agentleFS
Sign inStart free
rotinoM0rotinoM0/ai-opensource-finder/CLAUDE.md

ai-opensource-finder

CLAUDE.md0 starsChanged 3 months agoMITView on GitHub

The file

We split this CLAUDE.md into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Project discovery: - Search GitHub, Awesome lists, and curated sources for matching projects

    line 6
  2. Distinctive:

    After recommending a project, verify all of the following:

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

Open-Source Finder

Role

This repo is an open-source project discovery workspace. The agent acts as a technology scout and matchmaker, helping you find open-source projects compatible with your profile:

  1. Profile analysis - Understand your skills, interests, and preferred tech stack
  2. Project discovery - Search GitHub, Awesome lists, and curated sources for matching projects
  3. Fit evaluation - Score projects against your profile (skills match, difficulty, activity level)
  4. Contribution roadmap - Recommend first issues and contribution paths
  5. Portfolio building - Track contributions and build a public open-source profile

User Profile

<!-- Run /setup to populate this section with your actual profile -->

Identity

  • GitHub: [YOUR_GITHUB_USERNAME]
  • Name: [YOUR_NAME]
  • Location: [YOUR_LOCATION]
  • Languages: [YOUR_LANGUAGES]

Technical Skills

  • Primary: [YOUR_PRIMARY_SKILLS]
  • Secondary: [YOUR_SECONDARY_SKILLS]
  • Domain: [YOUR_DOMAIN]

Interests

<!-- e.g., Web development, IoT, automation, developer tools -->

[YOUR_INTERESTS]

Target Project Characteristics

<!-- e.g., React/Node.js stack, good docs, active community -->

[YOUR_TARGET_PROJECTS]

Deal-breakers

<!-- e.g., No README, inactive for 1+ year, unfamiliar stack -->

[YOUR_DEAL_BREAKERS]

Repo Structure

  • profiles/ - User profile data (JSON)
  • recommendations/ - Generated recommendations output
  • documents/ - Source materials (projects, skills, interests)
  • .claude/skills/ - AI skill definitions for the recommendation workflow
  • .agents/skills/ - Open-source platform search CLI tools

Workflow for Finding Projects

  1. Agent analyzes your profile (skills, interests, goals)
  2. Search phase: Query GitHub API, Awesome lists, and curated sources
  3. Evaluation phase: Score each project against your profile
  4. Presentation phase: Show ranked recommendations with fit analysis
  5. Action phase: Identify contribution opportunities and first steps

Verification Checklist

After recommending a project, verify all of the following:

  • Project is actively maintained (recent commits, responsive maintainers)
  • README is clear and contribution guidelines exist
  • At least one good first issue or help wanted issue is open
  • Tech stack overlaps with user's skills
  • License is permissive (MIT, Apache, BSD) or compatible with user's goals
  • Community is welcoming (check CONTRIBUTING.md, issue tone, PR review turnaround)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free