CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

weightloss-analyzer

分析减肥数据、计算代谢率、追踪能量缺口、管理减肥阶段

Quality

68%

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 ./skills/weightloss-analyzer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 content is highly actionable — exact formulas, thresholds, file paths, and runnable commands — and avoids re-teaching concepts Claude already knows. Its weaknesses are structural: no explicit workflow with validation checkpoints, duplicated safety bounds, ~150 lines of sample-data report templates inlined in the main file, and no use of separate reference files.

Suggestions

Move the four full output-report templates into a references/report-templates.md file and keep only one condensed example inline, cutting SKILL.md roughly in half.

Add an explicit ordered workflow section (e.g., 1. read data/fitness-tracker.json and health logs → 2. compute BMR/TDEE → 3. validate deficit against the calorie floor → 4. generate report) with a validation checkpoint before any recommendation.

De-duplicate the calorie safety bounds, which appear both in section 3 (热量安全边界) and again in 安全原则, stating them once in the safety section.

DimensionReasoningScore

Conciseness

The body is dense with skill-specific domain data (formulas, WHO thresholds, activity coefficients) that Claude does not know, avoiding concept re-explanation. However, four full example reports (~150 lines) with fabricated sample data inflate the body, and the calorie safety bounds are stated twice (section 3 and 安全原则). Matches 'mostly efficient but includes some unnecessary content or could be tightened' rather than level 4's 'minor instances'.

3 / 5

Actionability

Everything is executable: three BMR formulas with exact coefficients, numeric classification thresholds for BMI/body-fat/waist, exact data file paths (data/fitness-tracker.json, data/health-logs/YYYY-MM/YYYY-MM-DD.json), and runnable commands with flags (--weight 75 --height 175 --age 52 --gender male). Matches 'fully executable; copy-paste ready; covers common cases'.

5 / 5

Workflow Clarity

The example commands imply a sequence (setup → bmr → track → report → plateau-check), but there is no explicit step-by-step workflow section and no validation checkpoints (e.g., verifying data files exist or sanity-checking computed deficits against the safety floor). Matches 'sequence present but checkpoints missing or implicit'; not level 4 because no checkpoints are stated at all.

3 / 5

Progressive Disclosure

The single 320-line SKILL.md is well-organized into clear sections, but there is no references/ bundle and the four full output-report templates (~150 lines) clearly belong in separate reference files. The under-50-lines exception for a 5 does not apply; matches 'some structure but content that should be separate is inline' rather than level 2 because the section structure is good, not minimal.

3 / 5

Total

14

/

20

Passed

Description

58%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 is a compact third-person capability list with mostly concrete actions in a distinct domain, but it lacks any 'use when' trigger guidance and misses natural synonyms users would say when needing weight-loss help. Adding an explicit trigger clause and common synonyms would lift it substantially.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user wants to lose weight, track a calorie deficit, calculate BMR/TDEE, or manage dieting phases (减肥/减脂/瘦身).'

Include natural synonym keywords such as 减脂, 瘦身, 基础代谢, 卡路里, and 体重管理 so the description matches how users actually phrase requests.

Replace the generic '分析减肥数据' with a more concrete action such as '分析身体成分(BMI、体脂率、围度)' to remove the last vague verb phrase.

DimensionReasoningScore

Specificity

The description lists four actions — '计算代谢率' (calculate metabolic rate), '追踪能量缺口' (track energy deficit), '管理减肥阶段' (manage phases) are concrete, while '分析减肥数据' (analyze weight-loss data) is generic. This matches 'lists several specific actions; minor gaps in coverage' — above level 3 because more than 1-2 actions are concrete, below level 5 because the first item is vague.

4 / 5

Completeness

The 'what' is clear (four named capabilities), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Matches anchor 3 ('clear what but when is missing or only weakly implied').

3 / 5

Trigger Term Quality

Natural keywords like 减肥, 代谢率, 能量缺口 are present, but common user-side synonyms and variations are missing (减脂, 瘦身, 基础代谢/BMR, 体重管理, 热量/卡路里). Matches 'some relevant keywords but missing common variations or synonyms' rather than level 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

The metabolism/energy-deficit/phase-management niche is mostly distinct with clear domain triggers, but it could overlap with broader fitness or diet-tracking skills. Matches 'mostly distinct; minor overlap risk' rather than level 5's fully clear niche.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/weightloss-analyzer/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.