agentsclimarketplace

Amo refactor

Skill lencamo/skills/skills/amo-refactor

Practical agent skills for real engineering workflows.

Install
npx -y skills add lencamo/skills --skill amo-refactor

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when the user asks how to refactor, split modules, clarify architecture, move ownership, reduce coupling, or fix unclear state, data-flow, or component boundaries before coding. Do not use for ordinary feature work, bug fixes, or second-pass solution challenges.

SKILL.md

2.8 KB, as published. Nobody here has run it

Amo Refactor

Plan structural changes when boundaries, ownership, or coupling are the primary problem.

Shared Output Marker

Prefix the first output line inline with 🧱 [amo-refactor]. Do not put the marker in a separate paragraph.

Use When

  • The user asks whether code should be refactored or how to refactor it.
  • Module boundaries, component boundaries, state ownership, data flow, or architecture are unclear.
  • Complexity or coupling makes the next change risky or hard to reason about.

Do Not Use

  • The primary goal is new behavior; use amo-feature.
  • The primary goal is changing existing behavior; use amo-improve.
  • The primary goal is fixing broken behavior; use amo-fix.
  • A proposed refactor needs challenge; use amo-best.

Best Standard

Select and state one before recommending a refactor:

  • Target-state best: default for development-stage work when no explicit constraint is stated; prioritize correct boundaries, long-term maintainability, refactoring when needed, and not bending the design around legacy implementation.
  • Constraint best: use when the user requires fast delivery, compatibility, minimal change, short-term delivery, or limited scope.
  • Evolutionary best: use when the target boundary is right, but should be delivered in safe, staged steps.
  • Lowest-risk best: use when production, data, security, auth/permission, payment, migration, or rollback risk dominates.

Workflow

  1. Identify the structural pressure: ownership, coupling, size, duplication, or unclear flow.
  2. Select the best standard and explain why.
  3. Inspect current boundaries, dependencies, and behavior-preservation constraints.
  4. Define the target boundary and responsibilities.
  5. Recommend one scoped refactor with tradeoffs and verification.

Key Rules

  • Refactor only when structure is the problem, not because code merely looks imperfect.
  • Ownership boundary before patch.
  • Preserve behavior unless the user explicitly asks to change it.
  • Do not add speculative compatibility paths, fallback branches, or legacy handling without evidence from the codebase or explicit user requirements.
  • If implementation reveals a better approach, pause and explain before switching.

Output

Use the user's language for output labels and content.

🧱 [amo-refactor] Scenario: refactor / architecture boundary
Best standard:
Structural issue:
Target boundary:
Recommended approach:
Tradeoffs:
Impact scope:
Verification:
Next: use amo-best for second-pass pressure testing if needed

Gives 0 of the 12 instructions most refactoring skills give

Counted across 521 of the 525 authors here whose files we hold, read 2026-08-06

  • run tests after each changein 59 of 521, across 56 files
  • write tests before refactoringin 27 of 521, across 24 files
  • preserve external behaviorin 26 of 521, across 22 files
  • remove dead codein 25 of 521, across 24 files
  • make small incremental changesin 20 of 521, across 17 files
  • break the implementation into tiny commitsin 18 of 521, across 5 files
  • ask the user about alternative optionsin 17 of 521, across 4 files
  • create a GitHub issue with the planin 17 of 521, across 4 files
  • explore the repository to verify assertionsin 17 of 521, across 4 files
  • interview the user about the refactorin 16 of 521, across 3 files
  • check the codebase for test coveragein 16 of 521, across 3 files
  • refactor one thing at a timein 16 of 521, across 12 files

Said here and by no other author read

  • prefix first output line with marker
  • select and state one best standard
  • inspect current boundaries and dependencies
  • define target boundary and responsibilities
  • recommend one scoped refactor with tradeoffs
  • use the user's language for output labels

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.