miaodx/intuitive-flow/intuitive-reduce-entropy
Claude Code and agent skill by miaodx/intuitive-flow
- community
Checking that the SKILL.md file is still in the repository.
Find and rank material simplification candidates when the cleanup target or plan risks are unclear.
Install
npx vskill@latest install miaodx/intuitive-flow/intuitive-reduce-entropySKILL.md
Intuitive Reduce Entropy
Use this skill to find a bounded set of changes that remove real maintainer or execution friction. Prefer deletion, reuse, and one canonical owner over new workflow, code, test, or documentation surfaces.
Modes
| Mode | Use when | Output | Redirect when | |
|---|---|---|---|---|
| Repo entropy | The repo feels messy, stale, hard to navigate, or has no known cleanup owner. | Ranked maintenance candidates and specialist owners. | A concrete seam is already selected; use its specialist or $intuitive-refactor. | |
| Plan entropy | An idea, draft plan, or preflight needs missing decisions, weak assumptions, scope leaks, or proof gaps found. | Ranked plan risks and the next planning owner. | The contract is already approved; use $intuitive-flow. | |
| Discovery loop | The user asks to continue until meaningful cleanup saturates. | Fresh bounded rounds with deduplicated clear, parked, and rejected items. | A selected queue is ready for $intuitive-refactor. |
Pick the mode and discovery intensity (quick scan, selection scan, or saturation scan) and name them in the packet, with a redirect only when another mode or skill fits better.
Read First
Load only the reference needed for the active pass:
| Need | Read | |
|---|---|---|
| Mode selection, discovery-loop behavior, plan-ledger boundaries | Discovery modes | |
| High-noise summaries, materiality gate, no-change threshold | High noise and materiality | |
| Ranking, architecture review, delegation, specialist routing | Ranking and routing | |
| Candidate packet, user decision gates, handoff and final shapes | Handoff and reporting |
For broad repo scans, read the repo's thin orientation surface and run the bundled high-noise summary before searching planning archives, logs, generated trees, or other high-noise roots. Deep-read only enough to prove a candidate.
Candidate Gate
Every selected candidate must pass both gates:
- Demand sanity: the change deserves to exist now. For additions, explain why
reuse, narrowing, deletion, or documentation cannot achieve the outcome. For removals, show why preserving the surface is stale, misleading, or costly.
- Materiality: evidence shows false confidence, live source drift, a stale
reachable surface, real workflow friction, or recurring rediscovery.
Use scripts/materiality-gate.mjs when a deterministic gate helps compare a batch. Scripts provide evidence; they do not override repo facts or a required human decision.
Rank deletion and cleanup candidates in this order:
- Stale surfaces with an active replacement.
- Compatibility aliases, wrappers, or legacy paths without a live contract.
- Duplicate owners for one concept, state envelope, fixture, or rule.
- Pass-through modules and tests/docs that keep stale concepts alive.
- Bounded source-of-truth or verification drift.
Formatting, line motion, speculative abstraction, and taste are not selected candidates. Park work that needs product direction, public migration approval, credentials, hardware, paid services, or unavailable proof.
Ownership Boundary
- This skill owns discovery, ranking, evidence, and routing.
$intuitive-refactorowns mutation of selected cleanup seams.$intuitive-doc,$intuitive-init, and$intuitive-testsown their
specialist surfaces.
$grill-with-docs-batchowns unresolved human/domain decisions.$intuitive-preflightowns the approved execution contract.$intuitive-flowstarts only after that contract is approved.
Use the shared delegation policy for independent read-only probes. Keep the main session responsible for ranking, architecture decisions, and final synthesis.
Stop And Handoff
Stop when a decision-complete ranked packet is ready, or when a saturation pass finds no new material candidate. The user selects the subset and approves implementation. If nothing passes, say Selected candidates: none and stop there, with no gate, commit, or follow-up proposal.
End with a packet the next owner can act on without repeating the audit. Always include selected candidates (with evidence, specialist owner, and proof command), Recommended next action:, and Shortcut: (a ready-to-paste command, or park/none when there is no useful next step). Add parked items or saturation status only when they carry information.
Security
- Security scanPassed, 94 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/intuitive-reduce-entropy/SKILL.md
Popularity
- Repository stars
- 48
- Repository forks
- 3
- 7-day trend score
- 19
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/miaodx/intuitive-flow/intuitive-reduce-entropy)