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

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

68%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.

A well-structured CLI-wrapper skill: highly actionable per-domain command examples, lean prose, and proper use of a one-level-deep API reference. The main weaknesses are the Recipe section's line-wrapped, non-executable commands and the absence of explicit validation checkpoints (e.g., verifying a token before reusing it) in the multi-step enrichment workflow.

Suggestions

Reformat the Recipe section's commands as proper fenced code blocks with real line breaks so they are copy-paste executable like the Feature Domains examples.

Add explicit validation checkpoints to the enrichment workflow, e.g. after submission verify the token is present in the output JSON before running token-result, and check for empty pathwaysFound before drilling down.

Reference references/citation.bib from the body (e.g., in the Prerequisites/citation notification step) so every bundle file is discoverable, and consider moving the species/pathway ID tables into a reference file.

DimensionReasoningScore

Conciseness

The body is efficient — no explanations of concepts Claude already knows, terse command examples, and compact reference tables — but has minor trimmable padding such as 'Reference list for common research organisms' intro sentences and the verbose, poorly formatted Recipe prose. It does not reach the 5 anchor because the species/pathway ID tables and some redundant prose could be tightened or moved to references.

4 / 5

Actionability

All 14 feature domains include concrete, copy-paste-ready 'uv run scripts/reactome_analysis.py ...' commands, which is strong; however, the Recipe section's commands are mangled by line wrapping (e.g. 'bash uv run scripts/reactome_analysis.py analyze-projection \ --data ...' rendered as inline text rather than proper code blocks), so they are not fully executable as written.

4 / 5

Workflow Clarity

The Recipe provides a clear 6-step sequence with specific commands, but validation checkpoints are absent or only implicit — there is no step verifying the token exists in the output before token-based retrieval, no inspection of return status, and no error-recovery guidance for the batch analysis workflow. This matches 'sequence present but checkpoints missing or implicit' rather than the 4 anchor's 'most checkpoints present'.

3 / 5

Progressive Disclosure

The body is well organized with clear sections, and detailed API documentation is correctly split into a real, clearly signaled, one-level-deep reference (references/api_reference.md). Minor organization gaps keep it below 5: references/citation.bib exists in the bundle but is never referenced from the body, and the species/pathway ID tables arguably belong in a reference file.

4 / 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.

An excellent description: it states the domain and both wrapped services, enumerates concrete capabilities that mirror the skill body, and provides an explicit 'Use when' clause with natural trigger phrases. The only weakness is missing a few common synonyms (e.g., 'overrepresentation analysis', 'gene set enrichment').

DimensionReasoningScore

Specificity

The description names the domain ('Query the Reactome database (Analysis and Content Services)') and 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 (including top-level pathways), diagram export, cross-reference mapping, or searching the knowledgebase' — matching the body's feature domains with no meaningful gaps, which fits the comprehensive-coverage anchor rather than the 'minor gaps' anchor at 4.

5 / 5

Completeness

It clearly answers 'what' (query the Reactome database via the Analysis and Content Services) and explicitly answers 'when' with a 'Use when the user asks about...' clause enumerating concrete trigger topics, exactly matching the top anchor; the 4 anchor's 'when could be more explicit' does not apply here.

5 / 5

Trigger Term Quality

It includes natural multi-word phrases users would actually say ('pathway analysis', 'gene list enrichment', 'diagram export', 'top-level pathways'), but omits common synonyms such as 'overrepresentation analysis', 'gene set enrichment', and 'pathway diagram', so it falls just below the comprehensive synonym coverage of the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

'Reactome' plus domain-specific triggers (pathway enrichment, token-based retrieval, cross-reference mapping) carve out a clear niche with minimal overlap risk against generic bioinformatics or database skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

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.