InnerVault

Library

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

Results

  1. ⚒️ Open-source OSINT and digital forensics skills for AI assistants. Investigate sources, challenge hypotheses, analyze artifacts, and produce evidence-referenced reports with portable case files and offline Python tools. Designed for Claude Code, Codex, OpenCode, and Gemini CLI.

    Stale GitHub, OSINT-Forge-Community 9 ★Apache-2.0Updated 21 days ago

    git clone https://github.com/OSINT-Forge-Community/osint-forge-skills.git
  2. task-pipeline

    Skills

    Take repository changes from a clear brief to implementation, verification and a durable handoff through explicit delivery gates.

    Stale GitHub, ssheleg 7 ★MITUpdated 6 days ago

    git clone https://github.com/ssheleg/task-pipeline.git
  3. modlens

    Skills

    The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件,为 DeepSeek、GLM 等纯文本模型外挂视觉能力,粘贴图片即得结构化 JSON 证据(OCR、版面、语义)。

    Indexed GitHub, liustack 4,989 ★MITUpdated 2 days ago

    git clone https://github.com/liustack/modlens.git
  4. 生物医学论文精读 Skill 与本地阅读 App:逐图解析、证据评估、研究设计借鉴,支持中文、英文及双语报告。 | Biomedical paper-reading skill & local app: figure analysis, evidence appraisal, and research design insights. Chinese, English & bilingual reports.

    Stale GitHub, Gaoyuan-0423 151 ★MITUpdated 12 days ago

    git clone https://github.com/Gaoyuan-0423/biomedical-paper-reader.git
  5. odai

    Skills

    AI agent 通用任务治理框架:对齐目标与事实,规划和调度能力,守住授权与风险边界,治理任务执行到真实验收与交付。Governance framework for evidence-driven planning, orchestration, and verified delivery.

    Stale GitHub, orziz 132 ★MITUpdated 6 days ago

    git clone https://github.com/orziz/odai.git
  6. A portable project-planning skill for Codex, Claude Code, pi, Hermes, and Agent Skills-compatible harnesses. Evidence before build advice.

    Stale GitHub, AaravKashyap12 320 ★MITUpdated 2 months ago

    git clone https://github.com/AaravKashyap12/advise-project-approach.git
  7. Evidence-led qualitative analysis skill with five method-specific workflows and Markdown + HTML reporting

    Indexed GitHub, thePlannerIvan 13 ★AGPL-3.0Updated 3 days ago

    git clone https://github.com/thePlannerIvan/planners-quali-box.git
  8. 面向 Codex、Claude Code 等 AI Agent 的医学绘图 Skill,基于可信证据制作医学插画、科普漫画与科研示意图,提供可编辑成果与审核记录。 · Evidence-backed medical illustration, comics and research figures for Codex, Claude Code and other AI agents, with editable output and review records.

    Indexed GitHub, wilbert-MD-PhD 175 ★Custom licence (see repository)Updated 3 days ago

    git clone https://github.com/wilbert-MD-PhD/medical-illustration.git
  9. styleseed

    Skills

    Open-source design-method engine for Claude Code, Codex & Cursor. One agent skill with 22 internal workflows for fixed design judgment, multiple grammars, semantic palettes, reference compilation, and evidence-verified UI. MIT.

    Indexed GitHub, bitjaru 1,020 ★MITUpdated yesterday

    git clone https://github.com/bitjaru/styleseed.git
  10. axwise-flow

    Skills

    Local MCP extension for product discovery: personas, interviews, evidence analysis, PRDs and delivery briefs. Works with compatible agent hosts; bundled in Orqanix.

    Stale GitHub, AxWise-GmbH 62 ★Apache-2.0Updated 27 days ago

    git clone https://github.com/AxWise-GmbH/axwise-flow.git
  11. One epistemic standard on three hosts. Claude Code: 15 problem-shaped skills, 97 sourced reasoning patterns, 120 agents, commit-time gates. Codex and Gemini CLI: portable evidence-synthesis, design and goal-loop skills. Shared gates block unsourced constants, vacuous tests and AI-writing patterns. I do not know is a supported outcome.

    Indexed GitHub, cdeust 9 ★MITUpdated 2 days ago

    git clone https://github.com/cdeust/zetetic-team-subagents.git
  12. Fact-checked genealogy research recipes for AI agents: DNA evidence and record searches.

    Indexed GitHub, Kinprove 32 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/Kinprove/genealogy-research-recipes.git
  13. The meta-skill that improves your skills, including itself. Turns the corrections, judgement calls and repeated workflows of your sessions (autonomous or human-led) into small skill updates and new skill candidates, each with its evidence and reason. Nothing touches a skill until you approve it. Augmented Expertise in practice. CC BY 4.0.

    Indexed GitHub, rebelytics 3,925 ★CC-BY-4.0Updated 2 days ago

    git clone https://github.com/rebelytics/one-skill-to-rule-them-all.git
  14. Production-grade JavaScript reverse-engineering skill: evidence-driven workflows, verbatim sandbox harnesses, 19 battle-tested playbooks, 136 scripts, public benchmarks

    Stale GitHub, DQmyth 17 ★MITUpdated 8 days ago

    git clone https://github.com/DQmyth/js-reverse-ops.git
  15. paranoid-qa

    Skills

    Claude Code skills that turn an AI agent into a meticulous QA engineer. Evidence or it didn't happen.

    Stale GitHub, akovalion 16 ★MITUpdated 15 days ago

    git clone https://github.com/akovalion/paranoid-qa.git
  16. Two skills for coding agents: a day-zero production skeleton and a skeptic's audit that only accepts file:line evidence

    Stale GitHub, hallikkristjan-code 12 ★MITUpdated 11 days ago

    git clone https://github.com/hallikkristjan-code/production-skeleton.git
  17. jev-social

    Skills

    Open-source, local-first social media research agent for Instagram, TikTok, and LinkedIn. Jev routes read-only steps; socai CLI captures cited browser evidence.

    Stale GitHub, socai-io 205 ★MITUpdated 9 days ago

    git clone https://github.com/socai-io/jev-social.git
  18. squadra

    Skills

    Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.

    Indexed GitHub, dagoSte 1,277 ★MITUpdated 5 days ago

    git clone https://github.com/dagoSte/squadra.git
  19. modsearch

    Skills

    🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without native web access. Free, no signup, no API key. Ask the web or X, get structured JSON evidence. | 🥇 全网最强的 DeepSeek Harness 免费联网搜索插件,免费免注册免 API key。为不能联网的模型补上搜索,问网页或 X,拿回结构化 JSON 证据(搜索、抓取、引用)。

    Indexed GitHub, liustack 990 ★MITUpdated 2 days ago

    git clone https://github.com/liustack/modsearch.git
  20. enso-method

    Skills

    Agent skills for Claude Code and Codex that record business assumptions with evidence and confidence, and preserve requirements as the source of truth.

    Indexed GitHub, EnsoDynamics 7 ★MITUpdated 4 days ago

    git clone https://github.com/EnsoDynamics/enso-method.git
  21. vibe-codex

    Skills

    Evidence-first workflow skills for Codex CLI: right-sized planning, Two-Strike re-plan, and completion claims backed by checks that ran.

    Stale GitHub, kks0488 11 ★MITUpdated 33 days ago

    git clone https://github.com/kks0488/vibe-codex.git
  22. wicked-garden

    Skills

    The skills your coding agent can't build alone: done re-checked from evidence, graph-aware refactor, 40 QE specialists, review panels from other models.

    Stale GitHub, mikeparcewski 9 ★MITUpdated 5 days ago

    git clone https://github.com/mikeparcewski/wicked-garden.git
  23. skillhub

    Skills

    Give Claude Code a memory and make it cite its sources — keyless skills for research, daily work, and an evidence-gated coding loop.

    Stale GitHub, duthaho 9 ★MITUpdated 17 days ago

    git clone https://github.com/duthaho/skillhub.git
  24. Agentic Design Process with Designer-in-the-Loop product judgment across User, Evidence, and Business flows.

    Stale GitHub, cis2042 19 ★MITUpdated 25 days ago

    git clone https://github.com/cis2042/ux3-product-design-harness.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.