants: 8 GB (verify apps are truly uninstalled)\n - Docker images: 12 GB (may be in use)\n - Old .git repos: 4 GB (verify project is archived)\n\n🔴 Keep Unless Certain (0 GB):\n - No high-risk items detected\n\nRecommendation: Start with 🟢 Safe items (95 GB), then review 🟡 items together.\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [macos-cleaner/references/](./daymade-macos/macos-cleaner/references/) for:\n- `apple_content_caching.md` - Targeted Apple Content Caching diagnosis and supported repair\n- `cleanup_targets.md` - Detailed explanations of every cleanup target\n- `mole_integration.md` - How to combine scripts with Mole visual tool\n- `safety_rules.md` - Comprehensive safety guidelines and what to never delete\n\n**Requirements**:\n- **Python 3.6+** (pre-installed on macOS)\n- **macOS** (tested on macOS 10.15+)\n- **Optional**: [Mole](https://github.com/tw93/Mole) for visual cleanup interface\n\n---\n\n### **fact-checker** - Document Fact-Checking\n\nVerify factual claims in documents using web search and official sources, then propose corrections with user confirmation.\n\n**When to use:**\n- Fact-checking documents for accuracy\n- Verifying AI model specifications and technical documentation\n- Updating outdated information in documents\n- Validating statistical claims and benchmarks\n- Checking API capabilities and version numbers\n\n**Key features:**\n- Web search integration with authoritative sources\n- AI model specification verification\n- Technical documentation accuracy checks\n- Statistical data validation\n- Automated correction reports with user confirmation\n- Supports general factual statements and technical claims\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install fact-checker@daymade-skills\n\n# Fact-check a document\n\"Please fact-check this section about AI model capabilities\"\n\n# Verify technical specs\n\"Check if these Claude model specifications are still accurate\"\n\n# Update outdated info\n\"Verify and update the version numbers in this documentation\"\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [fact-checker/SKILL.md](./fact-checker/SKILL.md) for full workflow and claim types.\n\n**Requirements**:\n- Web search access (via Claude Code)\n\n---\n\n### **skill-reviewer** - Skill Quality Review & Improvement\n\nReview and improve Claude Code skills against official best practices with three powerful modes.\n\n**When to use:**\n- Validating your own skills before publishing\n- Evaluating others' skill repositories\n- Contributing improvements to open-source skills via auto-PR\n- Ensuring skills follow marketplace standards\n\n**Key features:**\n- **Self-review mode**: Run the bundled reviewer backed by canonical skill-creator validation\n- **External review mode**: Clone, analyze, and generate improvement reports\n- **Auto-PR mode**: Fork → improve → submit PR with additive-only changes\n- **Evaluation checklist**: Frontmatter, instructions, resources verification\n- **Additive-only principle**: Never delete files when contributing to others\n- **PR guidelines**: Tone recommendations and professional templates\n- **Reliable automation**: Distinguishes review findings from invocation/runtime failures with structured JSON output\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install daymade-skill@daymade-skills\n\n# Self-review your skill\n\"Validate my skill at ~/my-skills/my-awesome-skill\"\n\n# Review external skill repository\n\"Review the skills at https://github.com/user/skill-repo\"\n\n# Auto-PR improvements\n\"Fork, improve, and submit PR for https://github.com/user/skill-repo\"\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [daymade-skill/skill-reviewer/references/](./daymade-skill/skill-reviewer/references/) for:\n- `evaluation_checklist.md` - Complete skill evaluation criteria\n- `pr_template.md` - Professional PR description template\n\n---\n\n### **github-contributor** - Git",
"bytes": 60000,
"sha": "8eee8c7c2335fcd4c06fb049cfb531d02ca42388c9332a054cb46ab6f066d2f9",
"repo_slug": "daymade/claude-code-skills",
"fonte": "repo",
"truncated": false,
"api": "https://agentalog.com/api/listings/skl_daymade_claude_code_skills_youtube_downl_d9d52735/readme"
}