Skills Hub is a cross-platform desktop application for installing, organizing, updating, and syncing Agent Skills across AI coding tools. Developers use it to maintain one central skill library and distribute selected skills to tools such as Claude Code, Codex, Cursor, OpenCode, and Antigravity. Its catalogue instructions describe how to work with the managed skills.
Borrowing it
Nothing to install: this file belongs to qufei1993/skills-hub. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/qufei1993/skills-hub/main/AGENTS.mdgit clone --depth 1 https://github.com/qufei1993/skills-hubWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/qufei1993/skills-hub/agents-md)<a href="https://agentmods.dev/instructions/qufei1993/skills-hub/agents-md"><img src="https://agentmods.dev/badge/instructions/qufei1993/skills-hub/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/qufei1993/skills-hub/agents-md"><img src="https://agentmods.dev/badge/instructions/qufei1993/skills-hub/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02350 | $0.02350 |
| Opus 5 | $0.01175 | $0.01175 |
| Sonnet 5 | $0.00470 | $0.00470 |
| Haiku 4.5 | $0.00235 | $0.00235 |
Grade A, and why
skills-hub AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills Hub - Project Rules
Reply in Chinese; write PR titles and descriptions in English.
Overview
Skills Hub is a cross-platform desktop app (Tauri 2 + React 19) for managing AI Agent Skills and syncing them to 47+ AI coding tools. Core concept: "Install once, sync everywhere."
Tech Stack
- Frontend: React 19 + TypeScript 5.9 (strict) + Vite 7 + Tailwind CSS 4
- Backend: Rust (Edition 2021, MSRV 1.77.2) + Tauri 2
- Database: SQLite (rusqlite, bundled)
- Git: libgit2 (git2 crate, vendored-openssl)
- HTTP: reqwest (rustls-tls, blocking)
- i18n: i18next (English / Simplified Chinese / Korean)
- Notifications: sonner (toast)
- Icons: lucide-react
Common Commands
npm run dev # Vite dev server (port 5173)
npm run tauri:dev # Tauri dev window (frontend + backend)
npm run build # tsc + vite build
npm run check # Full check: lint + test + build + rust:fmt:check + rust:clippy + rust:test
npm test # Frontend regression tests
npm run lint # ESLint (flat config v9)
npm run rust:test # cargo test
npm run rust:clippy # Rust lint
npm run rust:fmt # Rust format
npm run rust:fmt:check # Rust format check
Directory Structure
src/ # React frontend
├── App.tsx # Root component (centralized state, all modal states)
├── App.css # Global styles (all component styles live here)
├── index.css # CSS variables (theming) + Tailwind entry
├── components/
│ ├── Layout.tsx # Main layout (sidebar + content area)
│ └── skills/ # Skills feature module
│ ├── Header.tsx # Top bar (branding + language toggle + new button)
│ ├── FilterBar.tsx # Filter/sort bar
│ ├── SkillsList.tsx # Skills list container
│ ├── SkillCard.tsx # Individual skill card
│ ├── LoadingOverlay.tsx
│ ├── types.ts # Shared DTO type definitions (frontend ↔ backend)
│ └── modals/ # Modal components (8 total)
└── i18n/
├── index.ts # i18next initialization
├── resources.ts # English/Chinese resources + locale registration
└── ko.ts # Korean translation resources
src-tauri/src/ # Rust backend
├── main.rs # Entry point (calls app_lib::run)
├── lib.rs # App initialization (plugin registration, DB, cleanup tasks)
├── commands/
│ ├── mod.rs # Tauri command layer (23 commands + DTOs)
│ └── tests/
└── core/ # Core business logic
├── skill_store.rs # SQLite ORM (4 tables: skills, skill_targets, settings, discovered_skills)
├── installer.rs # Skill installation (local/git, with multi-skill detection)
├── sync_engine.rs # Sync engine (symlink/junction/copy triple fallback)
├── git_fetcher.rs # Git clone/pull (with cache and TTL)
├── tool_adapters/mod.rs # Tool adapter registry (47 AI tools)
├── onboarding.rs # Existing skill scanning/discovery
├── github_search.rs # GitHub API search
├── central_repo.rs # Central repository path management
├── content_hash.rs # SHA256 directory content hashing
├── cache_cleanup.rs # Git cache cleanup
├── temp_cleanup.rs # Temp directory cleanup
└── tests/ # One test file per module (10 total)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · +16 lines · +441 tokens per session 5027d22a46a5
- 10d ago First seen · 146 lines · 1,909 tokens per session scan A 62e21b7ef6e8
skills-hub AGENTS.md is an instructions file published in the GitHub repository qufei1993/skills-hub (1,636 stars, last pushed today), licensed MIT. It adds 2,350 tokens to every session, about $0.0118 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.