agentleFS
Sign inStart free
greglas75greglas75/zuvo/skills/refactor/SKILL.md

refactor

Skill7 starsChanged 27 days agoMITView on GitHub

Refactor existing code by extracting helpers, splitting files, removing duplication, or untangling dependencies. Supports resumable and batch runs. Use for structural changes that preserve behavior; use zuvo:build for new features.

196 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

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

  • 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

  • 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

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 169 edited versions we read keep these.

  • 4

    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. Distinctive:

    Follow the user's current authorization, project verification rules and behavior scope.

    line 55
  2. Distinctive:

    Do not concatenate every phase at entry.

    line 72
  3. Very specific:

    Create new v7 contracts using ../../shared/includes/refactor-reference.md.

    line 97
  4. Distinctive:

    Use the real exit status. This calls the hook predicates.

    line 109
  5. Distinctive:

    Never claim COMPLETE over a pending check or critical unresolved requirement.

    line 117

“Common” is measured: kept by at least 6 in 10 of the 169 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

zuvo:refactor

Refactor the requested symbols while preserving their observed behavior. Resolve ../../shared/includes/execution-policy.md and ../../shared/includes/evidence-reuse.md once. Follow the user's current authorization, project verification rules and behavior scope.

Argument Parsing

ArgumentAction
<file(s)>Analyze and refactor this scope
continueResume the selected contract at its recorded phase
batch <file>Load batch handling in references/completion.md and ../../shared/includes/refactor-reference.md
no-commitFinish verification; retain uncommitted work and report its location
Other documented flagsResolve the full argument table in references/bootstrap.md

Mandatory File Loading

Load only the current phase reference below. Read its required includes when that phase needs them; use the realpath/hash/context-generation receipt protocol in evidence-reuse.md. After compaction reload current requirements; a persistent file ledger is not retained context. Do not concatenate every phase at entry. Missing optional enrichment is a named degradation; missing mandatory safety definitions blocks the dependent assessment.

Phase routing

Phase / contract boundaryRead on entryRequired outcome
0: discoveryreferences/bootstrap.mdCurrent worktree, capabilities, gate install, scope and refactor type
1: planreferences/planning.mdCallers, duplication, CQ baseline, behavior/symbol scope and contract
2: characterizereferences/characterization.mdEvery moved unit exercised on pre-change code; use ../../shared/includes/regression-fence.md
3: transformreferences/transformation.mdPlanned move, targeted verification, independent CQ audit under policy
3: reviewreferences/review.mdActual adversarial review of formatted final inputs; finding dispositions
3.5–3.6: fix/auditreferences/remediation.mdAuthorized fixes with linked red/green runs; test-quality substage with parent evidence; mutation substage over the tests this run produced
4: completionreferences/completion.mdShared verifier, content-keyed proof, required telemetry and concise result

Definition of Done

For preserve-behavior CQ and finding disposition, read references/change-assessment.md.

Characterization, CQ audit, adversarial review and remediation remain mandatory. Keep provider requirements unchanged; size alone does not waive a safety gate. An audit that ran inline is labeled with its actual independence. Under preserve_behavior, fix introduced regressions and report unrelated existing risks with their original severity. Authorized existing bugfixes require demonstrated red/green tests; green characterization rechecks are different proof.

Create new v7 contracts using ../../shared/includes/refactor-reference.md; preserve v3–v6 records on resume. Format before the final snapshot and review. Reuse completed test, mutation and review evidence only for verified matching inputs and scope; never treat pending runs as PASS. Stage explicit touched paths, not git add -u. Commits follow session policy and do not replace quality completion. Full repository checks required before push remain required.

Completion Gate Check

~/.zuvo/refactor-contract --contract <this-run-contract.json> check

Use the real exit status. This calls the hook predicates; do not recreate their shell/JSON logic. The completion phase records the CQ matrix, finding ledger and receipts in artifacts and invokes ../../shared/includes/run-logger.md with ../../shared/includes/retrospective.md once per run.

REFACTOR COMPLETE

Human result: outcome, actual checks, unresolved risks, readiness to publish, commit and file links. The full formal receipt belongs in the report. no-commit reports the exact worktree and diff. Never claim COMPLETE over a pending check or critical unresolved requirement.

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