agentleFS
Sign inStart free
its-everdredits-everdred/skills/skill-sync/SKILL.md

skill-sync

Skill2 starsChanged 20 days agoMITView on GitHub

Use when the user asks to set up, run, or debug syncing of their skills repo (~/github/skills) into Claude Code, Codex and ~/.agents/skills, or says a skill added to the repo isn't showing up on this machine. Pulls the repo, links every skill into ~/.claude/skills, ~/.codex/skills and ~/.agents/skills, and installs the pinned `shared` skills from external-skills.json; a SessionStart hook does this automatically in every new chat.

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use session-handoff, verification-before-completion and 2 more.

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.
  • wpankSkill

    session-handoff

    WHAT: Create comprehensive handoff documents that enable fresh AI agents to seamlessly continue work with zero ambiguity. Solves long-running agent context exhaustion problem.

    Also in 3 projects that use this

  • OpenAISkill

    verification-before-completion

    Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

    Also in 3 projects that use this

  • OpenAISkill

    test-driven-development

    Use when implementing any feature or bugfix, before writing implementation code

    Also in 3 projects that use this

  • 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:

    Every skill in this repo is linked into ~/.claude/skills/<name>, ~/.codex/skills/<name> and ~/.agents/skills/<name>, so adding a skill to …

    line 8
  2. Very specific:

    Run ~/github/skills/skill-sync/scripts/sync.sh and report what it printed (silence means nothing changed).

    line 29

“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

Every skill in this repo is linked into ~/.claude/skills/<name>, ~/.codex/skills/<name> and ~/.agents/skills/<name>, so adding a skill to the repo and pushing it makes it available on every machine that has this set up.

How it runs

  • scripts/session-start.sh is a SessionStart hook in both Claude Code and Codex. On every new chat it runs scripts/sync.sh, then passes the chat any skill changes and the open items in ~/remind.md (see the remind skill).
  • scripts/sync.sh pulls fast-forward only, and only when the checkout is a clean main (8-second cap via python3, so offline and macOS without timeout are fine). Then it links missing skills and removes links to skills deleted from the repo. It never replaces a real directory: a skill installed some other way under the same name wins.
  • sync.sh links ~/.claude/CLAUDE.md to the repo's global/CLAUDE.md (edit it there) when the local file is missing or identical; a different local file is reported, not replaced.
  • sync.sh then runs sync-external.sh --shared-only: pinned third-party skills from the manifest's shared section are copied into ~/.agents/skills (never overwriting a differing one) and linked into ~/.claude/skills. Conflicts and failures are printed as shared: ....
  • A skill linked during a chat is available from the next chat.

Set up a machine (once)

git clone git@github.com:its-everdred/skills.git ~/github/skills
~/github/skills/skill-sync/scripts/install.sh

The installer adds the hook to ~/.claude/settings.json and ~/.codex/hooks.json (each backed up to .bak first), and runs a first sync. Running it again changes nothing. Codex may ask once to trust the new hook.

When asked to sync now

Run ~/github/skills/skill-sync/scripts/sync.sh and report what it printed (silence means nothing changed). If a skill doesn't link, check for a real directory with the same name in the target. Don't delete it without asking.

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