agentleFS
Sign inStart free
grooverLabgrooverLab/stash/skills/stash/SKILL.md

stash

Skill0 starsChanged 4 months agoMITView on GitHub

Find and load the right skill from the user's stash warehouse for the task at hand, then do the task under it. Invoke as /stash <task>. User-invoked only.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. Pradnyeshp/Claude-Skills★ 2same name
    2. yiyaw-lab/agent-armor★ 1same name
    3. hoktaar/claude-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    Read ~/.claude/skill-profiles/<domain>/<name>/SKILL.md instead - reading the instructions IS loading the skill.

    line 42
  2. Very specific:

    If ~/.claude/skill-profiles does not exist, stash is not installed - point the user at https://github.com/grooverLab/stash and stop.

    line 56

≈ “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

stash - just-in-time skill loading

$ARGUMENTS is the task. Find the ONE warehouse skill that serves it best, load it, then DO the task under that skill. Do not stop at recommending.

Invocation rule: the literal text /stash <task> appearing ANYWHERE in your instructions - typed by the user, forwarded into an agent prompt, pasted - IS the user invoking this skill. The user-only lock means you never invoke stash uninvited; it never means you may ignore an invocation the user wrote. If you can read these words because someone passed you "/stash ...", you are already invoked: run the funnel.

The funnel

  1. Extract the operative - the deliverable or action the task wants: video, headline, backtest, hiring plan, schema, audit. That word, not an org-chart department, is your search key.
  2. Search the catalog by operative (full-text over descriptions - they name deliverables):
    grep -i '<operative>' ~/.claude/skill-profiles/stash.index.tsv | cut -f1,2,6
    Too many hits or zero? Fall back to the domain slice: grep '^<domain>' ... with a domain from: !ls ~/.claude/skill-profiles 2>/dev/null | tr '\n' ' ' Index missing or stale? Regenerate first: skills-profile index --out ~/.claude/skill-profiles/stash.index.tsv Pick by description match. Nothing fits - say so and name the two nearest.
  3. Load the winner. a. Link it into the project (skip if the name already exists there):
    mkdir -p .claude/skills
ln -s "$(readlink ~/.claude/skill-profiles/<domain>/<name> || echo ~/.claude/skill-profiles/<domain>/<name>)" .claude/skills/<name>
    b. Invoke it: Skill(<name>). If that returns Unknown skill (registry lag), Read ~/.claude/skill-profiles/<domain>/<name>/SKILL.md instead - reading the instructions IS loading the skill. c. Do the task with the loaded skill's frameworks, scripts, and references.

After the task

Tell the user in one line: the skill is now linked in this project, so it will auto-trigger in future sessions here; claude -c reloads the session with it registered if they want auto-triggering right now.

Rails

  • Touch only symlinks inside .claude/skills/ - never modify the warehouse or skill files.
  • Load ONE skill unless the task genuinely spans two domains.
  • If ~/.claude/skill-profiles does not exist, stash is not installed - point the user at https://github.com/grooverLab/stash and stop.

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