writing-skills

当创建新技能、编辑现有技能或在部署前验证技能是否有效时使用

Quality

45%

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 ./skills/writing-skills/SKILL.md

Quality

Content

57%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 and the TDD workflow is exceptionally clear with validation checkpoints and feedback loops, but it is verbose and inlines large reference-style content that, per its own advice, would benefit from being split into separate files.

Suggestions

Trim redundant good/bad YAML example pairs and consolidate the three rationalization sections (table, red-line list, rationalization list) into one to reduce token cost.

Move the large keyword/SDO reference tables and extended example banks into separate reference files and link them one level deep, practicing the progressive disclosure the skill teaches.

Tighten abstract directives like 'write a minimal skill' into concrete, executable steps that match the precision of the checklist items.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: the TDD mapping table, multiple repeated good/bad YAML example pairs, and several overlapping sections on rationalization reuse the same point many times when a tighter single presentation would carry the same instruction.	2 / 5
Actionability	Mostly executable guidance: concrete directory layouts, YAML frontmatter templates, bash word-count checks, render-graphs commands, and checklist items are copy-paste ready, with only minor gaps where instruction is abstract (e.g., 'write a minimal skill').	4 / 5
Workflow Clarity	The red-green-refactor process is clearly sequenced with explicit validation checkpoints (run baseline, observe failure, write minimal skill, re-test, refactor holes) plus feedback loops and a mandatory TDD-adapted deployment checklist with TodoWrite tracking.	5 / 5
Progressive Disclosure	Structure is present with clear section headers, but no bundle files exist so large reference material (the rationalization tables, SDO deep-dive, multiple example banks) is inlined monolithically rather than split into separate reference files as the skill's own guidance recommends.	3 / 5
	Total	14 / 20 Passed

Description

33%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 provides clear when-to-use guidance but omits any what-the-skill-does statement, and its trigger terms are abstract domain words rather than natural phrasings. Distinctiveness is its strongest dimension because the domain is narrow.

Suggestions

Add a brief 'what' clause stating what the skill does, e.g. 'Guide the test-driven authoring and validation of skill documents'.

Make trigger terms more natural and keyword-rich by including symptoms users would actually say, such as 'skill not triggering', 'skill description not loading', or 'validate a SKILL.md'.

Include concrete artifacts in the trigger (e.g., 'when writing or editing SKILL.md files') to improve keyword coverage and conflict resistance.

Dimension	Reasoning	Score
Specificity	The description names the domain (skill authoring) but only offers two minimal action fragments (create, edit, validate) that mirror each other; the phrase provides no concrete actions distinguishing these three cases.	2 / 5
Completeness	Only the 'when' is present via the explicit trigger clause; the description never states what the skill does, so it does not answer both halves of the completeness test.	2 / 5
Trigger Term Quality	It uses the trigger guidance 'Use when creating new skills, editing existing skills, or validating skills before deployment', but the keywords are abstract domain words; it lacks natural phrasings or synonyms a user would actually say in the moment.	2 / 5
Distinctiveness Conflict Risk	The three trigger conditions (creating, editing, validating skills) are a narrow niche with minimal overlap risk against unrelated skills, though it does overlap with sibling skill-authoring skills.	4 / 5
	Total	10 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (680 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	12 / 16 Passed

Repository: jnMetaCode/superpowers-zh
Path: skills/writing-skills/SKILL.md
Commit: c68725b

Reviewed: 4 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.