CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

reactome-database

Query the Reactome database (Analysis and Content Services). Use when the user asks about pathway analysis, gene list enrichment, retrieving results by token, finding unmapped or not-found identifiers, mapping identifiers, reaction participants (inputs, outputs), pathway hierarchy (including top-level pathways), diagram export, cross-reference mapping, or searching the knowledgebase.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 highly actionable with copy-paste command examples across all domains, but it suffers from missing validation/feedback loops in its batch-operation recipe and inlines reference tables that belong in the references directory.

Suggestions

Add explicit validation/checkpoint steps to the enrichment Recipe (e.g., inspect the output JSON, confirm 'pathwaysFound' is non-empty, retry on error) to satisfy the batch-operation feedback-loop requirement and raise workflow_clarity.

Move the Common Species IDs and Common Pathway IDs tables into references/ (e.g. references/api_reference.md or a new reference file) and reference them from SKILL.md, keeping the body as an overview, to improve progressive_disclosure.

Fix the malformed code blocks in the Recipe (line-wrapped 'bash uv run ...' with stray backslashes) so the workflow commands are copy-paste-executable.

DimensionReasoningScore

Conciseness

The body is mostly lean command examples, but the Overview paragraph and the inline Common Species/Pathway ID tables restate reference material that could be trimmed or moved out of SKILL.md.

4 / 5

Actionability

Every feature domain provides copy-paste-ready 'uv run scripts/reactome_analysis.py <subcommand> --output ...' examples with flags, covering the common cases fully.

5 / 5

Workflow Clarity

The enrichment Recipe has a numbered sequence, but batch/enrichment operations lack explicit validation or error-recovery feedback loops, and the recipe code blocks are malformed by line-wrapping; the batch-operation validation cap applies.

3 / 5

Progressive Disclosure

Section structure exists and one valid reference link (references/api_reference.md) is present at the end, but reference-style content (Species/Pathway ID tables) is inlined and the reference is only signaled once.

3 / 5

Total

15

/

20

Passed

Description

92%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 concisely states what the skill does and gives explicit 'Use when...' triggers with comprehensive, concrete capabilities. Its only minor gap is a few missing synonyms for enrichment terminology.

DimensionReasoningScore

Specificity

Enumerates many concrete actions (pathway analysis, gene list enrichment, token retrieval, identifier mapping, reaction participants, pathway hierarchy, diagram export, cross-reference mapping, search) matching the comprehensive-coverage anchor.

5 / 5

Completeness

Provides a clear 'what' (Query the Reactome Analysis and Content Services) and an explicit 'Use when...' clause with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Natural user phrases like 'pathway analysis', 'gene list enrichment', and 'diagram export' are present, but a few common synonyms (e.g. 'overrepresentation analysis', 'GSEA') are absent.

4 / 5

Distinctiveness Conflict Risk

Names a distinct niche (Reactome pathway/enrichment database) with triggers unlikely to fire for any other skill, minimizing conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

google-deepmind/science-skills

Path

skills/reactome_database/SKILL.md

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.