writing-plans

将 spec/需求拆分为可执行的分步实施计划。 Use when: 有 spec 或需求，准备动手前需要拆分步骤。 Not for: trivial 改动（≤5 行）、已有详细计划。 Output: 分步实施计划（含 TDD 步骤和检查点）。

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./cat-cafe-skills/writing-plans/SKILL.md

Quality

Content

81%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.

The body is highly actionable with concrete templates, exact commands, and a well-sequenced workflow with validation checkpoints. The main weakness is conciseness: anecdotal review-saga prose and a stale date add tokens that do not earn their place.

Suggestions

Move the F229 '20 轮' / PR #2202 narrative and the 2026-06-11 date out of the main flow (or into an 'old patterns' / reference file); keep only the actionable rule (census first, three-piece set per lifecycle object).

Extract the Stateful Object Gate three-piece-set detail into a references/ file and leave a concise overview + link in SKILL.md to improve progressive disclosure.

Tighten the Straight-Line Check and Census sections to imperative rules, dropping the retrospective '教训' framing that assumes context Claude does not share.

Dimension	Reasoning	Score
Conciseness	Mostly directive and dense, but the Stateful Object Gate section carries verbose war-story prose (F229 '20 轮' saga, PR #2202) and a time-specific date (2026-06-11) that is not placed in a deprecated/old-patterns section, so it could be tightened rather than trimmed of padding.	3 / 5
Actionability	Provides copy-paste-ready templates (Plan Document Header, full Task Structure with code blocks) and exact executable commands (pytest, git commit, pnpm check:fix / biome format --write) covering the common cases, matching the fully-executable anchor.	5 / 5
Workflow Clarity	Clear end-to-end sequence (recall → straight-line check → stateful gate → bite-sized tasks → header → formatting → next) with explicit validation checkpoints (TDD red/green, 'Only proceed when validation passes') and feedback loops.	5 / 5
Progressive Disclosure	Single well-sectioned file with clearly signaled one-level reference to decision-matrix.md and good header navigation; the 145-line body inlines substantial specialized material (e.g. the dense Stateful Object Gate three-piece set) that could live in a separate reference, keeping it just short of the ideal split.	4 / 5
	Total	17 / 20 Passed

Description

78%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.

The description is well-structured with explicit what/when/not-for/output clauses and natural bilingual triggers. It is slightly thin on enumerating multiple concrete actions, which keeps specificity at the midpoint.

Dimension	Reasoning	Score
Specificity	Names the domain (spec/requirements) and one main action — '拆分为可执行的分步实施计划' with 'TDD 步骤和检查点' — but does not list several distinct concrete actions, so it sits at the '1-2 concrete actions' anchor rather than the 'several specific actions' anchor above.	3 / 5
Completeness	Explicitly answers both what ('拆分为可执行的分步实施计划') and when ('Use when: 有 spec 或需求，准备动手前需要拆分步骤'), plus 'Not for' and 'Output' clauses, matching the anchor for clearly and explicitly answering both what and when.	5 / 5
Trigger Term Quality	Natural trigger phrases appear in both languages — 'implementation plan', '拆分步骤', '写计划', 'spec/需求' — giving good coverage; a few synonyms (e.g. 'break down', 'task list') are missing, so it is above the midpoint but not comprehensive.	4 / 5
Distinctiveness Conflict Risk	The plan-authoring niche is distinct from adjacent worktree/tdd skills and the 'Not for: trivial 改动、已有详细计划' boundary narrows overlap; minor overlap remains with general task-planning phrasing, so it is mostly distinct rather than a fully isolated niche.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: zts212653/clowder-ai
Path: cat-cafe-skills/writing-plans/SKILL.md
Commit: 090626a

Reviewed: ~23 hours 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.