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

78%

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 ./skills/reactome_database/SKILL.md

Quality

Content

57%Weight 40%Scale 1-3

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

A well-structured, largely actionable command reference with good progressive disclosure and a single one-level-deep API reference. Its main weakness is the end-to-end 'Recipe' workflow, whose inline commands are malformed and lack validation checkpoints for batch operations.

Suggestions

Fix the 'Recipe' section's inline code: remove the spurious 'bash' prefix and the '\ --data' line-continuation artifacts inside backticks so each step is a single copy-paste-ready 'uv run scripts/reactome_analysis.py ...' command.

Add validation checkpoints to the enrichment workflow (e.g., confirm a token was returned before retrieving results, check that 'pathwaysFound' is non-empty before drilling into a pathway) to satisfy the batch-operation feedback-loop expectation.

Trim redundancy: the 'When to Use This Skill' list overlaps the frontmatter description and the Recipe re-shows commands already in the feature domains — consider shortening one of each pair.

Dimension	Reasoning	Score
Conciseness	Mostly lean command examples, but the 'When to Use This Skill' section duplicates the frontmatter description and the 'Recipe' section re-states commands already shown in the feature domains with extra prose; not score 3 because there is removable redundancy, not score 1 because the body is not padded with concepts Claude already knows.	2 / 3
Actionability	The 14 feature domains give fully executable, copy-paste-ready commands, but the integrative 'Recipe' workflow contains malformed inline code (spurious 'bash' prefix and broken '\ --data' line-wrapping inside backticks) that would not run verbatim; not score 3 because a key section has non-executable details, not score 1 because the bulk is concrete and executable.	2 / 3
Workflow Clarity	The Recipe provides a numbered 6-step sequence, but there are no validation checkpoints for the batch submission/token retrieval flow and the recipe commands are malformed; the rubric caps batch-operation workflows without feedback loops at 2, so it is not score 3, and it is not score 1 because the sequence is clearly ordered.	2 / 3
Progressive Disclosure	Well-organized sections with a single clearly signaled one-level-deep reference to references/api_reference.md (a real file); not score 2 because content is appropriately split rather than inlined and navigation is easy, with no nested reference chains.	3 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that concisely states what the skill does and gives an explicit 'Use when' trigger enumerating many natural user phrasings. It carves out a distinct Reactome niche with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'pathway analysis, gene list enrichment, retrieving results by token, finding unmapped or not-found identifiers, mapping identifiers, reaction participants (inputs, outputs), pathway hierarchy ... diagram export, cross-reference mapping' — matching the anchor for multiple specific concrete actions; not the level below because it goes well beyond naming a domain.	3 / 3
Completeness	Explicitly answers both what ('Query the Reactome database (Analysis and Content Services)') and when ('Use when the user asks about ...'); not the level below because the 'Use when' trigger clause is present and explicit, not merely implied.	3 / 3
Trigger Term Quality	Natural bioinformatics terms a user would actually say ('pathway analysis', 'gene list enrichment', 'mapping identifiers', 'diagram export', 'searching the knowledgebase') with good coverage of variations; not the level below which only has some relevant keywords.	3 / 3
Distinctiveness Conflict Risk	A clear Reactome-specific niche with distinct triggers unlikely to fire for unrelated skills; not the level below because it is not generic and would not meaningfully overlap with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: google-deepmind/science-skills
Path: skills/reactome_database/SKILL.md
Commit: 0b42509

Reviewed: 8 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.