InnerVault

Library

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

Results

  1. 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
  2. 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 15 days ago

    git clone https://github.com/2389-research/simmer.git
  3. 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 11 days ago

    git clone https://github.com/rioffe/speccheck.git
  4. dokimi

    Skills

    Dokimi (Greek δοκιμή, "test, proof") measures whether a skill, MCP doc source, agent profile or repository guidance actually helps a coding agent: paired on/off arm comparisons, novel-vs-known content analysis, and repository scans with graded agent runs.

    Indexed GitHub, intel 37 ★Apache-2.0Updated yesterday

    git clone https://github.com/intel/dokimi.git
  5. agentops

    Skills

    DevOps discipline for AI coding agents: shape the work, track it as a graph, and get each change judged by a context that didn't write it.

    Indexed GitHub, boshu2 454 ★Apache-2.0Updated yesterday

    git clone https://github.com/boshu2/agentops.git
  6. turbo

    Skills

    A human-gated agentic software factory for Claude Code and Codex: you decide what to build and judge the result; skills shape, build, polish, ship, and learn.

    Indexed GitHub, tobihagemann 421 ★MITUpdated 2 days ago

    git clone https://github.com/tobihagemann/turbo.git
  7. agent-skills

    Skills

    Reusable agent skills for battle-tested engineering judgment. Works with Claude Code, Cursor, and 10+ AI tools...

    Stale GitHub, sayeed1999 6 ★MITUpdated 7 days ago

    git clone https://github.com/sayeed1999/agent-skills.git
  8. nasde-toolkit

    Skills

    CLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.

    Stale GitHub, NoesisVision 14 ★MITUpdated 33 days ago

    git clone https://github.com/NoesisVision/nasde-toolkit.git
  9. Agent skills distilled from real-world usage — codex-implementation-loop: delegate coding to Codex, keep review/gate/ship judgment in Claude's hands

    Stale GitHub, olddonkey 17 ★MITUpdated 33 days ago

    git clone https://github.com/olddonkey/olddonkey-skills.git
  10. snifftest

    Skills

    A prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model.

    Stale GitHub, DanRWilloughby 35 ★MITUpdated 25 days ago

    git clone https://github.com/DanRWilloughby/snifftest.git
  11. eval-genius

    Skills

    Teach your agent to work with evals: WHEN you actually need an eval or benchmark, HOW to build one that holds up, and how to read what it tells you. Deterministic-first, tool-agnostic.

    Stale GitHub, alexgreensh 24 ★Apache-2.0Updated 12 days ago

    git clone https://github.com/alexgreensh/eval-genius.git
  12. Make AI agents aim higher without losing control: a Claude Code skill with two bars per task, a cheap gate check before expensive work, and an independent verifier that never sees the worker's reasoning. Plain markdown, EN + RU.

    Stale GitHub, alexpiar 23 ★MITUpdated 23 days ago

    git clone https://github.com/alexpiar/be-ambitious-harness.git
  13. autocode

    Skills

    You say it. AutoCode ships it. 48 skills. Code to deployment in one session. iLang v5.0 judgment + secret-safe deploys. Free forever.

    Stale GitHub, ilang-ai 104 ★MITUpdated 26 days ago

    git clone https://github.com/ilang-ai/autocode.git
  14. 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
  15. 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
  16. kyber-weave

    Skills

    Agentic coding framework and meta-harness for planning, building, reviewing, and tuning software across coding agents. Portable agent squads, skills, governed project knowledge, quality gates, and local token observability. Human judgment. Agent speed.

    Indexed GitHub, dpalfery 23 ★MITUpdated yesterday

    git clone https://github.com/dpalfery/kyber-weave.git
  17. Graduate-application planning workspace for AI agents — the LLM does the judgement, deterministic validators keep it honest. Sourced program evaluations, evidence-grounded CVs and statement drafts, nothing final without human review.

    Stale GitHub, TianCZeng 5 ★MITUpdated 19 days ago

    git clone https://github.com/TianCZeng/admissions-ops.git
  18. Catch fabricated RAG citations before they reach the user: a zero-token verbatim gate + a burden-of-proof judge, framework-agnostic.

    Indexed GitHub, tonydzi 6 ★MITUpdated 3 days ago

    git clone https://github.com/tonydzi/verbatim-citation-gate.git
  19. Human-gated perspective-panel research: one question, several seats, one judge. Solo, native panel, or per-seat MoA/Fusion fanout.

    Stale GitHub, bmtrnavsky 5 ★MITUpdated 26 days ago

    git clone https://github.com/bmtrnavsky/storm-fusion-research-pipeline.git
  20. Five Claude Code plugins, Python stdlib + git. ar-board: judge agent proposals one by one on a local board; the agent keeps your reasons. publish-check: scan a repo's history for personal data before it goes public. tidy-board: delete stale branches, worktrees, and stashes only on approval. Plus doc, handoff, and TODO tools, and a status line.

    Stale GitHub, dvwinck 33 ★MITUpdated 14 days ago

    git clone https://github.com/dvwinck/capybara-toolbox.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.