CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

chinese-documentation

中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 high-quality, example-driven style guide: every rule is taught with concrete good/bad pairs, the templates are directly usable, and a closing checklist provides validation. The weaknesses are length concentration in the two large inline templates that should be split into reference files, and a lean profile that could be tightened overall.

Suggestions

Move the full 'README.md 中文模板' and 'API 文档中英对照格式' templates (~135 lines) into references/ files (e.g., references/readme-template.md and references/api-doc-template.md), keeping only a short excerpt plus a pointer in SKILL.md to shorten the always-loaded body.

Consolidate the five '空格' subsections into a single table of rule → good/bad example pairs to reduce repetition while preserving every rule.

Trim the '概述' section's motivational framing ('读起来别扭', '专业、好读、不出戏') to one or two sentences of core principles.

DimensionReasoningScore

Conciseness

The body is dense and example-driven — every rule is taught via a 好/坏 (good/bad) pair with no explanations of concepts Claude already knows — but the two full inline templates (API documentation template ~60 lines, README template ~75 lines) add bulk that could be trimmed or split out. Fits anchor 4 ('efficient; minor instances of over-explanation that could be trimmed'), not 5, since a lean version would externalize those templates.

4 / 5

Actionability

Fully actionable throughout: before/after examples for every rule ('使用 Git 进行版本管理' vs '使用Git进行版本管理'), complete copy-paste-ready API documentation and README templates, explicit terminology lists ('保留英文的情况' / '翻译为中文的情况'), and a final verification checklist. Matches anchor 5 ('fully executable; copy-paste ready; specific examples cover the common cases').

5 / 5

Workflow Clarity

This is a single-purpose convention skill whose single action — apply these typography/terminology conventions — is unambiguous, and the closing '写作检查清单' (排版/术语/内容/格式 checklist) provides an explicit validation step before publishing. Under the simple-skill exception this matches anchor 5; the checklist functions as the validation checkpoint that would otherwise be missing.

5 / 5

Progressive Disclosure

No bundle files exist, so all ~450 lines live in SKILL.md. Internal structure is good (clear hierarchical sections), but the self-contained README template and API documentation template (~135 lines combined) are inline content that clearly belongs in separate references/ files — matching anchor 3's pattern ('content that should be separate is inline') rather than 4, since this is more than a minor organization gap.

3 / 5

Total

17

/

20

Passed

Description

87%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 description: it names a distinct niche, lists concrete coverage areas, and gives an explicit, third-person trigger condition (slash-command-only invocation) that virtually eliminates conflict risk. The main gap is that capabilities are expressed as topic nouns rather than concrete actions, and a few natural trigger terms are absent.

DimensionReasoningScore

Specificity

The description enumerates several concrete topic areas — '中英文空格、全半角标点、术语保留、链接格式' — covering the Chinese typography domain, but frames them as '参考...约定' (reference conventions) rather than concrete actions, and omits areas the body covers (numbers, 机翻-style fixes). This matches anchor 4 ('lists several specific actions; minor gaps') better than 5, since these are topic nouns rather than the comprehensive action verbs of a 5.

4 / 5

Completeness

Both 'what' (Chinese documentation typography conventions: spacing, punctuation, terminology, link formatting) and 'when' are explicitly answered — '仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发' gives a concrete, unambiguous trigger phrase in third-person voice. This matches anchor 5 ('clearly and explicitly answers both what AND when with concrete trigger phrases'); a 4 would have a weaker or less specific 'when' clause.

5 / 5

Trigger Term Quality

Natural keywords users would say are present — '中文文档', '排版', '中英文空格', '标点', '术语', '链接' — giving good coverage, but common variations like '中英混排', '写作规范', or '文案' are missing. Fits anchor 4 ('good keyword coverage; a few natural terms missing'), not 3 (coverage is clearly better than 'some relevant keywords') and not 5 (no synonyms/extensions like a full 5 would have).

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (Chinese technical-writing typography conventions) and the explicit instruction not to auto-trigger ('不要根据上下文自动触发') makes wrong-skill triggering essentially impossible. Matches anchor 5 ('clear niche with distinct triggers; minimal conflict risk').

5 / 5

Total

18

/

20

Passed

Validation

75%

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

CriteriaDescriptionResult

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

relative_links

Relative link issues: 7 missing

Warning

Total

12

/

16

Passed

Repository

jnMetaCode/superpowers-zh

Path

skills/chinese-documentation/SKILL.md

Reviewed

Table of Contents

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.