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
- mannobeats/hyper-tastetheir own version, first seen Nov 16, 2026
- GoBeromsu/craft-skillstheir own version, first seen Nov 16, 2026
- erikperttu/steering-coding-agentstheir own version, first seen Nov 16, 2026
- chuckplayer/claude-agent-packtheir own version, first seen Nov 16, 2026
- Archont561/skillstheir own version, first seen Nov 15, 2026
- nazmirket/skillstheir own version, first seen Nov 15, 2026
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.
zebbernSkilldebug-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
SethGammonSkillascii-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
parcadeiSkillagent-context-isolation
Agent Context Isolation
Also in 3 projects that use this
parcadeiSkillagentica-infrastructure
Reference guide for Agentica multi-agent infrastructure APIs
Also in 3 projects that use this
- +8 more from parcadei
Other versions195 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 195
- github/awesome-copilot★ 41ksame name
- unkeyed/unkey★ 5.5ksame name
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- adobe/S3Mock★ 1.2ksame name
- SethGammon/Citadel★ 927same name
- poshan0126/dotclaude★ 871same name
- JordanCoin/codemap★ 715same name
- membrane/api-gateway★ 660same name
185 more not listed
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 repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- site/llms.txtllms.txt
- add-a-ruleSkill
- autoSkill
- buildSkill
- debugSkill
- docsSkill
- false-green-auditSkill
- gateSkill
- planSkill
- reviewSkill
- shipSkill
- site-checkSkill
- stackSkill
- workSkill
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
- Very specific: line 41
Leave alone: docs/generated/ (regenerate it), schemas/ (versioned contracts — a change is a migration, not a cleanup), …
“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.
Files
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:
| claim | evidence that settles it |
| code is dead | no 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 finished | one-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 dead | no producer anywhere (CLI, profile schema, guardana.yaml examples, Action inputs, CI templates) |
| a document is consumed | its 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 underexamples/, 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.pyby 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.txtandsite/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.
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
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.

