reactome-database

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

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/databases/reactome-database/SKILL.md

Quality

Content

70%

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 code and a clean progressive-disclosure structure backed by real bundle files, but it is held back by dated version-specific content and missing explicit validation/checkpoint steps in the analysis workflows.

Suggestions

Move the 'Current Database Statistics (Version 94, September 2025)' block and reactome2py version note into a clearly labeled version/deprecation section so time-sensitive data does not penalize conciseness.

Add explicit validation checkpoints to the analysis workflows (e.g., check the HTTP status, confirm the token was returned, handle unmapped identifiers) with a retry/re-check feedback loop before relying on results.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code throughout, but it spends tokens restating identifier types and includes a time-sensitive 'Version 94, September 2025' statistics block and dated package version notes that add maintenance burden without proportional value.	2 / 3
Actionability	Provides fully executable, copy-paste-ready Python snippets with real URLs and payloads (e.g., the overrepresentation POST with headers and token handling) plus runnable CLI examples for the helper script.	3 / 3
Workflow Clarity	Operations are grouped and sequenced (retrieve token, then GET by token), but multi-step analysis workflows lack explicit validation checkpoints or error-recovery feedback loops, which the rubric caps at 2 for batch/API operations.	2 / 3
Progressive Disclosure	SKILL.md is a concise overview that signals one-level-deep references to a real references/api_reference.md and a real scripts/reactome_query.py helper, both of which exist in the bundle; navigation is clear and content is appropriately split.	3 / 3
	Total	10 / 12 Passed

Description

67%

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 clearly scoped to the Reactome pathway niche, but it omits an explicit 'Use when...' trigger clause and leans on technical jargon, capping completeness and trigger-term quality below maximum.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when analyzing gene lists for enriched Reactome pathways, mapping genes to pathways, or querying Reactome reactions/interactions').

Soften technical jargon with natural user-facing terms (e.g., 'pathway enrichment', 'gene-to-pathway mapping') so the description matches phrases a user would actually say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'pathway analysis, enrichment, gene-pathway mapping, disease pathways, molecular interactions, expression analysis' — matching the top anchor that enumerates several specific capabilities.	3 / 3
Completeness	It clearly states what the skill does (the action list) but has no explicit 'Use when...' trigger clause; per the guidelines, a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant terms like 'pathway analysis', 'enrichment', and 'gene-pathway mapping', but uses technical jargon ('REST API', 'systems biology studies') and omits common natural variations a user might say; not the full breadth of the top anchor.	2 / 3
Distinctiveness Conflict Risk	The Reactome/pathway niche is highly specific and clearly distinguishable from other database skills, with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/reactome-database/SKILL.md
Commit: 52845c3

Reviewed: about 12 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.