reactome-database

Query Reactome REST API for pathway analysis, enrichment, gene-pathway mapping, disease pathways, molecular interactions, expression analysis, for systems biology studies.

Quality

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/bio/reactome-database/SKILL.md

Quality

Content

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable, copy-paste-ready examples, but it suffers from a dated statistics block, missing validation feedback loops in analysis workflows, and progressive-disclosure references to bundle files that do not exist. Tightening the dated content and adding the missing referenced files would lift the lower dimensions.

Suggestions

Create the referenced references/api_reference.md and scripts/reactome_query.py, or remove the references to them, so navigation is not broken.

Add validation checkpoints to the analysis workflow (check HTTP status, handle empty/unmapped identifier responses, handle expired-token errors).

Move the 'Current Database Statistics (Version 94, September 2025)' block into a dated/deprecated-style section or drop it, since time-sensitive version data penalizes conciseness as it ages.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code, but repeats concepts (API base URLs, identifier types) and includes a dated, soon-stale database-statistics block (Version 94, September 2025) that will bloat the file as it ages.	2 / 3
Actionability	Provides copy-paste-ready, executable Python for querying, analysis, expression submission, and visualization with concrete URLs and identifier examples.	3 / 3
Workflow Clarity	Multi-step workflows (submit analysis, capture token, retrieve by token) are sequenced, but there are no validation checkpoints or error-recovery feedback loops for operations that can fail (analysis submission, token expiry, unmapped identifiers).	2 / 3
Progressive Disclosure	References to references/api_reference.md and scripts/reactome_query.py are signaled, but no bundle directories (references/, scripts/, assets/) actually exist, so the referenced detailed materials are missing and navigation breaks.	1 / 3
	Total	8 / 12 Passed

Description

50%

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 specific and distinctive but fails the completeness requirement: it states capabilities but gives no explicit 'when to use' trigger guidance, capping completeness at the floor. Trigger terms are domain-relevant but technical rather than natural.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when performing pathway enrichment, mapping genes to pathways, or analyzing expression data for systems biology research.'

Include more natural user-facing trigger terms like 'pathways', 'gene list', 'Reactome', and 'overrepresentation'.

Use consistent third-person voice and trim the comma-separated action list slightly for readability.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'pathway analysis, enrichment, gene-pathway mapping, disease pathways, molecular interactions, expression analysis'.	3 / 3
Completeness	States what the skill does but has no 'Use when...' clause or equivalent trigger guidance, so the 'when' half is entirely missing.	1 / 3
Trigger Term Quality	Contains relevant domain terms (pathway, enrichment, gene) but leans technical and omits common user variations like 'pathways', 'gene list', or 'GO analysis'.	2 / 3
Distinctiveness Conflict Risk	The Reactome-specific niche (curated pathway database, enrichment, systems biology) is clearly distinct from other skills and unlikely to trigger the wrong one.	3 / 3
	Total	9 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 6 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/reactome-database/SKILL.md
Commit: df37802

Reviewed: about 1 hour 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.