{
  "markdown": "# Spec Driven\n\nAn orchestrator-first collection of Agent Skills for **spec-driven development**: the [`orchestrator`](docs/en/orchestrator.md) skill turns a PRD or idea into approved SPECs, tracked GitHub Issues, TDD-implemented slices, QA gates, and reviewed PRs — across Claude Code, OpenCode, Devin, Cursor, and other runtimes.\n\n[![skills.sh](https://skills.sh/b/afonsoft/skills)](https://skills.sh/afonsoft/skills)\n[![Spec Validation](https://github.com/afonsoft/skills/actions/workflows/skills-validate.yml/badge.svg?job=validate-spec)](https://github.com/afonsoft/skills/actions/workflows/skills-validate.yml)\n[![Quality Check](https://github.com/afonsoft/skills/actions/workflows/skills-validate.yml/badge.svg?job=validate-quality)](https://github.com/afonsoft/skills/actions/workflows/skills-validate.yml)\n[![Security Scan](https://github.com/afonsoft/skills/actions/workflows/skills-validate.yml/badge.svg?job=security-scan)](https://github.com/afonsoft/skills/actions/workflows/skills-validate.yml)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Agent Skills Spec](https://img.shields.io/badge/Agent%20Skills-Spec-blue)](https://agentskills.io)\n[![DeepWiki](https://img.shields.io/badge/DeepWiki-afonsoft%2Fskills-blue)](https://deepwiki.com/afonsoft/skills)\n[![Made in Brazil](https://img.shields.io/badge/Made%20in-Brazil-green)](https://github.com/afonsoft/skills)\n[![Last Commit](https://img.shields.io/github/last-commit/afonsoft/skills)](https://github.com/afonsoft/skills/commits/main)\n[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](https://github.com/afonsoft/skills/pulls)\n[![Open Source](https://img.shields.io/badge/Open%20Source-%E2%9D%A4-brightgreen)](https://github.com/afonsoft/skills)\n\n## 🚀 Overview\n\nThis repository implements **Spec-Driven Development (SDD)** for AI agents, following the **Agent Skills Specification** (agentskills.io). At the center is the [`orchestrator`](docs/en/orchestrator.md) skill: a control loop that audits preconditions, provisions the agent harness, consolidates domain language into approved SPEC SDDs (`.specs/SPEC-*.md`), fragments work into GitHub Issues, and delegates implementation, review, QA, and documentation to specialized skills — never doing complex work itself.\n\nEvery other skill in the catalog is a delegation target in that loop. Instead of generic prompts, each skill provides structured patterns, constraints, and reference materials that allow agents to perform complex software engineering tasks with production-grade quality.\n\n## 🧭 The Orchestrator\n\nThe [`orchestrator`](docs/en/orchestrator.md) is the entry point and central control skill for agent-driven projects. Invoke it with `/spec-driven` (alias for `/spec-driven:orchestrator`, or *\"use the orchestrator skill\"*) and it runs a continuous loop, delegating complex work to specialized skills and persisting state in `.claude/memory/orchestrator_stats.md`.\n\n```mermaid\nflowchart TD\n    A[Phase -1: Framework Update] --> B[Phase 0: Governance]\n    B --> C[Phase 1: Discovery]\n    C --> D[Phase 2: Audit]\n    D --> E[Phase 3: GitHub Fragmentation]\n    E --> F[Phase 4: Implementation Loop]\n    F --> G[Phase 5: Verification & QA]\n    G --> H[PR / Merge]\n\n    C -->|PRD only| I[/scaffold-mvp\\]\n    C -->|needs spec| J[/write-specs\\]\n    D -->|P2 gap| K[/improve-codebase-architecture\\]\n    E --> L[/create-issues\\]\n    F -->|per slice| M[/execute-specs\\]\n    F -->|bug| N[/diagnose\\]\n    G --> O[/qa-analyst\\]\n    G --> P[/architecture\\]\n    G --> R[/gap-analysis\\]\n\n    S[/migration-planner\\] -.->|domain plans| J\n    T[/web-design-guidelines\\] -.->|finding groups| J\n```\n\nThe orchestrator advances automatically between phases once validation passes. It only pauses for escalation gates (security, schema, public APIs, data changes), validation failures, or an explicit user request to stop.\n\n## 🛠️ Skill Catalog & Correlation\n\nThe skills are organized around the orchestrator's pipeline: **Harness Engineering**, **Orchestration & Delivery**, **Code Quality & Review**, **Frontend & Design**, **Extensibility & Integration**, and **MCP Integrations**.\n\n### 🏗️ Harness Engineering\n*Foundation for creating and managing AI agents.*\n- **[`create-agent-harness`](docs/en/create-agent-harness.md)**: The starting point. Use this to bootstrap a complete agent environment (CLAUDE.md, rules, skills) in any repo.\n- **[`create-readme`](docs/en/create-readme.md)**: Professionalizes the repository landing page. Generates evidence-based READMEs and SemVer-compliant CHANGELOGs.\n- **[`observability-and-instrumentation`](docs/en/observability-and-instrumentation.md)**: Once the harness is set, use this to ensure the agent's actions and the application's behavior are visible and diagnosable in production.\n\n### 🧭 Orchestration & Delivery\n*Planning, execution, verification, and documentation for agent-driven projects.*\n- **[`orchestrator`](docs/en/orchestrator.md)**: Central control skill. Audits preconditions, creates documentation, reconciles open GitHub Issues, turns gaps into Issues, and coordinates execution, tests, QA, and PR in a continuous loop. Persists state in `.claude/memory/orchestrator_stats.md` and auto-continues to the next slice.\n- **[`write-specs`](docs/en/write-specs.md)**: Interviews the user in Portuguese to consolidate domain language and produce an approved `.specs/SPEC-{YYYYMMDD}-{feature}.md` before implementation.\n- **[`scaffold-mvp`](docs/en/scaffold-mvp.md)**: Bootstraps a new .NET/Blazor/Angular repository after domain/spec alignment. Installs the agent harness, proposes a productive stack, and generates the initial project skeleton, AD-0001, and stubs.\n- **[`create-issues`](docs/en/create-issues.md)**: Turns approved gaps, roadmap, and specs into GitHub Issues with vertical slices and dependency links. Uses the `references/spec-sdd-template.md` structure when creating Issues from SPEC SDDs.\n- **[`execute-specs`](docs/en/execute-specs.md)**: Test-driven development using the approved SPEC SDD as the source of truth. Red-green-refactor one vertical slice at a time.\n- **[`qa-analyst`](docs/en/qa-analyst.md)**: Full QA cycle — requirements analysis, test planning, test cases, execution, bug reports, and process improvement.\n- **[`diagnose`](docs/en/diagnose.md)**: Disciplined diagnosis and re-validation loop for hard bugs and performance regressions — tight feedback loops, ranked falsifiable hypotheses, stack playbooks for .NET/Angular/Python/React, agent self-debug, and AI workflow audit.\n- **[`improve-codebase-architecture`](docs/en/improve-codebase-architecture.md)**: Finds architectural deepening opportunities by reading `.claude/CONTEXT.md`, `.claude/MEMORY.md`, and `docs/architecture/`, and produces an HTML report.\n- **[`architecture`](docs/en/architecture.md)**: The single owner of `docs/architecture/`. Routes ADRs, design docs, and diagrams to `drawio-architecture`, `mermaid-architecture`, and the optional `archify` skill (interactive HTML, used only when already installed — never installed at runtime), then ends with the `gap-analysis` evidence audit it owns.\n- **[`gap-analysis`](docs/en/gap-analysis.md)**: Evidence-backed audit of AS-IS code vs. TO-BE specs/docs. Confirmed gaps become Draft SPECs (`write-specs`), a tracked Epic with slices (`create-issues`), and orchestrated execution (`orchestrator`) — behind an explicit approval gate.\n- **[`migration-planner`](docs/en/migration-planner.md)**: Evidence-based legacy → .NET migration planning with the Strangler Fig pattern. Researches the codebase, maps bounded contexts, designs seams (YARP, DI, EF Core dual-write, Blazor/MAUI), writes per-domain plans + roadmap in `migration-plan/`, then converts each domain into Draft SPECs (`write-specs`), a tracked Epic (`create-issues`), and orchestrated execution (`orchestrator`) — behind an explicit approval gate. Default targets: Blazor WebAssembly, .NET MAUI, ASP.NET Core.\n\n### 💎 Code Quality & Review\n*Ensuring the output meets professional standards.*\n- **[`code-review-and-quality`](docs/en/code-review-and-quality.md)**: The primary gatekeeper. Performs multi-axis reviews (correctness, security, performance) before any code is merged.\n- **[`quality-test-implementation`](docs/en/quality-test-implementation.md)**: The whole-repo quality intervention. Fixes static-analysis warnings (Roslyn/Sonar, SpotBugs/Checkstyle, Bandit/Ruff), resolves security CVEs, and applies SOLID/DDD/Clean Architecture across .NET, Java, or Python repositories.\n- **[`sonarqube-autofix`](docs/en/sonarqube-autofix.md)**: The automated auditor. Integrates with SonarQube to identify and fix technical debt and smells systematically.\n\n### 🔬 Security & Reverse Engineering\n*Authorized analysis of shipped artifacts, protocols, and adversarial surfaces.*\n- **[`reverse-engineer`](docs/en/reverse-engineer.md)**: Consolidated RE hub merging REA (`rea-agents` CLI/MCP, evidence-ledger workflows) with the reverse-skill domain pack — 40+ guides covering binaries, APK/mobile, JS/Electron, .NET, firmware, protocols, malware, CTF, and authorized pentest lanes. Includes a deterministic router (`master-route.sh`), case/scope gates (`case-init.sh`, `auth.status=granted` required before ACT), a per-module tool-readiness checker (`check-tools.sh`), and an REA installer (`install-rea.sh`).\n\n### 🎨 Frontend & Design\n*Shaping user-facing interfaces with mobile-first, responsive craft.*\n- **[`design`](docs/en/design.md)**: Frontend UI design for Angular, React, and Blazor. Covers mobile-first responsive layouts, typography, color, components, accessibility, motion, design tokens, Bootstrap/Tailwind CSS examples, and production hardening.\n- **[`web-design-guidelines`](docs/en/web-design-guidelines.md)**: Web design validation, merged from vercel-labs/web-design-guidelines + lighthouse-95. Audits UI files against the complete interface-guidelines rule set (`file:line` findings, with Angular/Blazor mappings) and/or verifies deployed pages against Lighthouse 95+ (mobile + desktop, 3-run verdicts), then converts confirmed pendencies into Draft SPECs (`write-specs`), an Epic + Issues (`create-issues`), and orchestrated fixes (`orchestrator`).\n\n### 🔌 Extensibility & Integration\n*Expanding what the agent can actually do.*\n- **[`building-mcp-servers`](docs/en/building-mcp-servers.md)**: The power-user tool. Teaches agents how to build their own Model Context Protocol (MCP) servers to connect to any API or database.\n- **[`drawio-architecture`](docs/en/drawio-architecture.md)**: Visual intelligence. Merges architecture diagram authoring with the official draw.io MCP server for automated system design.\n- **[`mermaid-architecture`](docs/en/mermaid-architecture.md)**: Diagrams as code. Generates high-contrast, production-ready Mermaid architecture diagrams, workflows, and C4 models saved directly in `docs/architecture/`.\n- **[`obsidian`](docs/en/obsidian.md)**: Obsidian vault operations. Runs the Obsidian CLI (read/create/search/manage notes, tasks, properties), builds Bases (.base views/filters/formulas), writes Obsidian Flavored Markdown (wikilinks, embeds, callouts), and develops/debugs plugins and themes.\n\n### 🔗 MCP Integrations\n*Configuring, authenticating, and using external MCP servers across all supported agent platforms.*\n- **[`composio-mcp`](docs/en/composio-mcp.md)**: Connects AI agents to 1000+ external apps (Gmail, GitHub, Slack, Notion, Linear, Jira) via Composio. CLI-first path (`ak_*` project key) with MCP fallback (`ck_*` consumer key via `x-consumer-api-key` header). Includes multi-platform setup script (handles `serverUrl` vs `url`, `mcp` vs `mcpServers`, `environment` vs `env` across Claude Code/Desktop, Cursor, Devin CLI/Desktop, OpenCode, Antigravity IDE/CLI, OpenClaw), verify script, per-platform config reference, and cross-platform quirks matrix.\n- **[`notebooklm-mcp`](docs/en/notebooklm-mcp.md)**: Google NotebookLM (Gemini Notebook) integration via the `nlm` CLI and `notebooklm-mcp` server. Desktop `nlm login` is the default auth path; headless fallbacks (OpenClaw CDP or user-provided manual `cookies.txt`) require explicit user approval. Credentials/cookies are never logged, copied, or forwarded. Multi-platform setup script covering all 8 supported agent platforms, plus verify, auth guide, per-platform config reference, and cross-platform quirks matrix.\n- **[`wordpress-mcp`](docs/en/wordpress-mcp.md)**: Expose WordPress to AI agents over MCP using pinned, verified plugins. Three paths: (A) `wordpress/mcp-adapter` official plugin from GitHub releases, (B) AI Engine plugin from wordpress.org, and (C) wp-mcp-ultimate (community, opt-in, requires explicit source review and user approval). High-privilege actions require explicit approval; WordPress posts/comments/user submissions are treated as untrusted data. Includes hardened WP-CLI install scripts with checksum support, Application Password / Bearer Token / OAuth setup, per-platform MCP config, endpoint verification, and troubleshooting.\n\n> 📚 **Documentation:** each skill has a dedicated doc page in [`docs/en/`](docs/en/) (English) and [`docs/pt-br/`](docs/pt-br/) (Português).\n\n## 🛡️ Security Audits\n\nLatest results from the [skills.sh](https://skills.sh) third-party audit (**Gen Agent Trust Hub**, **Socket**, **Snyk**). Click **View** to see the full report for a skill.\n\n> **Updated:** 2026-10-08\n>\n> **Mitigations applied** (PR #11): `notebooklm-mcp`, `orchestrator`, and `wordpress-mcp` were hardened with explicit-approval gates, pinned installs, credential isolation, untrusted-content handling, and audit logging. The latest scan still flags `architecture`, `notebooklm-mcp`, and `wordpress-mcp` as 🟡 medium risk on Gen Agent Trust Hub, and `notebooklm-mcp` and `sonarqube-autofix` each carry 1 Socket alert.\n\n| Skill | Gen Agent Trust Hub | Socket alerts | Snyk | Details |\n|-------|---------------------|---------------|------|---------|\n| `architecture` | 🟡 medium | 0 | 🟢 low | [View](https://skills.sh/afonsoft/skills/architecture) |\n| `building-mcp-servers` | ✅ safe | 0 | 🟢 low | [View](https://skills.sh/afonsoft/skills/building-mcp-servers) |\n| `code-review-and-quality` | ✅ safe | 0 | 🟡 medium | [View](https://skills.sh/afonsoft/skills/code-review-and-quality) |\n| `composio-mcp` | ✅ safe | 0 | 🟡 medium | [View](https://skills.sh/afonsoft/skills/composio-mcp) |\n| `create-agent-harness` | ✅ safe | 0 | 🟢 low | [View](https://skills.sh/afonsoft/skills/create-agent-harness) |\n| `create-issues` | ✅ safe | 0 | 🟡 medium | [View](https://skills.sh/afonsoft/skills/create-issues) |\n| `create-readme` | ✅ safe | 0 | 🟢 low | [View](https://skills.sh/afonsoft/skills/create-readme) |\n| `design` | ✅ safe | 0 | 🟢 low | [View](https://skills.sh/afonsoft/skills/design) |\n| `diagnose` | ✅ safe | 0 | 🟢 low | [View](https://skills.sh/afonsoft/skills/diagnose) |\n| `drawio-architecture` | ✅ safe | 0 | 🟢 low | [View](https://skills.sh/afonsoft/skills/drawio-architecture) |\n| `execute-specs` | ✅ safe | 0 | 🟢 low | [View](https://skills.sh/afonsoft/skills/execute-specs) |\n| `gap-analysis` | ✅ safe | 0 | 🟡 medium | [View](https://skills.sh/afonsoft/skills/gap-analysis) |\n| `improve-codebase-architecture` | ✅ safe | 0 | 🟢 low | [View](https://skills.sh/afonsoft/skills/improve-codebase-architecture) |\n| `mermaid-architecture` | ✅ safe | 0 | 🟢 low | [View](https://skills.sh/afonsoft/skills/mermaid-architecture) |\n| `migration-planner` | ✅ safe | 0 | ⚪ pending | [View](https://skills.sh/afonsoft/skills/migration-planner) |\n| `notebooklm-mcp` | 🟡 medium | 1 | 🟢 low | [View](https://skills.sh/afonsoft/skills/notebooklm-mcp) |\n| `observability-and-instrumentation` | ✅ safe | 0 | 🟢 low | [View](https://skills.sh/afonsoft/skills/observability-and-instrumentation) |\n| `obsidian` | ✅ safe | 0 | 🟢 low | [View](https://skills.sh/afonsoft/skills/obsidian) |\n| `orchestrator` | ✅ safe | 0 | 🟡 medium | [View](https://skills.sh/afonsoft/skills/orchestrator) |\n| `qa-analyst` | ✅ safe | 0 | 🟡 medium | [View](https://skills.sh/afonsoft/skills/qa-analyst) |\n| `quality-test-implementation` | ✅ safe | 0 | 🟢 low | [View](https://skills.sh/afonsoft/skills/quality-test-implementation) |\n| `reverse-engineer` | ⚪ pending | 0 | ⚪ pending | [View](https://skills.sh/afonsoft/skills/reverse-engineer) |\n| `scaffold-mvp` | ✅ safe | 0 | 🟢 low | [View](https://skills.sh/afonsoft/skills/scaffold-mvp) |\n| `sonarqube-autofix` | ✅ safe | 1 | 🟡 medium | [View](https://skills.sh/afonsoft/skills/sonarqube-autofix) |\n| `web-design-guidelines` | ✅ safe | 0 | ⚪ pending | [View](https://skills.sh/afonsoft/skills/web-design-guidelines) |\n| `wordpress-mcp` | 🟡 medium | 0 | 🟡 medium | [View](https://skills.sh/afonsoft/skills/wordpress-mcp) |\n| `write-specs` | ✅ safe | 0 | 🟢 low | [View](https://skills.sh/afonsoft/skills/write-specs) |\n---\n\n## 📦 Installation\n\n### ⚡ via skills.sh (Recommended)\nThe fastest way to install and auto-detect your environment.\n```bash\nnpx skills add afonsoft/skills\n```\n\n### 🧩 via Claude Code plugin\nInstalls skills **and** slash commands natively (no `install.sh` needed):\n```text\n/plugin marketplace add afonsoft/skills\n/plugin install spec-driven@afonsoft\n```\nCommands are namespaced by the plugin name: `/spec-driven:orchestrator` and `/spec-driven:<skill>` for each skill.\n\n### 🤖 via Codex plugin marketplace\nThe repo ships a Codex plugin manifest (`.codex-plugin/plugin.json`) and a repo marketplace catalog (`.agents/plugins/marketplace.json`):\n```bash\ncodex plugin marketplace add afonsoft/skills\n```\nThen install `spec-driven` from the Plugins Directory, or invoke skills directly with `$<skill>` — Codex discovers them from the bundled `skills/` directory. Skills are also discovered from `.agents/skills/` (repo scope) and `~/.agents/skills/` (user scope, via `install.sh --codex`).\n\n### 🌐 via OpenCode HTTP catalog\nAdd the catalog URL to any `opencode.json` — OpenCode downloads `skills/index.json` and refreshes each skill automatically when its `version` changes:\n```jsonc\n{\n  \"$schema\": \"https://opencode.ai/config.json\",\n  \"skills\": [\"https://raw.githubusercontent.com/afonsoft/skills/main/skills/\"]\n}\n```\nRegenerate the catalog after skill changes with `python3 scripts/build-opencode-catalog.py`. OpenCode also discovers skills from `.opencode/skills/`, `.claude/skills/`, and `.agents/skills/` in project scope.\n\n### 🖥️ via install.sh (local clone)\nCopies the skills into each IDE's skills directory and generates slash commands:\n```bash\n./install.sh --all        # all supported IDEs/CLIs + slash commands\n./install.sh --claude     # Claude Code only\n./install.sh --opencode   # OpenCode only\n./install.sh --devin      # Devin Desktop + Devin CLI\n./install.sh --cursor     # Cursor only\n./install.sh --codex      # OpenAI Codex CLI only\n./install.sh --agy        # Google Antigravity CLI only\n./install.sh --aider      # Aider only\n./install.sh --cline      # Cline only\n./install.sh --continue   # Continue only\n./install.sh --grok       # Grok CLI only\n./install.sh --kimi       # Kimi Code CLI only\n./install.sh --kiro       # Kiro CLI only\n./install.sh --qwen       # Qwen Code only\n./install.sh --dry-run    # preview without changing anything\n```\n\nSlash commands follow each CLI's own convention — some clients do not accept `:` in command names:\n\n| CLI | Invocation | Mechanism |\n|-----|-----------|-----------|\n| Claude Code, OpenCode, Devin Desktop | `/spec-driven` and `/spec-driven:<skill>` | `commands/spec-driven:<skill>.md` shims |\n| Devin CLI | `/<skill>` | skills are native slash commands — no shims needed; installed to `~/.config/devin/skills/` |\n| Qwen Code | `/spec-driven` and `/spec-driven:<skill>` | `commands/spec-driven/<skill>.md` (namespace via subdirectory) |\n| Codex CLI | `/prompts:spec-driven-<skill>` | `prompts/spec-driven-<skill>.md` (custom prompts are deprecated — prefer `$<skill>`/`/skills`) |\n| Cline | `/spec-driven-<skill>` | `~/.cline/data/workflows/` workflows |\n| Continue | `/spec-driven-<skill>` | `~/.continue/prompts/` with `invokable: true` |\n| Grok CLI | `/spec-driven-<skill>` | `~/.agents/commands/` (skills also appear as `/<skill>`) |\n| agy, Kimi, Kiro | `/<skill>` (Kimi: `/skill:<skill>`) | skills are native slash commands — no shims needed |\n| Aider | `/read ~/.aider/skills/<skill>/SKILL.md` | no file-based commands; an index is written to `~/.aider/spec-driven-skills.md` |\n\nReinstalling removes legacy `/architecture:<skill>` shims automatically.\n\n## 📣 Publish on Skill Directories\n\n### SkillsLLM\n[SkillsLLM](https://skillsllm.com/) indexes open-source skills for Claude Code, Codex CLI, and ChatGPT. The scraper discovers repos daily via GitHub topics (`claude-code`, `ai-agent`, `mcp-server`, `agent-skills`, `skill-md`) and `SKILL.md` files. To list this collection:\n\n1. Sign in with GitHub at [Submit a Skill](https://skillsllm.com/submit)\n2. Submit the repository URL: `https://github.com/afonsoft/skills`\n3. The scraper validates, fetches metadata, runs a security scan (Semgrep + npm audit + pip-audit), and adds it to the catalog within 24 hours\n\n> **Note:** SkillsLLM's automated discovery filters for repos with 100+ stars. Manual submission via the form above bypasses that filter — the repo is then scanned and listed regardless of star count. The GitHub topics and description are already set so the scraper can categorize the skills correctly.\n\n### Awesome Skills\n[Awesome Skills](https://awesomeskill.ai/) discovers open-source `SKILL.md` skills from GitHub via its **Awesome List Import**. Each `skills/<name>/SKILL.md` directory becomes a separate listing with slug `afonsoft-skills-<name>`. Submit the repository URL through the site's **Submit a Skill** form:\n\n- **Repository URL:** `https://github.com/afonsoft/skills`\n- **Branch:** `main`\n- **Skills Path:** `/skills`\n\nEach skill's `description` frontmatter includes `afonsoft` so the collection is discoverable at [awesomeskill.ai/search?q=afonsoft](https://awesomeskill.ai/search?q=afonsoft). The Awesome Skills search API matches against skill `name` and `description` only (not owner, repo, or tags), so the `afonsoft` attribution in each description is what makes the search return results.\n\n### SkillHub\n[SkillHub](https://www.skill-marketplace.com/) aggregates skills from GitHub sources. Open **Sources** → **Add Source**, then use:\n\n- **Name:** `afonsoft/skills`\n- **Repository URL:** `https://github.com/afonsoft/skills`\n- **Source Type:** `GitHub Repo`\n- **Branch:** `main`\n- **Skills Path:** `/skills`\n\nSkillHub imports the collection from this source and lists each valid `SKILL.md` directory in its marketplace.\n\n### LobeHub Skills Marketplace\n[LobeHub](https://lobehub.com/skills) is the world's largest skills marketplace (100,000+ skills). Publishing is CLI-driven (no web form). Each skill gets identifier `afonsoft-skills-<name>`.\n\n**One-time setup (per machine, requires Node.js >= 22):**\n```bash\nnpx -y @lobehub/market-cli login           # browser OAuth\nnpx -y @lobehub/market-cli github connect  # verify GitHub ownership\n```\n\n**Publish all skills locally:**\n```bash\n./publish-lobehub.sh          # publishes all skills\n./publish-lobehub.sh --dry-run # preview without publishing\n```\n\n**Publish a single skill:**\n```bash\nnpx -y @lobehub/market-cli skill publish --dir skills/<skill-name> --identifier afonsoft-skills-<skill-name>\n```\n\n**Automatic publishing via GitHub Actions:**\n\nA workflow (`.github/workflows/lobehub-publish.yml`) publishes all skills when a `v*` tag is pushed, a release is published, or when triggered manually (`workflow_dispatch`). To enable it, add two repository secrets:\n\n1. **`LOBEHUB_M2M_CREDENTIALS`** — contents of `~/.lobehub-market/credentials.json` (device registration)\n2. **`LOBEHUB_USER_CREDENTIALS`** — contents of `~/.lobehub-market/user-credentials.json` (OAuth tokens)\n\n```bash\n# After running lhm login + lhm github connect locally:\ngh secret set LOBEHUB_M2M_CREDENTIALS < ~/.lobehub-market/credentials.json\ngh secret set LOBEHUB_USER_CREDENTIALS < ~/.lobehub-market/user-credentials.json\n```\n\nThe workflow restores both credential files, verifies auth, then runs `./publish-lobehub.sh`. The refresh token auto-renews the access token, so the workflow stays authenticated across runs.\n\nAfter publishing, skills appear at `market.lobehub.com/s/skills/afonsoft-skills-<name>` and are searchable at [lobehub.com/skills?q=afonsoft](https://lobehub.com/skills?q=afonsoft).\n\n### ClawHub\n[ClawHub](https://clawhub.ai/) is the public skill registry for OpenClaw. Each `skills/<name>/SKILL.md` directory becomes a versioned, installable skill under the `afonsoft` publisher.\n\n**Install from ClawHub:**\n\n```bash\n# Search for a skill\nclawhub search \"afonsoft\"\n\n# Install one skill\nclawhub install @afonsoft/<skill-name>\n\n# Or install with OpenClaw directly\nopenclaw skills install @afonsoft/<skill-name>\n```\n\n**Publish all skills locally:**\n\n```bash\nnpm i -g clawhub\nclawhub login\n./publish-clawhub.sh          # publish new/changed skills\n./publish-clawhub.sh --dry-run # preview the publish plan\n```\n\nThe `clawhub` CLI uses `clawhub sync` to compare local fingerprints against the registry and publishes only new or changed skills, defaulting to the next patch version.\n\n**Automatic publishing via GitHub Actions:**\n\nA workflow (`.github/workflows/clawhub-publish.yml`) publishes all skills when a `v*` tag is pushed, a release is published, or when triggered manually (`workflow_dispatch`). To enable it, add the repository secret:\n\n1. **`CLAWHUB_TOKEN`** — your ClawHub publisher token (`clawhub token create` or from https://clawhub.ai/settings/tokens)\n\n```bash\ngh secret set CLAWHUB_TOKEN\n```\n\n## 📖 How to use\n\n1. **Install** the collection using one of the methods above. Running `./install.sh` additionally generates `/spec-driven:<skill>` (or `/spec-driven-<skill>` where `:` is not supported) slash commands for the supported CLIs — see the table above.\n2. **Start with the orchestrator** — `/spec-driven` (same as `/spec-driven:orchestrator`) or *\"use the orchestrator skill\"* — and let it drive the spec → issues → slices → QA → PR pipeline.\n3. **Invoke** an individual skill directly when you know exactly what you need (e.g., `/spec-driven:write-specs`, or *\"Use the create-agent-harness skill to setup this repo\"*). The agent loads the `SKILL.md` and follows the structured workflow.\n\n## ⚖️ License\nMIT - See `LICENSE`.\n\n## 🛠️ Skill Development Tools\n\n### skillxp\n[skillxp](https://skillxp.dev/) observes skill loading behavior across harnesses (Claude Code, Codex CLI, Antigravity). Stage a skill in a fresh fixture, invoke the harness headlessly, and see what actually reached the model with transcript evidence. Install via `brew install agent-ecosystem/tap/skillxp` or `npm install -g skillxp`. Use `skillxp harnesses` to list supported platforms and `skillxp observe -harness <name> -install ./my-skill ...` to trace skill activation and phrase loading.\n\n## 📊 Skills Catalog\nBrowse all available skills at [skills.sh](https://www.skills.sh/?q=afonsoft).\n\n---\n\n## Star History\n\n<a href=\"https://www.star-history.com/?repos=afonsoft%2Fskills&type=date&legend=top-left\">\n <picture>\n   <source media=\"(prefers-color-scheme: dark)\" srcset=\"https://api.star-history.com/chart?repos=afonsoft/skills&type=date&theme=dark&legend=top-left\" />\n   <source media=\"(prefers-color-scheme: light)\" srcset=\"https://api.star-history.com/chart?repos=afonsoft/skills&type=date&legend=top-left\" />\n   <img alt=\"Star History Chart\" src=\"https://api.star-history.com/chart?repos=afonsoft/skills&type=date&legend=top-left\" />\n </picture>\n</a>\n\n## StarMapper\n\n[![StarMapper](https://img.shields.io/badge/StarMapper-afonsoft%2Fskills-blue)](https://starmapper.bruniaux.com/afonsoft/skills)\n\n> StarMapper also requires a GitHub token to fetch star geolocation data. The live map image is not available until the repository is scanned.\n",
  "bytes": 27918,
  "sha": "4e7a643096a959af73d483a9def8b7093cac0a972e7f4f9809d3fe29a9ce91dc",
  "repo_slug": "afonsoft/skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://api.agentalog.com/api/listings/skl_afonsoft_skills_observability_and_instru_0b756c94/readme"
}