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

76%

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

77%Weight 40%Scale 1-3

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

The skill body is highly actionable with excellent templates and a well-sequenced, validated TDD workflow. Conciseness suffers from internal project war-story padding, and progressive disclosure is weak because no reference bundle backs the inline-heavy sections.

Suggestions

Trim the Stateful Object Gate war-story narrative (F229/PR #2202/"20 轮" references and dated lessons) down to the actionable census + three-piece-set rules.

Create a bundled references/decision-matrix.md (and optionally a stateful-gate reference) and link to them one level deep, moving the long inline checklists out of SKILL.md.

Remove the leftover "（internal reference removed）" placeholder or replace it with a real pointer.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence, but the Stateful Object Gate section carries internal war-story padding ("F229 PR-A1 20 轮教训", "PR #2202 实测", dated lessons) and a leftover "（internal reference removed）" placeholder that do not earn their tokens.	2 / 3
Actionability	Provides fully executable, copy-paste-ready templates: an exact plan document header, a complete Task Structure block with real pytest commands and a git commit example, and the three-question Straight-Line Check.	3 / 3
Workflow Clarity	A clearly sequenced multi-step process (recall → straight-line check → stateful gate → task structure → open questions → commit → next step) with explicit TDD validation checkpoints ("verify it fails", "verify it passes") and expected FAIL/PASS output.	3 / 3
Progressive Disclosure	No bundled reference files exist despite the body citing refs/decision-matrix.md, and dense inline sections (Stateful Object Gate, Open Questions) that read like reference material are kept in SKILL.md rather than split into one-level-deep bundled files.	2 / 3
	Total	10 / 12 Passed

Description

75%Weight 40%Scale 1-3

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 clear and complete, explicitly stating both what the skill does and when to use it with helpful exclusions. Specificity and trigger-term coverage are adequate but could name more concrete sub-actions and natural-language variations.

Suggestions

Add 1-2 more concrete actions to the description (e.g., "定义终态 schema、识别状态对象 gate、生成 TDD 步骤清单") to lift specificity to the top anchor.

Expand trigger terms with common phrasings like "拆需求", "写实施步骤", "plan implementation", "break down feature".

Dimension	Reasoning	Score
Specificity	Names the domain (spec/requirements) and a concrete action ("将 spec/需求拆分为可执行的分步实施计划", "含 TDD 步骤和检查点"), but describes one main action rather than the multiple distinct concrete actions the top anchor requires.	2 / 3
Completeness	Explicitly answers both what ("将 spec/需求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") with a "Not for" clause, matching the top anchor.	3 / 3
Trigger Term Quality	Includes some natural terms users would say ("implementation plan", "写计划", "拆分步骤") but coverage is thin and "spec" is jargon, missing common variations the top anchor expects.	2 / 3
Distinctiveness Conflict Risk	Has a clear niche (pre-coding plan splitting) with distinct triggers and an explicit "Not for" clause disambiguating it from the tdd/worktree skills it chains to.	3 / 3
	Total	10 / 12 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: 80782c5

Reviewed: 11 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.