agentleFS

Find the best CLAUDE.md, AGENTS.md and Claude skills

One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.

Worked for most · soon
svg153Skill

startup-positioning

svg153/skills/skills/startup-positioning/SKILL.md

Market positioning strategy using the April Dunford framework, enriched with JTBD discovery, Moore positioning statement, and Neumeier's Onliness Test. Produces a complete positioning document, positioning statement, competitive alternatives map, and market category analysis. Use when the user wants to define or refine their market positioning, find their unique position, differentiate from competitors, craft a positioning statement, choose a market category, or figure out "how should we position this product." Triggers for "positioning", "how to position", "market position", "differentiation strategy", "positioning statement", "competitive positioning", "category strategy", "where do we fit in the market", "how are we different", "unique value proposition", or any request to define, sharpen, or rethink positioning. Works standalone — no prior startup-design or startup-competitors session needed, but leverages their output if available.

151d agoReviewMountCreate a free account to mount
svg153Skill

svg153-writing-style

svg153/skills/skills/svg153-writing-style/SKILL.md

Trigger: como si hablara yo, ordéname este mensaje, para copiar y pegar en WhatsApp, que no suene a IA, write like me. Preserve svg153's Spanish voice across messages, emails and technical posts.

151d agoReviewMountCreate a free account to mount
svg153Skill

work-unit-commits

svg153/skills/skills/work-unit-commits/SKILL.md

Organize implementation, tests and relevant documentation into coherent, reviewable commits rather than file-type batches. Use when choosing commit boundaries, splitting a feature into independently meaningful changes, preparing commits for review, or building a single PR or PR chain. Commit boundaries need not become separate PRs; follow the selected delivery mode and project budget.

151d agoReviewMountCreate a free account to mount
svg153AGENTS.md

github-stars-contrib-mcp-server

svg153/github-stars-contrib-mcp-server/AGENTS.md

Source of truth: src/githubstarscontrib_mcp/tools/* and src/githubstarscontrib_mcp/utils/*. Never translate a legacy GraphQL contribution/server ID into a REST client_id. Do not invent a contribution DELETE operation; deletion is a Stars web UI…

02mo agoReviewMountCreate a free account to mount
svg153Skill

discover-my-contributions

svg153/github-stars-contrib-mcp-server/skills/discover-my-contributions/SKILL.md

Bootstrap trusted sources, run bounded discovery, and present a review queue without publishing.

02mo agoReviewMountCreate a free account to mount
svg153Skill

publish-approved

svg153/github-stars-contrib-mcp-server/skills/publish-approved/SKILL.md

Dry-run first, then publish already-approved candidates only after explicit current user intent.

02mo agoReviewMountCreate a free account to mount
svg153Skill

review-candidates

svg153/github-stars-contrib-mcp-server/skills/review-candidates/SKILL.md

Inspect evidence-backed candidates and record explicit approve, edit, reject, or defer decisions.

02mo agoReviewMountCreate a free account to mount
svg153Skill

sync-source

svg153/github-stars-contrib-mcp-server/skills/sync-source/SKILL.md

Synchronize one configured source and report capability/provider failures without bypasses.

02mo agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

Agent instruction files

What are agent instruction files?

Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.

CLAUDE.md or AGENTS.md?

CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.

What is a skill?

A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.

Can I search my own team's files too?

Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.