AgentStack
SKILL verified MIT Self-run

Intuitive Refactor

skill-miaodx-intuitive-flow-intuitive-refactor · by MiaoDX

|

No reviews yet
0 installs
12 views
0.0% view→install

Install

$ agentstack add skill-miaodx-intuitive-flow-intuitive-refactor

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Intuitive Refactor? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Intuitive Refactor

Use $intuitive-refactor to make selected cleanup canonical: delete stale surfaces, merge duplicate concepts, move behavior to the right owner, update callers/tests/docs, and prove the behavior still holds.

This is a compact runtime router for mutation work. $intuitive-reduce-entropy owns unknown-target discovery and cleanup candidate ranking; return here only after the user names a target or selects a candidate packet.

Route

| Need | Read | | --- | --- | | Route selection, scope gate, severity guide, evidence ladder | references/mode-router.md | | Repeated cleanup, oversized modules, stale surfaces, deletion/owner-move ratchets | references/ratchet-mode.md | | Long-running ratchet overlay, active capsule, selected-slice loop, or repo-wide maintenance goal | references/ratchet-campaign.md and ../_shared/references/durable-run.md | | Diff-scoped reuse/quality/efficiency review after implementation | references/changed-code-review.md | | Full legacy guidance, templates, confidence ladder, command naming, persistent-state examples | references/detailed-guidance.md |

If multiple routes match, load the narrowest reference first and add the next one only when the work crosses that boundary.

Operating Rule

Start from a target and a stop condition, not from "make it cleaner."

  • Known seam/module/API/stale surface: gate or execute a bounded refactor slice.
  • Unknown repo-wide cleanup or deletion/merge discovery: route to

$intuitive-reduce-entropy first. Use its selected-candidate packet as this skill's discovery source.

  • Repeated cleanup or "keep going": run ratchet route, add the campaign overlay

only for long-lived/resumed work, execute only selected clear P1/P2 slices, and park uncertain decisions.

  • Periodic whole-repo architecture maintenance: add the campaign overlay's

repo-wide maintenance goal loop, alternate fresh reduce-entropy handoffs with execution of every clear queue item, and stop only after saturation deduplicates parked and low-value registries.

  • Changed-code cleanup: stay diff-scoped; report findings first and fix only

when authorized by the user or approved flow.

Prefer the organized future at HEAD over compatibility shims. Preserve compatibility only when an external contract, artifact reader, or explicit migration requirement makes it necessary.

For every slice, prefer concept reduction over code motion:

  1. Delete stale or unreachable surfaces.
  2. Merge duplicate concepts, wrappers, registries, fixtures, or owners.
  3. Move behavior to an existing canonical owner and update callers.
  4. Create a new owner only when the architecture lacks a true home.
  5. Extract helpers only around a named ownership boundary.

Reject slices that only make a file smaller, add vague modules, preserve stale aliases indefinitely, or lack focused proof.

Slice Loop

For non-trivial work, state:

Selected route:
Why:
Redirect:

Then run one vertical slice at a time:

  1. Orient from the smallest context that can prove the target and owner.
  2. Classify findings as P0, P1, P2, or Parked.
  3. State the architecture claim and expected value metrics.
  4. Update code, callers, tests, docs, and stale surfaces together.
  5. Verify with the smallest sufficient evidence ladder.
  6. Checkpoint what changed, what stayed parked, and what proof passed. With the

campaign overlay, commit verified implementation slices by default; the detailed skip rules live in references/ratchet-campaign.md.

Stop when the accepted checklist is complete and remaining candidates are parked, polish, public-contract migrations, or design decisions. With the campaign overlay, stop only after the selected-slice or repo-wide maintenance saturation rule in references/ratchet-campaign.md is met.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.