Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
stop-that-shit
SkillsStop That Shit(别再造史了)|面向 Codex/GPT 场景的多平台 Hook + Skill Guard:拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A multi-platform Hook + Skill Guard for AI coding agents in Codex/GPT workflows: stop unrequested hashes, checksums, and task-scope creep.
git clone https://github.com/lennney/stop-that-shit.git -
harness-scope
SkillsA Claude Code mod that turns your global skills, agents, rules and tools on or off per repo with named profiles. In my writing repo, it hid 94 of the 101 skills with one line.
git clone https://github.com/shimo4228/harness-scope.git -
chemdraw-skill
SkillsChemDraw Skill · AI 绘制可编辑化学结构式 — Editable ChemDraw figures for Claude Code, Codex & any AI agent: 28 journal & research-group house styles (JACS, Angew, Nature, Science, Baran, MacMillan…), rebuild paper figures (DECIMER OCSR), substrate-scope & SAR tables, ACS 1996 exam drawings, live ChemDraw in Word/PPT.
git clone https://github.com/ZiChenWang114514/chemdraw-skill.git -
ham
Skills(HAM) Memory system for AI coding agents. Cut token usage by 80% by scoping context to directories.
git clone https://github.com/kromahlusenii-ops/ham.git -
Local user preferences with sourced corrections, scoped recall, and Codex/Cursor host adapters. / 本地保存带来源的偏好,支持更正、限定检索与 Codex/Cursor 适配。
git clone https://github.com/KarmenLoop/user-behavior-personalization.git -
claude-code-skills
SkillsStandalone skills for Claude Code and Codex: product discovery, architecture, implementation, technical foundations, reviews and delivery, with explicit scope and verification.
git clone https://github.com/levnikolaevich/claude-code-skills.git -
dsh-toolbox-ui
SkillsToolbox panel for DeepSeek Harness Web: MCP manager (tools & JSON Schema, market, import, workspace copy) and skills manager (scopes & shadowing, enable/disable, model auto-invocation, skillhub.cn market).
git clone https://github.com/Imzl-zl/dsh-toolbox-ui.git -
anti-gold-plating
SkillsA skill for strict scope control, explicit user approval, and final compliance checks.
git clone https://github.com/TulossSolutions/anti-gold-plating.git -
vigilante
SkillsVigilante is a sandbox-first orchestration layer for coding agents. It isolates every task in a git worktree, enforces strict credential scoping, and gives you full audit logs — so your agents can't burn down production.
git clone https://github.com/aliengiraffe/vigilante.git -
trace-to-practice
SkillsEvidence-backed retrospectives for AI coding-agent histories. Offline indexing, scoped workflow improvements, and bilingual documentation.
git clone https://github.com/wssfk12138/trace-to-practice.git -
superpowers
SkillsJesse Vincent's Superpowers skills (brainstorm, plan, TDD, debug, verify, review) adapted for GitHub Copilot agent mode, with project-scoped installers. MIT, adapted from obra/superpowers.
git clone https://github.com/autovant/superpowers.git -
ai-engineering-skills
SkillsPortable AI-engineering skills for Claude Code, Codex, and coding agents: bounded scope, mini-specs, vertical slices, verification, ship gates, and handoff.
git clone https://github.com/tmusser/ai-engineering-skills.git -
agents-scaffold
SkillsGuardrails for AI coding agents — Claude Code, Codex and Antigravity — enforced by a real git pre-commit gate. One command installs AGENTS.md, path-scoped rules, skills, subagents, hooks and 13 stack presets. Plain files, offline-ready. English / 한국어
git clone https://github.com/LeeYudok/agents-scaffold.git -
ServerFS_MCP
SkillsSecure, scoped filesystem MCP server for ChatGPT and other MCP clients — read-only by default, with controlled mutations, binary transfer, native Codex/Claude/Qoder runtimes, generic ACP v1 profiles, and Agent Skills.
git clone https://github.com/NTLx/ServerFS_MCP.git -
KhaosMCP-Pentester-Agent
SkillsKhaosMCP is a local-first, agent-operated pentest platform using AI via MCP. It connects the external operator to the complete assessment cycle: scoping, supervised execution, integrations, evidence gathering, review of findings, and reporting.
git clone https://github.com/henriqqw/KhaosMCP-Pentester-Agent.git -
prompt-optimizer
SkillsClaude Code / Agent Skill: /prompt-optimizer polishes your existing AI prompts — fixes wording, grammar and structure without adding scope, changing constraints or touching commands, paths and code. 提示词优化技能:只改表达,不改语义。Works with Claude Code, Codex and any chat AI.
git clone https://github.com/talki-io/prompt-optimizer.git -
Foreman
SkillsA build playbook that turns your coding agent into the foreman of a website build. It interviews you, forces the design and scope decisions, locks a visual system, writes the build brief, then verifies, ships, and indexes the site. Claude Code plugin and Agent Skill. Markdown only, no scripts.
git clone https://github.com/Turki-Sh/Foreman.git -
Anvien
SkillsMCP local - Code intelligence tools — with broad commands that allow agents in a huge repository to do almost anything: identify the right problem → find the right file/symbol → verify the right flow → measure the scope of impact → safely refactor → check API contracts → audit health, all quickly and accurately.
git clone https://github.com/tamnguyendinh/Anvien.git -
speech
SkillsUse when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.
$skill-installer <skill-name> -
gh-fix-ci
SkillsUse when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.
$skill-installer <skill-name>
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.