CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

reactome-database

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

Quality

72%

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

Fix and improve this skill with Tessl

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

Quality

Content

65%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, highly actionable skill body with excellent progressive disclosure into the bundled reference and script. The main gaps are the absence of any validation/error-recovery steps in the analysis workflows and a time-sensitive database-statistics section that will go stale.

Suggestions

Add validation checkpoints to the analysis workflow: check the HTTP response status, inspect the summary/entities fields for unmapped identifiers, and show how to handle a failed or empty submission.

Move the 'Current Database Statistics (Version 94, September 2025)' section into references/api_reference.md or an explicitly dated 'database version notes' area so stale version data does not occupy the main body.

Consolidate the two separate pointers to references/api_reference.md into one well-placed link, and mirror the token-extraction line in the expression-analysis example for consistency.

DimensionReasoningScore

Conciseness

The body is mostly efficient — executable code with no conceptual padding about what pathways or REST are — but the 'Current Database Statistics (Version 94, September 2025)' section is time-sensitive version/date data outside any deprecated/old-patterns section, and the pointer to references/api_reference.md is repeated twice. Not anchor 4 because these are more than minor trimmable instances; not 2 because the bulk genuinely earns its tokens with API-specific details (TSV format rules, token lifetime, identifier types).

3 / 5

Actionability

Copy-paste-ready requests code with real endpoint URLs and example IDs, exact input format specifications (TSV with '#'-prefixed header, period decimal separator), accepted identifier types, and runnable CLI examples for the bundled script. Falls short of anchor 5 on minor gaps: no HTTP status/error handling in any example, and the expression-analysis example omits the token extraction shown in the overrepresentation example.

4 / 5

Workflow Clarity

The multi-step analysis flow (submit identifiers -> save token -> retrieve by token -> build PathwayBrowser URL) is sequenced across clearly ordered sections, and token lifetime is documented. However, no validation checkpoints exist anywhere — nothing checks response status, warns about unmapped identifiers in the 'entities' field, or handles a failed submission, matching the 'steps present but checkpoints missing' anchor.

3 / 5

Progressive Disclosure

Clean split: getting-started usage and key examples live inline, the 465-line endpoint reference is in references/api_reference.md with clearly signaled pointers (verified the file exists), and the helper script sits in scripts/reactome_query.py with CLI usage shown. References are one level deep and navigation is easy, matching the anchor-5 pattern.

5 / 5

Total

15

/

20

Passed

Description

70%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.

A concrete, domain-specific description with good trigger terminology and near-zero conflict risk. Its main weakness is the complete absence of a 'when to use it' clause, which both caps completeness and slightly weakens its value as a routing signal.

Suggestions

Append an explicit trigger clause, e.g. 'Use when working with Reactome, pathway enrichment, gene set analysis, or molecular interaction data.'

Use distinct concrete verbs for the actions (e.g., 'Analyze gene lists for pathway enrichment, map genes to pathways, retrieve molecular interactions') instead of one generic 'Query ... for' construction.

Add common synonyms such as 'overrepresentation analysis' and 'gene set enrichment' to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

The description lists several specific actions ('pathway analysis, enrichment, gene-pathway mapping, disease pathways, molecular interactions, expression analysis') within a named domain (Reactome REST API). It falls short of anchor 5 because all actions hang off the single generic verb 'Query' rather than distinct concrete verbs, and it does not name the two distinct API services.

4 / 5

Completeness

It clearly answers 'what' (queries Reactome for pathway analysis, enrichment, mapping, interactions) but contains no 'Use when...' clause or any equivalent explicit trigger guidance, capping completeness at 3 per the judging guidelines. It is not a 2 because the 'what' half is concrete and multi-faceted.

3 / 5

Trigger Term Quality

Good coverage of natural terms users would say ('pathway analysis', 'enrichment', 'gene-pathway mapping', 'expression analysis', 'systems biology') with Reactome explicitly named. Not anchor 5 because common variations like 'overrepresentation analysis', 'gene set enrichment', or 'pathway enrichment' are absent.

4 / 5

Distinctiveness Conflict Risk

'Query Reactome REST API' pins a clear niche (one specific pathway database) with distinct domain triggers; minimal risk of firing for the wrong skill. The trailing 'for systems biology studies' is slightly broad but the Reactome naming dominates.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

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.