InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. Linter for AI-writing tells in commit messages, PR descriptions and docs. It does not guess who wrote it. It shows the tells.

    Stale GitHub, Bubblegunn 9 ★MITUpdated 23 days ago

    git clone https://github.com/Bubblegunn/ai-slop-linter.git
  2. yomiyasu

    Skills

    AI生成の日本語を自然な日本語へ推敲するAgent Skill / Agent Skill for Refining AI-Generated Japanese into Natural Japanese

    Stale GitHub, nanaism 2,951 ★MITUpdated 6 days ago

    git clone https://github.com/nanaism/yomiyasu.git
  3. sloptrim

    Skills

    A local detector for AI-writing patterns. Scores every prose file your agent saves. Python standard library only, no network, no model.

    Indexed GitHub, seyedehsanhadi 424 ★Apache-2.0Updated 6 days ago

    git clone https://github.com/seyedehsanhadi/sloptrim.git
  4. dogent

    Skills

    Command line linter for your agentic manifestos, like SKILL.md and CLAUDE.md

    Indexed GitHub, yegor256 8 ★MITUpdated yesterday

    git clone https://github.com/yegor256/dogent.git
  5. snifftest

    Skills

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

    Stale GitHub, DanRWilloughby 35 ★MITUpdated 24 days ago

    git clone https://github.com/DanRWilloughby/snifftest.git
  6. A local, zero-dependency prose, copywriting, UI-text, and code-comment linter that flags stiff, AI-sounding writing (stock phrases, flat sentence rhythm, repeated wording) and tells you what to revise. Includes 8 language packs. A style checker, not an AI detector.

    Stale GitHub, yanstd888 102 ★MITUpdated 9 days ago

    git clone https://github.com/yanstd888/humanizer-lint.git
  7. geo-lint

    Skills

    The first open-source GEO linter. 92 rules for SEO, GEO, and content quality — built for AI agents to run, read, fix, and re-lint automatically.

    Stale GitHub, IJONIS 40 ★MITUpdated 8 months ago

    git clone https://github.com/IJONIS/geo-lint.git
  8. write-human

    Skills

    Statistical linter that flags the words, phrases and constructions that make text read as LLM output, measured against billions of words people wrote before 2022. Runs offline. CLI on npm plus an Agent Skill for coding agents.

    Stale GitHub, arslanrakh 12 ★MITUpdated 11 days ago

    git clone https://github.com/arslanrakh/write-human.git
  9. tracemantle

    Skills

    Validate SKILL.md files, track agent-skill bundle changes, and check release evidence against trusted policies.

    Stale GitHub, moonrunnerkc 24 ★MITUpdated 11 days ago

    git clone https://github.com/moonrunnerkc/tracemantle.git
  10. openqodex

    Skills

    Open source AI code review for coding agents. A separate reviewer checks every change your agent writes before you push, in Claude Code, Codex, Cursor and Cline. No account or key of its own.

    Indexed GitHub, openqodex 1,197 ★Apache-2.0Updated yesterday

    git clone https://github.com/openqodex/openqodex.git
  11. SAMOSA

    Skills

    A step auditor for matrix algebra, stochastics and algebra. Checks every step of a derivation, exactly, over finite fields.

    Stale GitHub, Hussain004 6 ★MITUpdated 6 days ago

    git clone https://github.com/Hussain004/SAMOSA.git
  12. iceberg

    Skills

    Claude Code plugin: grades every plan Claude writes against 14 Hemingway rules and rewrites docs to an A.

    Stale GitHub, gagoar 8 ★MITUpdated 27 days ago

    git clone https://github.com/gagoar/iceberg.git
  13. fallow-skills

    Skills

    Agent skills for fallow. They teach coding agents (Claude Code, Codex, Cursor, and others) to check health, complexity, duplication, architecture, styling drift, and unused code with fallow.

    Stale GitHub, fallow-rs 137 ★MITUpdated 9 days ago

    git clone https://github.com/fallow-rs/fallow-skills.git
  14. auteur

    Skills

    The Claude Code skill that directs a website like a film. Commit-sheet, generated assets, build, and an executable anti-slop linter that gates every ship.

    Stale GitHub, agiwhitelist 1,040 ★MITUpdated 3 months ago

    git clone https://github.com/agiwhitelist/auteur.git
  15. duology

    Skills

    Claude Code skills for designing, building, testing and shipping apps on iPhone Duo and iOS 27. Layout patterns, app recipes, a fold linter and pose checks.

    Stale GitHub, Kimeur 40 ★MITUpdated 10 days ago

    git clone https://github.com/Kimeur/duology.git
  16. Free, offline Vietnamese copy linter plus 16 agent skills for Claude Code, Codex, Gemini CLI and Antigravity. Flags calques, US-style dates and numbers, unproven superlatives and outdated legal terms. 31 registers, 489 eval pairs, 18 UKMC.v1 modules. Zero telemetry. Source-available (PolyForm Shield 1.0.0).

    Stale GitHub, jangtrinh 13 ★Custom licence (see repository)Updated 10 days ago

    git clone https://github.com/jangtrinh/design-os-vietnamese.git
  17. skills

    Skills

    43 Claude Code skills for making content that doesn't read like a machine made it — prose editing with an offline linter, prompt engineering for 40+ image/video/music models with optional one-command execution, and orchestrators from research to a published carousel, reel or proposal. Russian-first, English throughout.

    Stale GitHub, Mikefluff 26 ★MITUpdated 20 days ago

    git clone https://github.com/Mikefluff/skills.git
  18. Battle-tested DayZ (Enfusion) modding knowledge for AI coding assistants: 44 domain playbooks (DayZ 1.30 stable and what changed from 1.29), the py3d-dayz MLOD toolchain, strict RTM/SEAnim/ODOL inspectors, 3D-model viewer tools, an offline Enforce linter for compile and coding issues, and a UI lab, with every claim carrying its path:line evidence.

    Indexed GitHub, willy92wins 25 ★MITUpdated yesterday

    git clone https://github.com/willy92wins/DayZ-Modding-Knowledge-Pack.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.