CtrlK
BlogDocsLog inGet started
Tessl Logo

food-database-query

Food Database Query

38

Quality

37%

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 a long, well-sectioned but padded specification that mixes actionable logic with non-actionable reference material (RDA tables, full schema dumps, roadmaps). Code examples are illustrative pseudocode rather than executable, and the workflows lack the validation/verification checkpoints that batch nutrition calculations call for.

Suggestions

Move the RDA reference tables, the full per-food JSON schema, and the extension roadmap into separate reference files (e.g. references/rda.md, references/schema.md) and link to them one level deep, leaving SKILL.md a lean overview.

Replace stub-function pseudocode with runnable helpers or clearly mark them as interfaces and provide concrete implementations for at least fuzzy_search and portion parsing so Claude can execute rather than re-implement.

Add validation checkpoints to the auto-calculation workflow (verify each food resolved from the database, flag unrecognized foods, confirm portion-to-gram conversion before computing nutrition, and re-check the summed meal totals).

DimensionReasoningScore

Conciseness

The ~780-line body is noticeably verbose with several padded sections that do not help Claude act — a full RDA reference table, a complete per-food JSON schema dump, an "extension roadmap", "quality assurance" and "notes" sections, and explanatory asides about cooking/vitamins Claude already knows — matching the score-2 anchor for several unnecessary or padded sections; it is above 1 because core operational content is still present, but below 3 due to the volume of non-actionable padding.

2 / 5

Actionability

Concrete logic and data structures are provided, but the code examples rely on undefined stub functions (extract_food_name, normalize_food_name, query_database, levenshtein_distance, fuzzy_search) and are illustrative rather than executable, fitting the score-3 anchor "Some concrete guidance but incomplete; pseudocode instead of executable code"; it is not a 2 because real logic and JSON schemas are given, and not a 4 because nothing is copy-paste runnable.

3 / 5

Workflow Clarity

Sequences exist (query flow 1-4, meal-processing 1-5) but they are descriptive lists with no validation checkpoints (e.g. confirming a food was found, handling missing foods, verifying portion conversions before calculating), matching the score-3 anchor of steps present but checkpoints missing; the batch auto-calculation path without verification also caps it at 3 per the batch-operation guideline.

3 / 5

Progressive Disclosure

The body has clear section structure (five functional modules, data structure, RDA, examples) but is a single monolithic file with content that belongs in separate reference files (RDA tables, full food JSON schema, roadmap) inlined, and the only file references are to external data/command files rather than bundle references, fitting the score-3 anchor of some structure with content that should be separate left inline; it is above 2 because sectioning is genuine, and below 4 because no one-level-deep reference files split the bulk out.

3 / 5

Total

11

/

20

Passed

Description

32%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 title ("Food Database Query") with no enumerated actions, no trigger phrases, and no "Use when" guidance, so it fails to tell Claude what the skill does or when to invoke it. Only its narrow food/nutrition niche keeps it from being entirely generic.

Suggestions

Rewrite as full third-person sentences listing concrete actions, e.g. "Queries a food/nutrition database for foods, compares nutrition across foods, recommends foods by nutrient or health condition, and computes meal nutrition from portion descriptions."

Add an explicit trigger clause: "Use when the user asks about food nutrition, calories, macros, vitamins, GI values, food comparisons, or meal nutrition calculations."

Include natural synonyms and file artifacts users say (nutrition, calories, protein, fiber, glycemic index, RDA, food-database.json) to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description is just the label "Food Database Query" — it names the domain and a single implied action (query) but lists no concrete capabilities, matching the score-2 anchor "Names the domain but actions are minimal or generic"; it is not a 1 because it does name a concrete domain, and not a 3 because no distinct concrete actions are enumerated.

2 / 5

Completeness

It has only a vague "what" (queries a food database) and no "when"/"Use when" clause at all, matching the score-2 anchor "Has a vague 'what' and no 'when'"; it cannot reach 3 because the "what" is not clearly stated as concrete actions, and the missing trigger guidance caps it regardless.

2 / 5

Trigger Term Quality

Only the generic keywords "food", "database", and "query" appear with no natural trigger phrases users would say (e.g. "nutrition", "calories", "food lookup"), fitting the score-2 anchor of one or two generic keywords missing the natural phrases; it is above 1 because "food" is a genuine natural term, but below 3 because common variations/synonyms are absent.

2 / 5

Distinctiveness Conflict Risk

The food/nutrition database niche is fairly specific and unlikely to collide with unrelated skills, matching the score-4 anchor "Mostly distinct; minor overlap risk"; it is not a 5 because the terse label lacks explicit distinct triggers, and not a 3 because the domain is concrete rather than broad like "document files".

4 / 5

Total

10

/

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 (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
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.