InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. Agent Plugins Specification v1.0.0 — A minimal standard for packaging agent extensions into distributable plugins

    Stale GitHub, agentplugins 1,383 ★Custom licence (see repository)Updated 49 days ago

    git clone https://github.com/agentplugins/agent-plugins-spec.git
  2. A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until all models reach consensus.

    Stale GitHub, zscole 556 ★MITUpdated 9 months ago

    git clone https://github.com/zscole/adversarial-spec.git
  3. C.R.I.S.P

    Skills

    CRISP — The missing layer between vibe coding and building something people actually want.

    Stale GitHub, radekamirko 52 ★MITUpdated 59 days ago

    git clone https://github.com/radekamirko/C.R.I.S.P.git
  4. Claude-Red

    Skills

    claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface — from SQLi to shellcode, EDR evasion to exploit development.

    Stale GitHub, SnailSploit 7,510 ★MITUpdated 35 days ago

    git clone https://github.com/SnailSploit/Claude-Red.git
  5. speccheck

    Skills

    Specification conformance checker: for every ID a SPEC.md declares, find where code and tests cite it, join JUnit results, and report one evidence-backed status per ID — with an optional downgrade-only LLM judge. Ships the spec-writing / spec-review / spec-build skills.

    Stale GitHub, rioffe 5 ★Custom licence (see repository)Updated 10 days ago

    git clone https://github.com/rioffe/speccheck.git
  6. Claude Code skill for OWASP security best practices (2025-2026). Includes Top 10:2025, ASVS 5.0, Agentic AI security, and 20+ language-specific security quirks.

    Stale GitHub, agamm 428 ★MITUpdated 13 days ago

    git clone https://github.com/agamm/claude-code-owasp.git
  7. 面向 AI 编码助手的源码知识生产工具包:提取业务规则,生成可追溯的机器人问答知识 | An agent toolkit for evidence-backed knowledge from source code.

    Stale GitHub, Ethereal-Space-one 18 ★Apache-2.0Updated 6 days ago

    git clone https://github.com/Ethereal-Space-one/code2kb-agent-toolkit.git
  8. Agent Skill for GitHub repository setup and platform-specific features | Claude Code compatible

    Stale GitHub, netresearch 10 ★Custom licence (see repository)Updated 17 days ago

    git clone https://github.com/netresearch/github-project-skill.git
  9. Evidence-led qualitative analysis skill with five method-specific workflows and Markdown + HTML reporting

    Indexed GitHub, thePlannerIvan 13 ★AGPL-3.0Updated 2 days ago

    git clone https://github.com/thePlannerIvan/planners-quali-box.git
  10. agent-skills

    Skills

    A collection of Agent Skills for AI coding assistants (Claude, Cursor, Copilot). Following agentskills.io specification.

    Stale GitHub, rlespinasse 12 ★MITUpdated 27 days ago

    git clone https://github.com/rlespinasse/agent-skills.git
  11. screenshot

    Skills

    Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.

    Stale Agent skill collections on GitHub, openai 1 note

    $skill-installer <skill-name>
  12. smart-ralph

    Skills

    Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow.

    Stale GitHub, tzachbon 565 ★MITUpdated 19 days ago

    git clone https://github.com/tzachbon/smart-ralph.git
  13. Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. | 覆盖主流期刊的 Claude Code/Codex 期刊技能包,从选题、识别策略到表格规范与审稿回复全流程,助你快速发论文。

    Stale GitHub, brycewang-stanford 1,256 ★MITUpdated 50 days ago

    git clone https://github.com/brycewang-stanford/Awesome-Journal-Skills.git
  14. specmint-core

    Skills

    Persistent, resumable specs for AI coding agents. Deep research, iterative interviews, phased implementation, resume context. Claude Code plugin + universal skill (Codex, Cursor, Windsurf, Cline, Gemini CLI, Devin, Antigravity).

    Stale GitHub, ngvoicu 12 ★MITUpdated 23 days ago

    git clone https://github.com/ngvoicu/specmint-core.git
  15. 🔍 Agent skill that reads your real code and explains any module or flow: technical report, user stories for business, or a clean spec to rebuild it right. Works in English and Spanish. ⭐ Stars and contributions welcome!

    Indexed GitHub, djcesar 5 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/djcesar/skill-module-report.git
  16. Motifcode

    Skills

    A coding agent harness built specifically for Motif-3

    Indexed GitHub, TaewoooPark 77 ★Apache-2.0Updated today

    git clone https://github.com/TaewoooPark/Motifcode.git
  17. simmer

    Skills

    Iterative artifact refinement with investigation-first judge board - constructs problem-specific judges that read the code, understand the problem, and propose evidence-based improvements

    Stale GitHub, 2389-research 16 ★MITUpdated 14 days ago

    git clone https://github.com/2389-research/simmer.git
  18. TypeScript/Bun tools for coding agents. Run checks once, keep complete evidence, and test output filters against task-specific requirements. No runtime packages.

    Indexed GitHub, Supersynergy 8 ★MITUpdated 3 days ago

    git clone https://github.com/Supersynergy/agent-token-saver.git
  19. 🧭 Keep AGENTS.md lean. Route coding agents to task-specific docs with byte budgets and integrity checks.

    Indexed GitHub, runkids 6 ★MITUpdated 2 days ago

    git clone https://github.com/runkids/agents-context-router.git
  20. Mini Program Engineering Skill Suite is an Agent Skill suite for evidence‑first mini‑program development. It helps agents bring WeChat or other mini‑program projects from vague intent to reliable engineering work: project intake, product specification, architecture, implementation, UI & device adaptation, debugging, verification, release readiness.

    Stale GitHub, NocodeMrLi 95 ★MITUpdated 13 days ago

    git clone https://github.com/NocodeMrLi/mini-program-engineering-skill-suite.git
  21. Claude Skill for Backblaze B2 Cloud Storage management from the terminal. Manage buckets, list and search files, audit storage usage, detect stale or large objects, review security posture, and safely clean up data using natural language. Built on the Agent Skills specification and compatible with Claude Code and other skills-based agents.

    Indexed GitHub, backblaze-labs 44 ★MITUpdated 3 days ago

    git clone https://github.com/backblaze-labs/claude-skill-b2-cloud-storage.git
  22. vibe-skill

    Skills

    vibe-* is a collection of Claude Code CLI skills. Each skill is a structured instruction set that tells Claude Code exactly what to do at a specific moment in a project — how to plan it, build it, review it, test it, deploy it, and hand it off.

    Stale GitHub, aakashdhar 7 ★Updated 17 days ago

    git clone https://github.com/aakashdhar/vibe-skill.git
  23. The Synapti Marketplace is a curated collection of Claude Code plugins designed for AI-augmented development + advanced analytical and research tasks. Each plugin provides specialized agents, skills, and commands that extend Claude Code's capabilities in specific domains.

    Indexed GitHub, synaptiai 7 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/synaptiai/synapti-marketplace.git
  24. An open registry of 76 fully specified AI agent skills — taxonomy, canonical schema, composer, governance model, and a fleet runner that deploys hundreds of agents against one objective and rehearses them against their own definitions.

    Stale GitHub, jersonboydmilan 6 ★MITUpdated 14 days ago

    git clone https://github.com/jersonboydmilan/Agent-Skills-Compendium.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.