agentleFS
guardanaguardana/guardana/.claude/skills/refactor/SKILL.md

refactor

Skill225 starsChanged 40 days agoApache-2.0View on GitHub

Behaviour-preserving restructuring and cleanup — splitting an oversized module, removing dead code, finished scripts, flags or documents, consolidating duplicates, tightening comments. Use for any task whose promise is "nothing changes for users", in any of the five packages, in scripts/ or in docs/.

195 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use debug-fix, ascii-diagram 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.
  • zebbernSkill

    debug-fix

    Find and fix a bug or issue — from any source (GitHub issue, error message, user report, or observed behavior)

    Also in 4 projects that use this

  • SethGammonSkill

    ascii-diagram

    Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.

    Also in 4 projects that use this

  • parcadeiSkill

    agent-context-isolation

    Agent Context Isolation

    Also in 3 projects that use this

  • parcadeiSkill

    agentica-infrastructure

    Reference guide for Agentica multi-agent infrastructure APIs

    Also in 3 projects that use this

  • +8 more from parcadei

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Leave alone: docs/generated/ (regenerate it), schemas/ (versioned contracts — a change is a migration, not a cleanup), …

    line 41

“Common” is measured: kept by at least 6 in 10 of the 170 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

Refactor and cleanup

Target: $ARGUMENTS

The promise is "same behaviour". Every step below exists to make that promise checkable.

1. Inventory before touching (delegate the sweep)

Send scout for callers and references; do not read the tree yourself. For each candidate record the evidence, because "looks unused" has been wrong here before:

claimevidence that settles it
code is deadno import or call (git grep), not reached through an entry-point group, the registry, a YAML evaluator: / requires: string, a CLI command table, a schema $ref or a fixture; a test alone does not make it live
a script is finishedone-off by its own docstring AND not named in CI, .pre-commit-config.yaml, scripts/release.py, a skill or another script
a flag or option is deadno producer anywhere (CLI, profile schema, guardana.yaml examples, Action inputs, CI templates)
a document is consumedits findings are closed or live elsewhere; no LIVE file cites its path

Low reference count on a recent file means "new", not "dead" — check git log -1 first.

2. Pin behaviour

  • Green full gate on the untouched tree (/gate), so later red is yours.
  • Where tests do not cover the target, write characterisation tests FIRST from real inputs: the fixtures in guardana.core.testing, a saved run under examples/, a scripted transport.
  • For anything that writes a document: run the documented command on a fixture before and after, and diff the JSON. Expected result: no difference.

3. Change in small, reversible commits

  • Move/rename in one commit, change in the next: a reviewer can only trust a move that is pure.
  • One theme per commit: "split x.py by concept" and "delete finished scripts" are two.
  • Deleting is cheap because git keeps it — but fix every inbound reference in the SAME commit: docs/index.md (the nav refuses a missing page), docs/ links (a test refuses a dead one), site/llms.txt and site/docs/ (regenerate), CLAUDE.md, .claude/rules/, the skills.
  • Leave alone: docs/generated/ (regenerate it), schemas/ (versioned contracts — a change is a migration, not a cleanup), examples/vulnerable-model/ (deliberately malicious fixture), anything a user's persisted document depends on.
  • Comment cleanup follows the hard rule: keep the WHY, drop dates, names, incident stories and references to decisions; history goes to the commit message.

4. Prove nothing moved

Full gate green; the before/after artifact diff empty; guardana scan packages --profile scripts/dogfood.yaml still at zero findings. Then /review.

5. Report

What was removed or moved and the evidence for each, what was kept and why, what is left as an issue.

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.