agentleFS
jisuzzzzjisuzzzz/haechi/skills/refactor/SKILL.md

refactor

Skill17 starsChanged 14 days agoMITView on GitHub

Change structure while preserving external behavior — characterize the contract, delete unnecessary code, transform mechanically and migrate consumers. Use for /haechi:refactor or an authorized behavior-preserving change within other work.

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

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 169 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Delete before adding structure: Remove dead code, unused exports and unnecessary checks when in scope.

    line 14
  2. Distinctive:

    Transform mechanically: Use a type-aware rename or codemod for symbol moves, rather than an indiscriminate text replacement.

    line 15

“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

Restructure without changing behavior

Apply the common work contract within the authorized scope. It owns required implementation, verification, review and completion obligations; this skill supplies methods. Use /haechi:delegate for a bounded worker task when independent execution helps. Existing step names below are compatible delegation entry points, not an exclusive workflow state.

Methods

  1. Name the structural problem and preserved contract. Define the intended end state in checkable terms, such as no remaining imports of a retired internal module. Use /haechi:spec when the boundaries need synthesis; settled requirements need no new approval.
  2. Characterize current behavior. Reuse tests covering observable results or add missing characterization before changing structure. Where affected, cover errors and timing, input mutation, side-effect order and partial writes. An old/new equivalence check on the same inputs can be useful. Use /haechi:mutation-check when a concrete concern suggests the characterization could miss a regression.
  3. Delete before adding structure. Remove dead code, unused exports and unnecessary checks when in scope. Keep independently verifiable cleanup and mechanical transformations in coherent units under the repo's commit rules.
  4. Transform mechanically. Use a type-aware rename or codemod for symbol moves, rather than an indiscriminate text replacement. Move files with the repository's appropriate tools. Do not combine an intentional behavior change with a claimed behavior-preserving transformation.
  5. Migrate consumers and retire obsolete paths. Remove old internal paths once their in-scope consumers are migrated. Do not invent a compatibility layer merely to avoid completing the migration; retain public compatibility explicitly required by the task. Resolve consumers outside the authorized scope before deleting their dependency.
  6. Investigate a broken check. If it asserts internals, replace it with a behavior assertion and explain why. If observable behavior changed unintentionally, restore it rather than changing the expected result. A necessary intentional behavior change follows the user's authorization and common obligations; choosing another method is not a new approval by itself.

Inspect remaining consumers, unused exports and stale documentation. The common contract governs preservation evidence and any affected rendered behavior, including use of /haechi:screen-parity when an independent comparison adds evidence.

Delegation contracts

These compatible entries identify delegated methods, not an exclusive workflow or a mandatory agent sequence. Packet assembly also supplies the canonical common work contract. The main session fills the named context fields and task-specific acceptance criteria; detailed procedures and principle bodies stay in their referenced files. read-only means repository files remain unchanged; authorized temporary or report outputs must be named separately in artifactPaths.

{
  "implement": {
    "skills": [
      "implement-work"
    ],
    "principles": [
      "dry",
      "yagni",
      "kiss",
      "boundary-validation",
      "root-cause",
      "failing-test-first",
      "behavior-tests"
    ],
    "checks": [],
    "writeScope": "scoped",
    "contextRequired": [
      "repository",
      "requirements",
      "pinningEvidence",
      "ownership"
    ],
    "completion": [
      "Report the assigned implement work, its observed results and any remaining scope limitations."
    ]
  },
  "attack": {
    "skills": [
      "attack-tests",
      "sibling-path-map",
      "mutation-check"
    ],
    "principles": [
      "sibling-paths",
      "behavior-tests"
    ],
    "checks": [],
    "writeScope": "scoped",
    "contextRequired": [
      "repository",
      "requirements",
      "changedFiles",
      "ownership"
    ],
    "completion": [
      "Demonstrate that tests detect the targeted defects without weakening expected behavior."
    ]
  },
  "review": {
    "skills": [
      "verify-work",
      "review-diff",
      "impact-map"
    ],
    "principles": [
      "evidence-levels",
      "behavior-tests"
    ],
    "checks": [
      "agent-defects",
      "sibling-paths",
      "dry",
      "yagni",
      "kiss"
    ],
    "writeScope": "read-only",
    "contextRequired": [
      "repository",
      "requirements",
      "base",
      "changedFiles",
      "priorEvidence"
    ],
    "completion": [
      "Report concrete defects with expected and observed behavior and affected consumers.",
      "Distinguish passing checks, failures, missing proof and unresolved expectations."
    ]
  },
  "parity": {
    "skills": [
      "screen-parity"
    ],
    "principles": [
      "real-artifact"
    ],
    "checks": [],
    "writeScope": "read-only",
    "contextRequired": [
      "repository",
      "beforeUrl",
      "afterUrl",
      "states",
      "intendedDifferences",
      "artifactLocation",
      "loginContext"
    ],
    "completion": [
      "Return PASS or FAIL against real rendered comparisons and the noise baseline, or BLOCKED."
    ]
  }
}

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.