CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

reactome-skill

Query the Reactome REST API for pathway content and enrichment analyses; use when you need curated pathway data, reaction details, or overrepresentation results for a gene list.

Quality

79%

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 ./scientific-skills/Evidence Insight/reactome-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-organized with runnable, copy-paste examples that match the bundled script. Its main weaknesses are a padded Implementation Details section and Key Features entries (expression mapping, hierarchy, species projection) that have no corresponding commands. The reference file also defers entirely to external documentation rather than adding value.

Suggestions

Trim the Implementation Details section: remove statements that restate the examples (stable-ID format, generic API-access description) and the duplicated https://reactome.org/dev link, keeping only non-obvious details like the text/plain newline-separated identifier submission format.

Either provide runnable examples for the claimed expression analysis, hierarchy access, and species projection features, or remove them from Key Features since the bundled script supports only query_content and analyze_identifiers.

Remove the reactome2py dependency (the script uses only requests) and populate references/api_reference.md with concrete endpoint details (e.g., /data/query/{id}, POST /identifiers/ with text/plain) instead of a bare pointer to reactome.org/dev.

DimensionReasoningScore

Conciseness

Mostly efficient, but the "Implementation Details" section pads with statements Claude can infer: "The skill uses the Reactome REST API... to fetch pathway content" and "Stable IDs: Content retrieval expects Reactome stable identifiers (commonly formatted like R-HSA-xxxxx...)" restate what the examples already show. The https://reactome.org/dev link is also duplicated from references/api_reference.md. Not a 2 because the rest (When to Use, Key Features, Dependencies, examples) is tight and useful.

3 / 5

Actionability

Both example commands ("python scripts/reactome_tool.py query_content --id \"R-HSA-69278\"" and "analyze_identifiers --identifiers \"TP53,BRCA1\"") are copy-paste ready and match the actual script's CLI. Not a 5 because Key Features claims "Expression analysis", "Pathway hierarchy access", and "Species projection" yet provides no commands or steps for any of them.

4 / 5

Workflow Clarity

The install-then-run sequence is clear and both single-step actions are unambiguous (this is a simple, non-destructive skill, so no validation cap applies). Falls short of 5 because there is no guidance on interpreting the JSON output, handling the script's error dictionaries, or what to do after an analysis returns.

4 / 5

Progressive Disclosure

The body is a well-sectioned overview pointing to a real one-level-deep reference ("see `references/api_reference.md`") and a working script (scripts/reactome_tool.py), so navigation is easy. Not a 5 because api_reference.md is content-free (just an external link), so the split adds little, and the reference is mentioned twice redundantly.

4 / 5

Total

15

/

20

Passed

Description

83%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 specific, complete, and clearly triggers on Reactome-related pathway and enrichment requests. It explicitly answers both what the skill does and when to use it. Minor improvements would add the remaining capabilities (hierarchy, expression mapping, species projection) and a few more natural synonyms.

DimensionReasoningScore

Specificity

"Query the Reactome REST API for pathway content and enrichment analyses" plus outputs like "curated pathway data, reaction details, or overrepresentation results" lists several specific actions and output types. Not a 5 because the body's other capabilities (hierarchy access, expression mapping, species projection) are absent, leaving minor coverage gaps.

4 / 5

Completeness

Both what ("Query the Reactome REST API for pathway content and enrichment analyses") and when ("use when you need curated pathway data, reaction details, or overrepresentation results for a gene list") are explicit, with concrete trigger phrases. Matches the anchor-5 example structure; anchor 4's "when could be more explicit" does not apply.

5 / 5

Trigger Term Quality

Natural terms users would say are present: "pathway", "enrichment", "gene list", "overrepresentation", "Reactome". A few common variations are missing (e.g., "gene set", "pathway analysis", "functional enrichment"), so it sits between anchor 3 and comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

Naming Reactome gives a clear niche with minimal conflict against unrelated skills, but generic triggers like "enrichment analyses... for a gene list" create minor overlap risk with closely related enrichment skills (GO/KEGG-style). Mostly distinct rather than fully distinct.

4 / 5

Total

17

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

aipoch/medical-research-skills

Path

scientific-skills/Evidence Insight/reactome-skill/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.