agentleFS
Sign inStart free
n24q02mn24q02m/wet-mcp/skills/lock-project-stack/SKILL.md

lock-project-stack

Skill23 starsChanged 9 months agoApache-2.0View on GitHub

Detect a project's manifest (pyproject.toml / package.json / go.mod / Cargo.toml), pin its library set into wet's Cabinets project_context, then route subsequent docs queries to the locked versions automatically.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. n24q02m/wet★ 23100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    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 repository7 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 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.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user gave an absolute path, use it.

    line 17

≈ “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

lock-project-stack

Bind a project to its declared dependency versions so every search(action="docs_query") call from inside that project surfaces docs for the exact versions you pinned, instead of "latest". Mirrors the Cabinets workflow from spec section 4.3.

Steps

  1. Resolve the project root:
    • If the user gave an absolute path, use it.
    • Otherwise infer the root from the current workspace context (e.g. git rev-parse --show-toplevel output).
    • Confirm at least one supported manifest exists: pyproject.toml, package.json, go.mod, or Cargo.toml.
  2. Lock the project:
    • Call search(action="docs_lock_project", project_path=<abs_path>).
    • The response includes total detected libraries + indexed count (how many already have docs in Tier 1 or Tier 2). Surface both numbers to the user so they know how much coverage they have today.
  3. Trigger Tier 2 ingestion for missing libraries (optional):
    • Iterate the locked_libraries list; for entries with indexed == false, call search(action="docs_query", library=<name>, project_path=<abs_path>, query="<library> overview") once. The first call kicks off background Tier 2 ingestion; subsequent calls return real chunks.
  4. Verify lock reuse:
    • Re-call search(action="docs_query", library=<name>, project_path=<abs_path>, query=...) WITHOUT specifying version. The response should include a non-null lock_pin field matching the version from the manifest, confirming Cabinets is honoring the pin.
  5. Surface the pin to the user:
    • Summarize "Locked N libraries against versions X.Y.Z (M already indexed, K queued for Tier 2 ingestion)."

Best practices

  • Re-run after every dependency bump so the lock stays in sync with what is actually installed.
  • For monorepos, lock each workspace project separately — wet keys on absolute path so apps/web and apps/api get distinct locks.
  • The lock is a hint, not a hard constraint — callers can always override the version by passing it explicitly to docs_query.

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