{
  "markdown": "# Claude Code Skills by Vishal Sachdev\n\n> # ⚠️ This repository has moved and is archived\n>\n> **All skills here now live in [vishalsachdev/claude-skills](https://github.com/vishalsachdev/claude-skills).**\n>\n> As of **2026-08-01** this repository is archived and read-only. Everything moved: all 10 skills,\n> `skill-specs/`, `releases/`, the MIT license, the attribution note, and the contributing guide\n> (now `docs/skill-authoring-mechanics.md`). Nothing was dropped.\n>\n> Several skills here had also fallen behind their maintained versions, so the copies in\n> `claude-skills` are newer — please use those rather than forking from this snapshot.\n>\n> Open issues and PRs against\n> [vishalsachdev/claude-skills](https://github.com/vishalsachdev/claude-skills) instead.\n>\n> Two items were intentionally left behind and remain readable here:\n> `docs/QM Higher Education Rubric Seventh Edition.pdf` (a third-party copyrighted rubric, not\n> duplicated), and `AGENTS.md` (machine-specific agent boilerplate).\n\n[![Agent Skills](https://img.shields.io/badge/Agent%20Skills-Compatible-blue?style=flat&logo=anthropic)](https://agentskills.io)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n\nProfessional skills for [Claude Code](https://claude.com/claude-code) following the [Agent Skills](https://agentskills.io) open specification.\n\n> **Attribution note:** Some skills in this repository were originally contributed or inspired by other authors in the broader Claude Code community. I've collected and refined them over time across many machines and sessions, and I've lost the traceability needed to credit individual contributors. If you recognize a skill as yours or derived from your work, please open an issue and I'll happily add attribution. Skills I authored myself are noted in their frontmatter.\n\n## 📚 Available Skills\n\n### 📝 Paper Writing\n\nComprehensive academic paper writing guidance with expert workflows, templates, and quality checking tools.\n\n**Perfect for:**\n- Research papers and journal articles\n- Conference papers (ACM, IEEE, etc.)\n- Technical reports and white papers\n- Thesis chapters and dissertations\n- Literature reviews and survey papers\n\n**What's included:**\n- **4 comprehensive reference guides** (69KB total)\n  - Elite IS Papers (Thatcher's 17 Rules)\n  - Writing Guidelines (argument, evidence, citations, ethics)\n  - Structure Templates (7 paper types)\n  - Style Guide (clarity, precision, revision)\n- **2 detailed paper templates**\n  - Research Paper (IMRAD format)\n  - Conference Paper (CS/Engineering)\n- **Quality checker script** (automated style analysis)\n- **3,478 lines** of expert guidance\n\n**Based on:**\n- **Thatcher, Jason Bennett** (2024). \"Rules for Writing Elite Information Systems Papers.\" SSRN: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5993034\n- APA Style (7th Edition)\n- IEEE Editorial Style\n- Academic writing best practices from Ohio University, Duke, MIT, USC, UCSD\n\n📖 [Full Documentation](./skills/paper-writing/SKILL.md) | 💾 [Download v1.0.0](https://github.com/vishalsachdev/claude-code-skills/releases/download/v1.0.0/paper-writing-v1.0.0.skill)\n\n---\n\n### 🔮 Premortem\n\nRun a Gary Klein-style premortem on any plan, launch, hire, or strategy: assume it already failed 6 months from now and work backward to find every reason why. Produces a revised plan with blind spots exposed.\n\n**Use when:** you have a concrete plan with high cost-of-being-wrong and want to surface failure modes before committing.\n\n**How it works:** gathers minimum context, generates the full failure-reason list, spawns one parallel agent per failure to write the failure story, then synthesizes the most likely / most dangerous / hidden assumption / revised plan / pre-launch checklist into an HTML report.\n\n📖 [Full Documentation](./skills/premortem/SKILL.md) · Inspired by [@itsolelehmann](https://x.com/itsolelehmann/status/2050548948419645488)\n\n---\n\n### 📊 Agentic Eval-First Development\n\nArchitect, execute, and iterate on AI evaluations using the Data-Task-Score framework. Treats evals as the modern, quantifiable version of a PRD — moves teams beyond vibe checks to measurable AI quality.\n\n**Use when:** building an eval, improving model quality, testing an agent workflow, quantifying product intuition, or setting up evaluation infrastructure.\n\n📖 [Full Documentation](./skills/agentic-eval-first-development/SKILL.md)\n\n---\n\n### 🛡️ Agentic Validators\n\nDesign and install validation hooks for coding agents to make AI changes safer and more deterministic. Covers post-tool-use and stop hooks, automated tests/linters/formatters, parallel sub-agents with per-file validation, and audit logs.\n\n**Use when:** you want to harden Claude Code with deterministic guardrails — catching bad edits before they land instead of after.\n\n📖 [Full Documentation](./skills/agentic-validators/SKILL.md)\n\n---\n\n### 🎯 Codebase Singularity\n\nA repeatable workflow for reliable codebase understanding and change. Provides guardrails and verification gates for high-trust, minimal-diff work — features, bugfixes, refactors, migrations.\n\n**Use when:** the cost of an incorrect change is high and you want explicit validation steps and exit criteria, not just \"looks good to me.\"\n\n📖 [Full Documentation](./skills/codebase-singularity/SKILL.md)\n\n---\n\n### 🚀 Start / Wrap-Up Session\n\nTwo paired meta-skills for session lifecycle. **Start** reads project context (CLAUDE.md, git status, recent commits) and orients you for the session. **Wrap-up** reviews work, updates roadmaps, archives session logs, and surfaces carry-forward items.\n\n**Use when:** you want consistent session bookends across all your repos — a reliable \"where were we?\" at the start and a clean handoff at the end.\n\n📖 [Start Session](./skills/start-session/SKILL.md) · [Wrap-Up Session](./skills/wrap-up-session/SKILL.md)\n\n---\n\n### 🐦 Tweet Series Extractor\n\nExtract tweet series from X/Twitter profiles with full content, embedded links, and engagement metrics preserved. Useful for analyzing recurring tweet formats — daily updates, weekly roundups, threads.\n\n**Use when:** you want to study how someone tweets, archive your own tweets, or build a content corpus from a creator's profile.\n\n📖 [Full Documentation](./skills/tweet-series-extractor/SKILL.md)\n\n---\n\n### 🏛️ LLM Council\n\nConvene a 3-model council (Claude + GPT via codex CLI + Gemini CLI) on a high-stakes decision. Forces cross-critique between members and surfaces where the models actually disagree — breaking Claude's default agreeableness.\n\n**Use when:** architecture, strategy, hiring, or pricing decisions where being wrong is expensive and you want genuinely different model perspectives, not just three Claude responses.\n\n**How it works:** Round 1 — each model answers independently. Round 2 — each model critiques the others' answers. Round 3 — Claude synthesizes agreement, disagreement, what matters most, and a recommendation. Requires `codex` and `gemini` CLIs installed.\n\n📖 [Full Documentation](./skills/llm-council/SKILL.md)\n\n---\n\n## 🚀 Quick Start\n\n### Installation\n\n**Option 1: Download pre-packaged skill**\n```bash\n# Download the .skill file\ncurl -L https://github.com/vishalsachdev/claude-code-skills/releases/download/v1.0.0/paper-writing-v1.0.0.skill -o paper-writing.skill\n\n# Extract to Claude Code skills directory\nunzip paper-writing.skill -d ~/.claude/skills/paper-writing\n\n# Verify installation\nls -la ~/.claude/skills/paper-writing/\n```\n\n**Option 2: Clone and copy**\n```bash\n# Clone this repository\ngit clone https://github.com/vishalsachdev/claude-code-skills.git\n\n# Copy specific skill\ncp -r claude-code-skills/skills/paper-writing ~/.claude/skills/\n\n# Verify installation\nls -la ~/.claude/skills/paper-writing/\n```\n\n### Usage\n\nSkills automatically activate in Claude Code when relevant to your task. For example:\n\n- Start typing \"Help me write a research paper...\" → Paper Writing skill activates\n- \"Review my paper's introduction...\" → Paper Writing skill provides guidance\n- \"What's the best structure for a literature review?\" → Paper Writing skill loads templates\n\nYou can also manually invoke skills by referencing them directly in your conversation.\n\n---\n\n## 📁 Repository Structure\n\n```\nclaude-code-skills/\n├── README.md                          # This file\n├── CONTRIBUTING.md                    # Contribution guidelines\n├── LICENSE                            # Repository license\n├── skills/                            # Source skills\n│   └── paper-writing/                 # Paper writing skill\n│       ├── SKILL.md                   # Main skill file\n│       ├── LICENSE.txt                # Skill license\n│       ├── references/                # Reference materials\n│       │   ├── ELITE-PAPERS.md\n│       │   ├── REFERENCE.md\n│       │   ├── STRUCTURE.md\n│       │   └── STYLE.md\n│       ├── assets/                    # Templates\n│       │   ├── research-paper-template.md\n│       │   ├── conference-paper-template.md\n│       │   └── README.md\n│       └── scripts/                   # Helper scripts\n│           └── check_paper.py\n├── releases/                          # Packaged .skill files\n│   └── paper-writing-v1.0.0.skill\n└── .github/\n    └── workflows/\n        └── package-skills.yml         # Auto-packaging workflow\n```\n\n---\n\n## 🤝 Contributing\n\nContributions are welcome! Whether you want to:\n- Report a bug\n- Suggest improvements\n- Add new skills\n- Fix documentation\n\nSee [CONTRIBUTING.md](./CONTRIBUTING.md) for guidelines.\n\n---\n\n## 📖 About Agent Skills\n\nThese skills follow the [Agent Skills](https://agentskills.io) open specification, which means:\n\n- ✅ **Portable** - Works across any AI platform that adopts the standard\n- ✅ **Modular** - Each skill is self-contained and composable\n- ✅ **Progressive** - Loads content only when needed to conserve context\n- ✅ **Open** - Simple markdown format, easy to read and modify\n\nSkills are not locked to Claude - the same skill format works across AI platforms and tools that adopt the Agent Skills standard.\n\n---\n\n## 📜 License\n\nThis repository is licensed under the MIT License - see [LICENSE](./LICENSE) file for details.\n\nIndividual skills may have their own licenses - check each skill's LICENSE.txt file.\n\n---\n\n## 🔗 Links\n\n- [Agent Skills Specification](https://agentskills.io)\n- [Claude Code Documentation](https://code.claude.com/docs)\n- [Anthropic Skills Repository](https://github.com/anthropics/skills)\n\n---\n\n## 📬 Contact\n\n**Vishal Sachdev**\n- GitHub: [@vishalsachdev](https://github.com/vishalsachdev)\n\n---\n\n## ⭐ Show Your Support\n\nIf you find these skills useful:\n- ⭐ Star this repository\n- 🐛 Report issues\n- 💡 Suggest new skills\n- 🤝 Contribute improvements\n\n---\n\n**Made with ❤️ for the Claude Code community**\n",
  "bytes": 10752,
  "sha": "5e357829aff73f501d8459156ce57e0a446235bea967bad11395d71306ce5949",
  "repo_slug": "vishalsachdev/claude-code-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/skl_vishalsachdev_claude_code_skills_paper_w_789eff09/readme"
}