agentleFS
vladcheckvladcheck/agentic/skills/update-skills-via-skills-sh/SKILL.md

update-skills-via-skills-sh

Skill1 starsChanged 14 days agoMITView on GitHub

Use when installing or updating agent skills with skills.sh, avoiding repo-local .agents installs, or enabling OMP discovery. Not for skill authoring.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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. Distinctive:

    Use the same command for both operations.

    line 21
  2. Very specific:

    Verify each expected skill at the global Claude Code location.

    line 23
  3. Very specific:

    If project-local installation was not requested, distinguish new output from pre-existing content.

    line 37

≈ “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

Install or update skills via skills.sh

  1. Record the original directory, then set the command working directory to the user's home directory. The current working directory determines where the CLI can create ./.agents/skills/; running from a repository can pollute that repository instead of producing the intended global installation.

    project_dir=$PWD
    cd "$HOME"
  2. Install or update from a source identified as <owner>/<repo>:

    DISABLE_TELEMETRY=1 npx -y skills add <owner>/<repo>

    Use the same command for both operations. Rerun it to overwrite previously installed skills with the source's current versions.

  3. Verify each expected skill at the global Claude Code location; do not treat CLI success or an .agents directory alone as proof of installation:

    test -f "$HOME/.claude/skills/<skill-name>/SKILL.md"
  4. Inspect the original directory for an unintended repository-local installation:

    if [ -d "$project_dir/.agents" ]; then
      printf 'Inspect installation output: %s\n' "$project_dir/.agents"
    fi

    If project-local installation was not requested, distinguish new output from pre-existing content. Move only confirmed unwanted output to a trash or backup location; if .agents pre-existed, move only the newly added skill entries. Do not recursively delete the directory.

  5. Inspect the OMP configuration actually loaded in the target environment, following includes or symlinks when present rather than assuming a personal dotfiles path. Ensure skills.customDirectories includes ~/.claude/skills, preserving the active configuration's existing style:

    skills:
      customDirectories:
        - ~/.claude/skills

    Confirm that the configured directory exists:

    test -d "$HOME/.claude/skills"

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.