CtrlK
BlogDocsLog inGet started
Tessl Logo

health-trend-analyzer

分析一段时间内健康数据的趋势和模式。关联药物、症状、生命体征、化验结果和其他健康指标的变化。识别令人担忧的趋势、改善情况,并提供数据驱动的洞察。当用户询问健康趋势、模式、随时间的变化或"我的健康状况有什么变化?"时使用。支持多维度分析(体重/BMI、症状、药物依从性、化验结果、情绪睡眠),相关性分析,变化检测,以及交互式HTML可视化报告(ECharts图表)。

55

Quality

63%

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/skills/health-trend-analyzer/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

42%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 well-structured with concrete data-source paths and a clear output format, but it is padded with non-executable pseudocode stubs and explanations of standard statistics, and it references detail files that do not exist in the bundle. Tightening the stubs and providing the referenced files would substantially improve it.

Suggestions

Replace the pseudocode stubs (pearsonCorrelation, detectChangePoints, assessRisks, etc.) with executable code, or remove them and keep only the concrete data-source reading and output-format guidance.

Either create the referenced files (data-sources.md, algorithms.md, examples.md) in a references/ directory or remove the dangling '请参考' pointers and inline the essential content directly.

Add explicit validation checkpoints inside the 8-step workflow (e.g. verify data was loaded and spans enough days before running trend analysis) rather than relying only on the separate error-handling section.

DimensionReasoningScore

Conciseness

Noticeably verbose: pseudocode stubs whose bodies are only comments ('pearsonCorrelation', 'detectChangePoints', 'assessRisks'), a '分析算法' section explaining standard statistics Claude already knows (CUSUM, Pearson/Spearman), and a ~70-line text-report mockup all pad the document; padding spans multiple sections rather than isolated over-explanation, keeping it at 2 rather than 3.

2 / 5

Actionability

Data-source paths and the output format are concrete, but the core analysis code is non-executable pseudocode/stubs using fake helpers ('readFile', 'readAllJson') that are not among the declared allowed tools (Read, Grep, Glob, Write); the stubs keep it below 4, while the real data-source and output guidance keeps it above 2.

3 / 5

Workflow Clarity

A clear 8-step sequence is present, but the batch read of many data files has no inline validation checkpoints; the separate error-handling section provides fallbacks but no explicit verify-then-proceed gates, so per the batch-operation cap it stays at 3.

3 / 5

Progressive Disclosure

Section structure is good and references are signaled ('详细算法说明请参考:algorithms.md'), but no bundle files exist — the referenced data-sources.md, algorithms.md, and examples.md are dangling — and large content that belongs in separate files (algorithms, full output example) is inlined; structure keeps it above 2 but the missing files keep it below 4.

3 / 5

Total

11

/

20

Passed

Description

83%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 clearly and concretely states both capabilities and explicit trigger conditions in third person, with good natural-language trigger phrases. It is held back only by a few abstract category labels and a modest synonym set.

DimensionReasoningScore

Specificity

Lists several concrete actions ('关联药物、症状、生命体征、化验结果', '识别令人担忧的趋势、改善情况', '交互式HTML可视化报告(ECharts图表)'), but a few items like '相关性分析, 变化检测' are category labels rather than fully concrete actions, keeping it below a 5.

4 / 5

Completeness

Explicitly answers both what ('分析...关联...识别...提供洞察') and when ('当用户询问健康趋势、模式、随时间的变化或"我的健康状况有什么变化?"时使用') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural phrases a user would actually say ('我的健康状况有什么变化?', '健康趋势', '随时间的变化'), but the synonym set is narrower than the comprehensive-with-extensions anchor at 5.

4 / 5

Distinctiveness Conflict Risk

Has a clear niche (health trend/correlation analysis over time) with specific triggers, but carries minor overlap risk with general health-query or symptom-tracking skills, so not a 5.

4 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

14

/

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.