InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. pstack-t3

    Skills

    Lauren Tan's pstack agent skills, ported to T3 Code so any model can lead and other models can review the work. Adds brigade, a standing coordinator per project that runs each unit of work in its own git worktree, has another model family review the commit when one can run, and lands it through a queue that is the only writer to trunk.

    Stale GitHub, creedants 18 ★MITUpdated 10 days ago

    git clone https://github.com/creedants/pstack-t3.git
  2. Development workflows for Codex that keep technical rigor and edge-case handling from becoming product overengineering.

    Stale GitHub, shinpr 38 ★MITUpdated 14 days ago

    git clone https://github.com/shinpr/codex-workflows.git
  3. Use when completing tasks, implementing major features, or before merging to verify work meets requirements

    Stale Agent skill collections on GitHub, obra MIT1 note

  4. Planning skills for Claude Code, Copilot, Agy, etc.

    Stale GitHub, serbanghita 13 ★MITUpdated 28 days ago

    git clone https://github.com/serbanghita/plan-critique-skills.git
  5. Make your AI coding agent work properly: pick the right skill, run its own code, and remember your project rules.

    Stale GitHub, wankimmy 22 ★MITUpdated 19 days ago

    git clone https://github.com/wankimmy/Bossku-Superpowers.git
  6. skills

    Skills

    Agent skills for software delivery, from requirements gap analysis to reviewed, shipped code. Supports Claude Code, Codex, Cursor, Copilot, and OpenCode.

    Indexed GitHub, kevinlin 5 ★MITUpdated 3 days ago

    git clone https://github.com/kevinlin/skills.git
  7. 面向中文研究生与科研工作者的学术辅导 skill 套件(支持 Claude Code / Codex 等编程智能体):选题 → 检索 → 成文 → 评审 → 投稿全链路 25 个命令,引用核验以真实 API 响应为准、不凭模型记忆编造,AI 管效率、人管研究决策——辅导不代笔

    Stale GitHub, cabbage2000-lab 48 ★Custom licence (see repository)Updated 13 days ago

    git clone https://github.com/cabbage2000-lab/paper-tutor-skills.git
  8. Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

    Stale Agent skill collections on GitHub, obra MIT1 note

  9. sci-paper

    Skills

    Claude Code plugin for scientific paper writing, source-traced review, and de-AI rewriting. 12 skills + 35 tools under one typed standard: non-waivable integrity blockers, zero-target L0 lexicon, ranked advisories, and explicit measurement states so missing calibration never reads as clean. Corpus-calibrated for ApJ/MNRAS/PRD/JCAP manuscripts.

    Stale GitHub, skymanbp 6 ★Custom licence (see repository)Updated 31 days ago

    git clone https://github.com/skymanbp/sci-paper.git
  10. A ready-to-fork Claude Code template for academic research — papers, data analysis (R, Stata, Python), slides and teaching — with multi-agent review, enforced quality gates and replication protocols. Codex and Antigravity can use it too.

    Stale GitHub, pedrohcgs 1,689 ★MITUpdated 10 days ago

    git clone https://github.com/pedrohcgs/claude-code-my-workflow.git
  11. 45 agent skills from shipping three live products: decide what to build, build it with Claude Code or Codex, have a second model review it, release it.

    Indexed GitHub, phuryn 597 ★MITUpdated 3 days ago

    git clone https://github.com/phuryn/product-engineering.git
  12. shidi-skill

    Skills

    AI4S 科研 Agent 技能 | AI-for-Science research workflow skill for coding agents: literature review · experiment design · figures · paper reading — files out, cross-verified, zero deps | 文献调研/实验方案/作图/精读,交付文件+交叉验证,零依赖,MIT

    Stale GitHub, IcyCreamDAS 14 ★MITUpdated 20 days ago

    git clone https://github.com/IcyCreamDAS/shidi-skill.git
  13. hallmark

    Skills

    Agentic development · automated review · a full record - Coding agents build your change. An independent principal-engineer agent reviews it. Only commits that earn a hallmark leave your machine.

    Stale GitHub, tiagocolombo 9 ★MITUpdated 21 days ago

    git clone https://github.com/tiagocolombo/hallmark.git
  14. skill-doctor

    Skills

    🩺 A bilingual meta-skill for Claude Code: health-check your other skills and review agent-workflow architecture - runtime reality, ownership, scaffolding, recovery. Diagnose-only. Built on Matt Pocock's method.

    Stale GitHub, isalicema 7 ★MITUpdated 12 days ago

    git clone https://github.com/isalicema/skill-doctor.git
  15. QA workflow for AI coding agents: ticket → reviewed test plan → real-browser run with independent evidence review → bug tickets. Claude Code, OpenCode, any Agent Skills harness.

    Stale GitHub, QAMarcos 8 ★MITUpdated 28 days ago

    git clone https://github.com/QAMarcos/claude-qa-flow.git
  16. modularity

    Skills

    Claude Code plugin for designing modular systems from functional requirements and reviewing existing codebases for modularity problems with actionable improvement recommendations. Based on the Balanced Coupling model.

    Stale GitHub, vladikk 561 ★Custom licence (see repository)Updated 2 months ago

    git clone https://github.com/vladikk/modularity.git
  17. code-review

    Skills

    Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".

    Indexed Agent skill collections on GitHub, mattpocock MIT1 note

  18. Skills, hooks, and git-enforced quality gates for AI coding assistants. Extends obra/superpowers.

    Indexed GitHub, bordenet 8 ★MITUpdated 4 days ago

    git clone https://github.com/bordenet/superpowers-plus.git
  19. supermatt

    Skills

    The best of Matt Pocock's Skills, Superpowers, and Compound Engineering. One complete, simple, supercharged SDLC system for your coding agent.

    Stale GitHub, svyatov 14 ★MITUpdated 26 days ago

    git clone https://github.com/svyatov/supermatt.git
  20. stop-vague

    Skills

    Turn vague feedback into SBI or STAR feedback people can act on.

    Stale GitHub, sumanbukka 5 ★MITUpdated 29 days ago

    git clone https://github.com/sumanbukka/stop-vague.git
  21. podori

    Skills

    취약점은 고치고, 정상 동작은 다시 확인합니다. AI 코딩 에이전트를 위한 독립 보안 스킬 모음. | Security skills for AI coding agents: review code, fix vulnerabilities, and verify normal behavior.

    Indexed GitHub, VerifiedIdiot 10 ★MITUpdated yesterday

    git clone https://github.com/VerifiedIdiot/podori.git
  22. Claude Code plugin marketplace: Rust, ESP32 C++, Python backend, SwiftUI, dead code detection

    Stale GitHub, johnkozaris 11 ★MITUpdated 12 days ago

    git clone https://github.com/johnkozaris/jko-claude-plugins.git
  23. AI学术工作流 · 乔淼PhD「AI学术训练营」skills 库,按工作流分类:期刊初稿 / 综述文章 / 投稿与审稿。涵盖选题、文献、研究设计、数据分析、写作、改稿、投稿与返修,支持 Claude Code / Codex;后续按工作流扩展。

    Stale GitHub, qiaomiaojoe 10 ★Custom licence (see repository)Updated 7 days ago

    git clone https://github.com/qiaomiaojoe/ai-academic-workflow.git
  24. skills

    Skills

    Univer Skill enables AI tools to work directly with spreadsheets, Excel workbooks, and CSV files. Powered by Univer CLI, it brings Git-style diffs, reviews, approvals, and rollbacks to spreadsheet workflows — making human-AI collaboration structured, reviewable, and safe.

    Stale GitHub, dream-num 77 ★Apache-2.0Updated 34 days ago

    git clone https://github.com/dream-num/skills.git

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.