agentleFS
Sign inStart free
truemetal74truemetal74/skills/stack-audit/SKILL.md

stack-audit

Skill0 starsChanged 21 days agoMITView on GitHub

Audit a house-stack web project (React+Vite front-end, FastAPI+Firestore back-end, Cloud Run deploy) against the canonical shared packages and skill templates, producing a drift report and optionally applying upgrades. Use this when asked to audit/sync/align a project with the standard stack, after changing any shared package or skill template (to propagate the fix to all projects), when a bug fixed in one project may exist in the siblings, or periodically as stack hygiene — even if the user just says "is this project up to date?".

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. VECTORG99/acf★ 2same name
    2. patmeh1/product-docs-kit★ 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 repository7 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Always produce this table, worst first, before proposing any change:

    line 35
  2. Distinctive:

    Follow with a short "recommended fixes in order" list.

    line 40
  3. Distinctive:

    If the *project* has an improvement the canon lacks (newer behavior, a bugfix, a better pattern), that is canon-drift, not project-drift: …

    line 47

≈ “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

Stack audit — drift detection against the canonical stack

The reuse system has two layers: pip packages (github.com/truemetal74/my-python, local source C:\prog\my-py) and skill templates (the sibling skills in this repo). Both only help if projects actually track them. This skill compares one project against both layers and reports drift; fixes are applied only on request.

Known fleet (audit others on demand): C:\prog\perfect-resume (migrated 2026-07), C:\prog\brandician, C:\prog\wine-your-sign.new (both still on embedded copies).

Procedure

Work through references/checklist.md area by area (read it now). For each item:

  1. Locate the project's counterpart file (paths differ per project — search, don't assume).
  2. Compare against the canonical source listed in the checklist. Template files contain PROJECT CONFIG markers — differences inside those blocks are expected and NOT drift; differences in the engine/invariant parts ARE.
  3. Classify each finding:
    • BUG-CLASS — the project misses a fix/behavior the canon has (e.g. no 401 refresh, no /config.js no-cache rule, missing update_field date conversion). These are the "fixed it in one project, not the others" cases the system exists to kill.
    • STRUCTURAL — embedded copy where a shared package should be used, wrong SA name, unpinned/divergent library versions.
    • COSMETIC — naming/layout differences with no behavioral impact. List briefly, don't push fixes.

Report format

Always produce this table, worst first, before proposing any change:

#AreaProject fileCanonical sourceDriftClass

Follow with a short "recommended fixes in order" list. Apply fixes only when the user asks; prefer one commit per area so each upgrade is independently revertable. After applying, re-run the relevant checklist section to confirm the drift is gone, and run the project's tests.

Reverse drift

If the project has an improvement the canon lacks (newer behavior, a bugfix, a better pattern), that is canon-drift, not project-drift: propose updating the shared package / skill template instead, then propagating to the other projects. The canon must stay the best-known version or the whole system rots.

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