kegg-api

Access the KEGG database API to retrieve biological data (genes, pathways, compounds, drugs). Invoke when the user asks to search, list, or get details from KEGG.

Quality

71%

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 ./scientific-skills/Evidence Insight/kegg-api/SKILL.md

Quality

Content

56%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 actionable with executable KEGG commands and a clear validation-aware workflow, but it is weighed down by generic boilerplate and weak reference signaling. Tightening the templates and moving the operations detail into the reference would materially improve it.

Suggestions

Remove the generic templated sections (When to Use, Key Features, Implementation Details, Output Contract, etc.) that restate process boilerplate and keep only KEGG-specific guidance to cut token bloat.

Replace the inline Operations listing with a pointer to references/KEGG_API_Manual.txt, or vice versa, to avoid duplication and tighten progressive disclosure.

Signal the reference file by name (e.g. "See references/KEGG_API_Manual.txt for full operation details") instead of the generic "Reference material available in references/".

Dimension	Reasoning	Score
Conciseness	The body is padded with generic templated boilerplate ("Scope-focused workflow aligned to...", "Use it when the user can provide the required inputs and expects a structured deliverable", and repeated When-to/Required-Inputs/Workflow/Output-Contract sections) that restates process guidance instead of KEGG specifics, adding many unnecessary tokens.	2 / 5
Actionability	Provides concrete, executable commands (Operations with usage and examples, bash invocations against a real scripts/kegg_client.py) covering the common cases, with only minor gaps such as the optional --option semantics.	4 / 5
Workflow Clarity	The Recommended Workflow sequences validation-first steps with a final validation pass and Failure Handling gives recovery guidance; the KEGG operations are read-only so the destructive/batch cap does not apply, leaving only minor checkpoint gaps.	4 / 5
Progressive Disclosure	A real one-level-deep reference (references/KEGG_API_Manual.txt) and script exist, but the body inlines an Operations summary that duplicates the reference and signals references only generically ("Reference material available in references/") rather than with clear named pointers.	3 / 5
	Total	13 / 20 Passed

Description

87%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 strong: it states concrete capabilities and an explicit invocation trigger scoped to KEGG, with good distinctiveness. Minor gains are available from adding a few more natural trigger synonyms.

Dimension	Reasoning	Score
Specificity	Names the KEGG domain and multiple concrete retrievable entity types ("genes, pathways, compounds, drugs"), giving broad action coverage, though it frames them as one retrieve action rather than enumerating distinct verbs.	4 / 5
Completeness	It explicitly answers what ("Access the KEGG database API to retrieve biological data") and when ("Invoke when the user asks to search, list, or get details from KEGG") with a concrete trigger phrase.	5 / 5
Trigger Term Quality	"search, list, or get details from KEGG" supplies natural trigger verbs a user would say, but omits a few common synonyms (e.g. query, look up) and the API-style term "find".	4 / 5
Distinctiveness Conflict Risk	Scoped to the KEGG database with KEGG-specific triggers, occupying a clear niche with minimal overlap against generic data-retrieval skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/kegg-api/SKILL.md
Commit: 63c61d3

Reviewed: 11 hours 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.