neat-freak

Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and also on clear knowledge-closeout intent without the name: syncing or tidying project docs/rules/memory after development ("把文档和记忆整理一下", "收尾时把文档同步掉", "docs 和代码对不上了"), stale or conflicting CLAUDE.md/memory, a clean handoff to a teammate or a fresh session, or auditing whether workspace rules are actually followed. Do not trigger for pure coding/refactoring/debugging tasks, tidying data or prose (JSON, 周报, changelog announcements), or a bare "整理" with no project-knowledge context.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

76%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-architected governance skill: two clearly sequenced paths with validation and a destructive-cleanup confirmation loop, concrete tooling and a report template, and clean one-level references. The main weakness is conciseness — the policy prose is dense and somewhat repetitive on authorization and reporting, which could be trimmed without losing clarity.

Suggestions

Tighten the repeated authorization emphasis: the '权限和范围先于洁癖' section, the cleanup-confirmation paragraph, and several self-check items restate the same authorization/confirmation rule; consolidate into one authoritative statement and reference it.

Move the per-platform memory control-surface specifics (e.g. exact `/memories`, settings, config-item names per platform) into references/agent-paths.md or a dedicated reference, keeping the body to the decision rule.

Consider shortening the six-row completion-contract table's prose preamble and the lightweight-path step descriptions; the table and numbered steps already convey the contract.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no explanation of what CLAUDE.md or a worktree is), but the body is ~190 lines of dense policy prose with some repeated emphasis on authorization and reporting that could be tightened.	3 / 5
Actionability	Provides concrete executable guidance — a real script invocation (`bash scripts/audit-inventory.sh <project-root>`), a status-label vocabulary, a fill-in report template, and a final self-check checklist — with only minor gaps around per-platform memory control surfaces.	4 / 5
Workflow Clarity	Both the lightweight five-step and full 0–7 paths are explicitly sequenced with validation checkpoints, a destructive-cleanup two-phase confirmation loop (preview → report → user confirmation → delete → re-audit), and a final self-check; the destructive-operation feedback loop is present and central.	5 / 5
Progressive Disclosure	Clear one-level-deep references to four real files (agent-paths.md, governance.md, sync-matrix.md, verification.md) plus a real audit script, each well-signaled in-body and summarized in a final reference list; no nested/2+-level references and bulk detail is kept out of SKILL.md.	5 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that concretely names what is reconciled, gives rich bilingual trigger terms plus anti-triggers, and cleanly delineates its niche from ordinary coding or tidying tasks. It is dense but every clause carries discriminating information.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do.	5 / 5
Completeness	Explicitly answers both 'what' (reconcile docs/rules/memory/workspace with code and runtime so the next session starts from one current answer) and 'when' (trigger when the user names it or shows knowledge-closeout intent), with concrete trigger and anti-trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural triggers including the name 'neat-freak', '洁癖', '/neat', plus intent phrases in English and Chinese ('docs 和代码对不上了', '把文档和记忆整理一下') and clear anti-triggers.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear knowledge-governance closeout niche with distinct triggers and an explicit 'Do not trigger' boundary against pure coding/refactoring/data-tidying, minimizing wrong-skill conflicts.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: KKKKhazix/khazix-skills
Path: neat-freak/SKILL.md
Commit: 7a5c493

Reviewed: 21 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.