CtrlK
BlogDocsLog inGet started
Tessl Logo

tcm-constitution-analyzer

分析中医体质数据、识别体质类型、评估体质特征,并提供个性化养生建议。支持与营养、运动、睡眠等健康数据的关联分析。

51

Quality

58%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/tcm-constitution-analyzer/SKILL.md

The canonical home for this skill is tcm-constitution-analyzer in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

50%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 skill is actionable with concrete algorithms and data paths, and reasonably well-structured, but it is noticeably verbose due to a large inline example report and exhaustive reference lists, and its workflow steps lack integrated validation checkpoints. Moving template material into reference files and tightening the example would improve the lowest dimensions.

Suggestions

Move the full ~260-line example report and the exhaustive food/acupoint/formula lists into a reference file (e.g. references/report-template.md) and keep only a compact example inline.

Add explicit validation checkpoints into the execution steps — e.g. 'verify data files exist before analyzing', 'run 危险信号检测 before emitting advice' — and integrate the medical safety boundary into the step flow.

Define or reference CONSTITUTION_QUESTIONS (and the 60-item questionnaire) so the scoring algorithm is copy-paste executable rather than depending on an undefined constant.

DimensionReasoningScore

Conciseness

The body is noticeably verbose — a ~260-line inline example report plus exhaustive food/acupoint/herbal-formula/seasonal lists that pad the file beyond what Claude needs to execute the task.

2 / 5

Actionability

Provides mostly executable guidance: concrete Python scoring/determination algorithms and explicit data-file paths; minor gap is the undefined CONSTITUTION_QUESTIONS constant and missing questionnaire content.

4 / 5

Workflow Clarity

A clear 4-step sequence (确定范围→读取数据→数据分析→生成报告) is present, but validation checkpoints are not woven into the step flow; the medical safety boundary exists as a separate guardrail rather than an inline checkpoint.

3 / 5

Progressive Disclosure

Sections are well-organized and domain knowledge is externalized to data files (constitutions.json, constitution-recommendations.json), but no bundle reference files exist and large template/reference material (the full example report, formula details) is inlined rather than split out.

3 / 5

Total

12

/

20

Passed

Description

66%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 conveys a clear, multi-action 'what' for a distinct TCM niche with good natural keyword coverage, but omits any explicit 'when to use' trigger guidance, capping completeness at 3. Adding a 'Use when...' clause with concrete trigger phrases would lift the two dimensions currently sitting at 3-4.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks for 中医体质辨识、体质类型查询、体质特征分析, or personalized 中医养生建议'.

Add common synonyms/variants to the trigger terms (体质辨识, 九种体质, 体质测试) to broaden natural-language coverage.

Keep the current concrete action list but avoid stacking generic verbs (分析/评估/识别) — tighten to the most specific actions only.

DimensionReasoningScore

Specificity

Lists several concrete domain actions — '分析中医体质数据', '识别体质类型', '评估体质特征', '提供个性化养生建议', '关联分析' — rather than vague language, though the verbs (分析/评估/识别) are somewhat generic.

4 / 5

Completeness

Clearly answers 'what' but provides no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Good coverage of natural user phrases (中医体质, 体质类型, 养生建议, 营养, 运动, 睡眠) that a user requesting this skill would actually say; a few synonyms/variants (e.g. '体质辨识', '九种体质') are absent.

4 / 5

Distinctiveness Conflict Risk

The TCM constitution-analysis niche is mostly distinct with clear domain triggers; minor overlap risk with general health/wellness skills, and the lack of explicit triggers slightly raises ambiguity.

4 / 5

Total

15

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (667 lines); consider splitting into references/ and linking

Warning

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.