agentleFS
jnsfhrmnnjnsfhrmnn/jf-agentic-coding-starter-kit/.claude/skills/claude-skill-proxy-sync/SKILL.md

claude-skill-proxy-sync

Skill1 starsChanged 4 months agoMITView on GitHub

Synchronize canonical repository-local Claude skills from .claude/skills into portable thin Codex proxies under .codex/skills. Use after adding, renaming, moving, or removing a local skill, or after changing its YAML trigger description or agents/openai.yaml interface metadata. Do not use for ordinary SKILL.md body edits because Codex reads the canonical Claude file at runtime.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 8 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep one canonical skill implementation for Claude and Codex without installing anything into a user's global skill directories.

    line 8
  2. Distinctive:

    Every proxy resolves the repository root at runtime and reads the canonical Claude skill through a repository-relative path.

    line 15
  3. Very specific:

    Never read from or write to %USERPROFILE%\.claude\skills, %USERPROFILE%\.codex\skills, ~/.claude/skills, ~/.codex/skills, or …

    line 17
  4. Distinctive:

    Never embed the current machine's absolute repository path in a proxy.

    line 20
  5. Distinctive:

    Run the sync after:

    line 25
  6. Distinctive:

    Do not sync after an ordinary body, script, reference, or asset edit.

    line 32
  7. Distinctive:

    Read AGENTS.md, CLAUDE.md, and repository rules before changing files.

    line 38
  8. Distinctive:

    If a canonical skill was deliberately removed, review the stale list and prune only generated proxies:

    line 53
  9. Very specific:

    Run the script once more without --apply.

    line 60
  10. Distinctive:

    Run the bundled tests and skill validation.

    line 62
  11. Very specific:

    Use --name <skill-name> to inspect or update one skill.

    line 64

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill 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
SKILL.md

Claude Skill Proxy Sync

Keep one canonical skill implementation for Claude and Codex without installing anything into a user's global skill directories.

Contract

  • .claude/skills/<name>/SKILL.md is the canonical implementation.
  • .codex/skills/<name>/SKILL.md is a generated thin proxy.
  • Every proxy resolves the repository root at runtime and reads the canonical Claude skill through a repository-relative path.
  • Never read from or write to %USERPROFILE%\.claude\skills, %USERPROFILE%\.codex\skills, ~/.claude/skills, ~/.codex/skills, or $CODEX_HOME/skills.
  • Never embed the current machine's absolute repository path in a proxy.
  • Preserve csk-adopt-plan-scaffold; it is a required bundled skill.

Decide Whether Sync Is Needed

Run the sync after:

  • adding, renaming, moving, or deleting a directory in .claude/skills;
  • changing name or description in a canonical skill's YAML frontmatter;
  • changing display_name, short_description, or default_prompt in a canonical skill's agents/openai.yaml.

Do not sync after an ordinary body, script, reference, or asset edit. The proxy loads those canonical repo-local files at runtime, so those changes are live.

Workflow

  1. Resolve the current Git repository root. Stop if .claude/skills is missing.
  2. Read AGENTS.md, CLAUDE.md, and repository rules before changing files.
  3. Inspect the plan without writing:

    python .claude/skills/claude-skill-proxy-sync/scripts/sync_claude_skill_proxies.py --repo .
  4. Review every create, update, stale, or conflict result. Never overwrite an unmanaged Codex skill.
  5. Apply safe creates and updates:

    python .claude/skills/claude-skill-proxy-sync/scripts/sync_claude_skill_proxies.py --repo . --apply
  6. If a canonical skill was deliberately removed, review the stale list and prune only generated proxies:

    python .claude/skills/claude-skill-proxy-sync/scripts/sync_claude_skill_proxies.py --repo . --apply --prune
  7. Run the script once more without --apply; it must report ok for every canonical skill and no stale proxies.
  8. Run the bundled tests and skill validation.

Use --name <skill-name> to inspect or update one skill. Use --json for a machine-readable plan. Read references/proxy-plan.md before changing the proxy schema or generator behavior.

Safety

  • --prune is valid only with --apply and removes only directories carrying this generator's marker.
  • A target without the marker is a conflict and remains untouched.
  • Generated paths must remain inside .codex/skills under the resolved repo.
  • AGENTS.md and CLAUDE.md are maintained source files, not generated output. Change them only when the user authorized that exact change.

Completion Evidence

Report the canonical skill count, created/updated/pruned proxies, conflicts, test results, and confirmation that no generated file contains an absolute or global user path.

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.