CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

food-database-query

Food Database Query

Quality

46%

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/food-database-query/SKILL.md

The canonical home for this skill is food-database-query 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 rich in genuine domain data (schemas, thresholds, RDA values, worked examples) but is buried in an 800-line monolith padded with roadmaps, disclaimers, and pseudocode of trivial algorithms, with all executable detail left unimplemented and referenced data files missing from the bundle. The core content would be strong if split into reference files and stripped to actionable instructions with an error-handling path.

Suggestions

Move the RDA tables, full food JSON schema, and category tree into reference files (e.g. references/rda.md, references/data-schema.md) and actually include the cited data files (data/food-database.json, data/food-categories.json) in the bundle so references resolve.

Delete non-instructional padding: 扩展计划 (roadmap), 质量保证, and the generic 注意事项 disclaimers add tokens without guiding execution.

Replace pseudocode with one executable script (or concrete, copy-paste query instructions) and add an explicit error-handling flow for unmatched foods (fuzzy-match failure → ask user / suggest closest matches).

DimensionReasoningScore

Conciseness

The ~780-line body carries substantial padding Claude does not need — an 扩展计划 product roadmap, 质量保证 assurances, generic disclaimers, full mock output transcripts — and explains concepts Claude already knows (Levenshtein fuzzy matching, proportional scaling written as "(value_per_100g * portion_grams) / 100"). It stays above anchor 1 because the data schema, nutrient thresholds, and RDA values are genuine domain knowledge.

2 / 5

Actionability

Concrete artifacts exist (complete food JSON schema, threshold definitions like 高蛋白 ≥15g/100g, example commands such as "/nutrition food 三文鱼"), but all logic is pseudocode with unbound names (database, extract_food_name, normalize_food_name) and the cited data files (data/food-database.json, data/food-categories.json) are absent from the bundle, so nothing is end-to-end executable — matching the anchor-3 pseudocode profile rather than anchor 4's executable guidance.

3 / 5

Workflow Clarity

Sequences are listed (查询流程 steps 1–4; 记录早餐 steps 1–5) but validation checkpoints and error-recovery flows are missing — e.g. no guidance on what to do when find_food returns None or when a portion cannot be parsed. Anchor 3 ("steps listed but validation gaps; checkpoints missing or implicit") fits; anchor 4 is unwarranted since checkpoints are absent entirely, not merely minor.

3 / 5

Progressive Disclosure

The body is well-sectioned but is a ~780-line monolith inlining content that clearly belongs in reference files (full RDA tables, the complete food data structure, the category tree), and its references (data/food-database.json, data/food-categories.json, .claude/commands/nutrition.md) point to files that do not exist in the bundle. Structure is good, keeping it above anchor 2's "minimal structure", but heavy inlining plus dangling references hold it to anchor 3.

3 / 5

Total

11

/

20

Passed

Description

28%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 bare three-word title that names the domain but communicates nothing about what the skill does, when to use it, or which natural phrases should trigger it. It would rarely fire correctly and would collide with other nutrition-related skills. A single sentence stating concrete capabilities plus a "Use when..." clause would transform it.

Suggestions

State concrete capabilities in third person, e.g. "Looks up per-100g nutrition profiles for 50 common foods, compares foods side by side, and recommends foods by nutrient thresholds or health condition (DASH, diabetes)."

Add an explicit trigger clause: "Use when the user asks about nutrition, calories, protein, or GI of a food, wants food comparison or condition-based food recommendations."

Include natural synonyms and both languages users would say — nutrition, calories, 营养, 卡路里, 升糖指数 — so the skill fires on real user phrasing.

DimensionReasoningScore

Specificity

The description is just the title "Food Database Query" — it names the food-database domain but contains no action verbs or capability statements, sitting below the anchor-2 example "Processes PDF files" (which at least states an action) while remaining more domain-specific than the purely generic anchor-1 example.

2 / 5

Completeness

The 'what' is only a vague title (no stated capabilities such as querying, comparing, or recommending) and the 'when' is entirely absent — matching anchor 2 exactly ("vague 'what' and no 'when'"); it cannot reach 3 because the what is never clearly stated.

2 / 5

Trigger Term Quality

Only "food" is a natural user term; users would say "nutrition", "calories", "protein", "营养", or "卡路里", none of which appear, and "database query" is technical phrasing rather than a phrase a user would naturally utter.

2 / 5

Distinctiveness Conflict Risk

The food-nutrition niche is somewhat specific, but a bare title with no trigger guidance would easily overlap with any general nutrition-tracking or diet-logging skill, matching anchor 3 rather than 4 which requires distinct triggers.

3 / 5

Total

9

/

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.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (788 lines); consider splitting into references/ and linking

Warning

description_field

'description' is very short (19 chars), consider making it more detailed

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

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/food-database-query/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.