agentleFS
Sign inStart free
trac3r00trac3r00/agent-skills/skills/skill-sync/SKILL.md

skill-sync

Skill0 starsChanged 3 months agoMITView on GitHub

Discovers custom skills across every AI provider install on the machine — Claude Code, Codex, OMO, gjc, OpenCode, Gemini, Cursor, Factory, and plugin caches — and unifies them into one universal directory (symlinks by default) so any SKILL.md-reading agent can use all of them. Reports provenance, dedupes by name and resolved path, and surfaces cross-provider conflicts.

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use tdd.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • GoogleSkill

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Add any other root with --root DIR (repeatable).

    line 41
  2. Very specific:

    After sync, every provider-specific skill is available to every agent.

    line 61

“Common” is measured: kept by at least 6 in 10 of the 18 edited versions of this file we could read. “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
SKILL.md

Skill Sync

One machine, many agents, one skill library. skill_sync.py scans the known skill roots of every AI provider, parses each SKILL.md frontmatter, dedupes, and can materialize the union into a single universal directory.

Commands

python3 scripts/skill_sync.py doctor          # which provider roots exist here
python3 scripts/skill_sync.py list            # unified inventory with provenance
python3 scripts/skill_sync.py list --json     # machine-readable
python3 scripts/skill_sync.py sync --dry-run  # preview what would be linked
python3 scripts/skill_sync.py sync            # symlink all into ~/.agents/skills
python3 scripts/skill_sync.py sync --copy --target /some/dir   # portable copies

Scanned providers (priority order — earlier wins name conflicts)

  1. ~/.agents/skills (the universal target itself)
  2. ~/.claude/skills (Claude Code user skills)
  3. ~/.codex/skills (Codex)
  4. ~/.omo/skills and the omo-ai plugin install (OMO/Senpi)
  5. ~/.gjc/skills (gajae-code)
  6. ~/.config/opencode/skills (OpenCode)
  7. ~/.gemini, ~/.cursor, ~/.factory skills dirs
  8. ~/.claude/plugins/cache/*/*/*/skills (installed plugin skills; newest version of a plugin wins over older cached versions)

Add any other root with --root DIR (repeatable). Missing roots are skipped silently — doctor shows what exists. --no-default-roots scans only the --root dirs you pass (useful for tests and scripted audits).

Semantics

  • Dedupe: identical resolved paths (symlinks back to the same skill) count once; same name from different providers keeps the highest-priority one and records a conflict.
  • Sync is non-destructive: existing entries in the target are never overwritten; a mismatch is reported as skip-exists. Symlinks keep the provider's copy as the single source of truth; --copy makes standalone copies for machines you'll sync to.
  • Gate: --fail-on-conflict exits 1 when two providers ship different skills under the same name — useful in CI or a dotfiles check.

Making agents read the universal directory

Most SKILL.md-reading agents accept a skills directory: point Claude Code, Codex, OMO, or any other harness at ~/.agents/skills (many already read it). After sync, every provider-specific skill is available to every agent.

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