agentleFS
syangasyanga/astack/skills/astack-help/SKILL.md

astack-help

Skill0 starsChanged 53 days agoMITView on GitHub

Recommend astack skills for a task. Use when the user asks which astack skills exist or fit. Most astack skills are user-invoked and absent from this catalog.

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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. Very specific:

    Read astack's installation manifest at ${XDG_STATE_HOME:-$HOME/.local/state}/astack/manifest.json.

    line 8
  2. Distinctive:

    If the manifest is missing, ask for the installation location.

    line 11
  3. Distinctive:

    Check for an update before recommending:

    line 13
  4. Very specific:

    If it reports update available, ask the user whether to update astack from main now.

    line 19
  5. Very specific:

    Read the frontmatter names and descriptions of its existing /SKILL.md entries, including skills absent from the automatic catalog.

    line 25
  6. Distinctive:

    Stop after recommending. The approved update is the only skill workflow this skill runs.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Find the right astack skills

Read astack's installation manifest at ${XDG_STATE_HOME:-$HOME/.local/state}/astack/manifest.json. For --home installations, use that home's .local/state/astack/manifest.json. If the manifest is missing, ask for the installation location.

Check for an update before recommending:

python3 <skill-directory>/scripts/check_update.py <manifest>

If it reports update available, ask the user whether to update astack from main now. If they agree, follow astack-update, then reread the manifest. If it reports check skipped, show that line to the user. In every case, then recommend skills as below.

Under targets, select the current agent's map of installed file paths. Read the frontmatter names and descriptions of its existing /SKILL.md entries, including skills absent from the automatic catalog. Read promising skill bodies only to assess fit.

Recommend the smallest useful set for the task in the conversation, with a brief reason for each. When the task has open decisions the user owns, include one skill that settles them, the most specific one that fits, with "run this first" in its reason. This rule does not apply to bug fixes, investigations, or tasks whose decisions are settled. Add a glossary or ADR skill when the task needs one. If no skill fits the task, say so. Stop after recommending. The approved update is the only skill workflow this skill runs.

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.