AGENTS.md is agent-read markdown (agents) from kunanonj/ai-skills-hub.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
## Learned User Preferences
- Only create git commits when explicitly requested.
- Uses Söhne font in Cursor (editor, integrated terminal, debug console), not Test Söhne.
- Prefix shell commands with `rtk` for Headroom token savings when safe; use raw commands only for debugging.
- Configure MCP servers globally in `~/.cursor/mcp.json`; disable broken `plugin-*` duplicates in Settings → Tools & MCP and keep working user-defined entries.
- Reload Cursor (Developer: Reload Window) to pick up MCP and skills changes; full quit is rarely needed.
## Learned Workspace Facts
- Canonical GitHub repo is `https://github.com/KunanonJ/ai-skills-hub`; local workspace folder is `claude-skills-hub-lean`.
- Lean corpus ships exactly 100 skills; validate with `python -m app.skill_quality validate-lean`.
- Run tests from `.venv` with `python -m pytest`.
- Cursor global skills install: `npx skills add KunanonJ/ai-skills-hub -g -a cursor -s '*' --copy -y`.
- Full historical corpus is preserved on branch/tag `archive/full-corpus-fa85915`.
- Project-level skill mirror lives at `.agents/skills/`.
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
GET https://markdownregistry.com/api/v1/artifacts/art_ix6xkwn6r7zi4kyx
GET https://markdownregistry.com/api/v1/resolve?ref=kunanonj/ai-skills-hub/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/0e6da182c9920b156ffbe493e79bc3c3ab795570dcd7f59edeff11615cced7b0
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
kunanonj/ai-skills-hub · .agents/skills/analyze-codebase-for-mcp/SKILL.md · Analyze an arbitrary codebase to identify functions, APIs, and data sources suitable for exposure as MCP tools…
kunanonj/ai-skills-hub · .agents/skills/api-analyzer/SKILL.md · Validates whether an API request is correct based on provided inputs (method, URL, headers, body, auth, query params)…
kunanonj/ai-skills-hub · .agents/skills/api-design-principles/SKILL.md · Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight…
kunanonj/ai-skills-hub · .agents/skills/architecture-decision-records/SKILL.md · Comprehensive patterns for creating, maintaining, and managing Architecture Decision Records (ADRs) that capture the…
kunanonj/ai-skills-hub · .agents/skills/backend-api-design/SKILL.md · Design RPC-style APIs with layered architecture (Controller → Manager → Repository). Use when creating new API…
kunanonj/ai-skills-hub · .agents/skills/backend-dev-guidelines/SKILL.md · You are a senior backend engineer operating production-grade services under strict architectural and reliability…
kunanonj/ai-skills-hub · .agents/skills/backend-security-coder/SKILL.md · Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use…
kunanonj/ai-skills-hub · .agents/skills/browser-screenshot-diff/SKILL.md · Visual + DOM diff between two recorded sessions at matching trajectory step ids; used for visual regression and replay…
kunanonj/ai-skills-hub · .agents/skills/browser-testing-with-devtools/SKILL.md · Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use…
