Name: food-database-query
Rating: 32.800000000000004 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

food-database-query

Food Database Query

Quality

29%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

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/food-database-query/SKILL.md

The canonical home for this skill is food-database-query in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

38%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 thorough, well-sectioned specification of the food database skill with concrete logic and usage examples, but it is token-heavy due to inlined reference data and would benefit from externalizing data structures and adding validation steps to its batch workflows.

Suggestions

Move the full food-record JSON schema and RDA dictionaries into separate reference files (e.g. references/data-structure.md, references/rda.md) and link to them one level deep to improve progressive disclosure and token efficiency.

Add explicit validation/verification checkpoints to the meal-recording and nutrition-calculation workflows (e.g. confirm each food resolved, validate portion conversion, verify totals before logging).

Either provide the helper functions (extract_food_name, normalize_food_name, query_database, levenshtein_distance) or mark the code as illustrative pseudocode so the actionability gap is explicit rather than implicit.

Dimension	Reasoning	Score
Conciseness	The ~780-line body inlines a complete 110-line food-record JSON and full male/female RDA dictionaries that clearly belong in separate data/reference files, making it noticeably verbose despite not explaining concepts Claude already knows.	2 / 5
Actionability	It provides concrete Python logic for search, compare, recommend, parse, and calculate, but the examples call undefined helpers (extract_food_name, normalize_food_name, query_database, levenshtein_distance, RDA) so they are illustrative rather than copy-paste executable, leaving key details missing.	3 / 5
Workflow Clarity	Multi-step sequences are present (query flow, meal recording 1-5), but the batch meal-recording and nutrition-calculation workflows lack any validation/verification checkpoints, which caps workflow clarity at 3 per the batch-operation guideline.	3 / 5
Progressive Disclosure	No references/scripts/assets bundle exists and the skill is a single monolithic file with the full data structure and RDA tables inlined rather than split into one-level-deep reference files, matching the 'content that clearly belongs in separate files is inlined' anchor despite good section headers.	2 / 5
	Total	10 / 20 Passed

Description

20%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 frontmatter description is just a skill name rather than a descriptive sentence, omitting both concrete capabilities and any 'Use when…' trigger guidance. It is too vague to reliably route the model to this skill.

Suggestions

Rewrite the description as a third-person sentence stating concrete actions, e.g. 'Queries, compares, and recommends foods from a nutrition database and calculates per-portion nutrients.'

Add an explicit trigger clause such as 'Use when the user asks about food nutrition, compares foods, needs dietary recommendations, or logs a meal for calorie/nutrient calculation.'

Include natural synonyms users say (nutrition, calories, 营养, dietary) and file/keyword cues to improve trigger matching and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description 'Food Database Query' names the domain (food database) plus a minimal action (query), matching the 'Names the domain but actions are minimal or generic' anchor like 'Processes PDF files'; it does not list the concrete capabilities (search, compare, recommend, calculate) that the body covers.	2 / 5
Completeness	It is a three-word title with no explicit 'what does this do' detail and no 'when should Claude use it' clause, so both halves are missing/extremely vague per the score-1 anchor.	1 / 5
Trigger Term Quality	It surfaces only 'food', 'database', and 'query' — a couple of generic keywords — and omits natural phrases and synonyms a user would actually say such as nutrition, calories, 营养, or dietary recommendations.	2 / 5
Distinctiveness Conflict Risk	'Food Database Query' targets a specific enough niche that it is unlikely to fire for unrelated skills, but the bare label could still overlap with other nutrition or recipe skills and carries no distinct trigger phrasing.	3 / 5
	Total	8 / 20 Passed

Validation

81%

Warnings & errors only

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

Criteria	Description	Result
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-claude/skills/food-database-query/SKILL.md
Commit: 57c135b

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.