agentleFS
Sign inStart free
pankaj-mahaurpankaj-mahaur/Agent-Daemon/skills/daemon/skill-installer/SKILL.md

skill-installer

Skill0 starsChanged 6 days agoMITView on GitHub

Use when the user asks to install, add, remove, or find a skill — \"install this skill\", \"add skill X\", \"install skill from <url>\", \"skill install karo\", \"ye skill add karo\", \"uninstall skill\", \"remove skill\", \"what skills are available\", \"find a skill for X\" — or pastes a git URL of a skill repo to use. Drives the `ad skill` CLI: bundled catalog, local paths, or git repos, lint-validated, provenance recorded, right lane selected.

  • Deletes or force-pushes

46 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use meeting-notes-and-actions, pr-review-ci-fix and 10 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.
  • ComposioHQSkill

    meeting-notes-and-actions

    Turn meeting transcripts or rough notes into crisp summaries with decisions, risks, and owner-tagged action items; use for Zoom/Meet/Teams transcripts, call notes, or long meeting chats to generate share-ready outputs.

    Also in 4 projects that use this

  • ComposioHQSkill

    pr-review-ci-fix

    Automated PR review and CI auto-fix for GitHub and GitLab using the Composio CLI. Pulls diffs, fetches failing job logs, posts review comments, and loops fix commits until checks go green.

    Also in 4 projects that use this

  • petestewartSkill

    datadog-logs

    Query Datadog logs via the Logs Search API v2. Use when the user asks to "check the logs", "search logs", "find errors in Datadog", "look up logs for", "show me production logs", "check for errors", "search Datadog", or any request involving log search, error investigation, or production debugging that requires Datadog log data.

    Also in 3 projects that use this

  • MicrosoftSkill

    deploy-pipeline

    Triggers a Power Platform Pipeline deployment run for a Power Pages solution. Selects a target stage, validates the package, optionally configures deployment settings (environment variables, connection references), then deploys and polls for completion. Use when asked to: "deploy pipeline", "run pipeline", "trigger deployment", "deploy to staging", "deploy to production", "run power platform pipeline", "deploy solution via pipeline", "promote solution", "push to staging", "push to production".

    Also in 3 projects that use this

  • +8 more from ComposioHQ

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 41 edited versions we read keep these.

  • 1

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Git installs: read the skill's description back to the user before confirming — they should know what they just added (supply-chain …

    line 46
  2. Very specific:

    Never rm -rf skill directories by hand — the manifest and route maps must stay in sync.

    line 62
  3. Very specific:

    Ask the user before --replace.

    line 79

“Common” is measured: kept by at least 6 in 10 of the 41 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 Installer

Install skills through ad skill — never by hand-copying folders. The CLI lint-gates the frontmatter, records provenance (source + commit + sha256) in ~/.agent-daemon/skill-manifest.json, and recompiles the route maps so the routing hook starts recommending the new skill immediately.

1. Resolve the source

User gave youDo this
A bare name ("install debug-triage")ad skill search <name> first; on a bundled hit, install by name
A vague need ("a skill for accessibility")ad skill search <keyword>, show the hits, install the chosen one
A local pathVerify <path>/SKILL.md exists (or it's a folder of skills) before installing
A git URLPass it through verbatim; multi-skill repos need --skill <name> — the CLI lists candidates on ambiguity

2. Decide the lane

  • Default: global (~/.claude/skills/) — available in every project.
  • --project (<cwd>/.claude/skills/) when the skill is stack- or project-specific, or the user says "for this project" / "sirf is project ke liye". Project-local shadows a same-named global skill.

3. Install and verify

ad skill install <spec> [--project] [--skill <name>]
ad skill list                      # confirm it landed, with provenance
  • Lint failure: show the errors. Offer to fix the frontmatter (follow skill-author conventions) and retry. --force only if the user insists — say why the lint failed first.
  • Already installed: tell the user; --force overwrites, ad init refreshes bundled skills.
  • Git installs: read the skill's description back to the user before confirming — they should know what they just added (supply-chain hygiene).

4. Mid-session bridge (important)

Claude Code discovers skills at session start. After installing:

  1. Tell the user it will auto-trigger from the next session.
  2. To use it NOW: Read the installed SKILL.md and follow its procedure inline.

5. Removal

ad skill remove <name> [--project] [--force]

Never rm -rf skill directories by hand — the manifest and route maps must stay in sync. Unmanaged (hand-authored) skills need --force and a heads-up to the user.

6. Other hosts and versions

Skills ad improves (accepted in ad review) are versioned in ~/.agent-daemon/skills/<name>/ and written to the hosts that read skills:

ad skill history <name>                # every version and where it came from
ad skill publish [<name>] [--host <id>] [--dry-run]   # write accepted skills to the hosts' skills folders
ad skill undo <name>                   # an older version becomes current (asks the user to type it)
  • ad overwrites only a folder it wrote itself and that nobody changed since; otherwise it says so and keeps the folder (--replace backs it up first). Ask the user before --replace.
  • undo refuses from the agent's own shell: hand the user the command.

Anti-patterns

  • Hand-copying skill folders into ~/.claude/skills/ (no lint, no provenance, stale route map).
  • Installing a multi-skill repo wholesale when the user asked for one skill.
  • Forcing past lint errors without telling the user what was wrong.
  • Writing a new SKILL.md from scratch when the user said "install" — that's skill-author's job, and only for authoring.

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