CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cbioportal-skill

Submit compact cBioPortal API requests for studies, molecular profiles, mutations, clinical data, and samples. Use when a user wants concise cBioPortal summaries

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

86%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 tight, actionable, and honest about its bundle: a single script, an exact runnable command, complete request patterns, and explicit scope limits. The only meaningful gap is that the multi-step study → profile → mutation-fetch flow and error-recovery behavior are implied rather than sequenced.

DimensionReasoningScore

Conciseness

The body is lean bullet-point guidance with no explanation of concepts Claude already knows and no padding (e.g. "Collection endpoints are better with `pageSize=10` and `max_items=10`"). Not a 5 because the Input section restates the script's complete field list and duplicate JSON patterns — details Claude could read from `scripts/rest_request.py` itself.

4 / 5

Actionability

Fully executable guidance: a fixed base URL, an exact `echo '{...}' | python scripts/rest_request.py` command, and two complete JSON request patterns covering the common study-search and mutation-fetch cases. Copy-paste ready with concrete headers, params, and paths.

5 / 5

Workflow Clarity

The single action (pipe one JSON object to the script) is unambiguous, and preferred endpoint paths are listed. Not 5 because the chained lookup flow (find study → resolve profile ID → fetch mutations) is only implied by the path list, and there is no retry/error-recovery loop for `ok=false` responses; above 3 since the simple-skill sequence is clear and no risky operations require validation checkpoints.

4 / 5

Progressive Disclosure

The skill is well under 50 lines with clearly organized sections, and its bundle structure matches reality: `scripts/rest_request.py` exists, no references directory is needed, and the body explicitly states "No additional runtime references are required; keep the import package limited to this file and `scripts/rest_request.py`." Per the simple-skill guideline this earns full marks with just well-organized sections.

5 / 5

Total

18

/

20

Passed

Description

71%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 and distinct, anchored by the cBioPortal platform name and a well-enumerated set of data domains, with an explicit "Use when" clause. Its main weakness is trigger coverage: natural user phrasings and synonyms for the domain are thin, and the "when" clause only covers the summary use case.

Suggestions

Broaden trigger terms to include natural user phrasings such as "cancer study", "genomic data", "gene mutations", and "patient clinical data" so users who don't say "cBioPortal" verbatim still match.

Expand the "Use when" clause to cover all supported flows, e.g. "Use when a user asks about cBioPortal studies, molecular profiles, mutations, or clinical/sample data, or wants a concise summary of results".

Name the concrete output actions per domain (e.g. "fetch mutations for a gene", "list samples in a study") instead of the generic "Submit compact API requests".

DimensionReasoningScore

Specificity

"Submit compact cBioPortal API requests for studies, molecular profiles, mutations, clinical data, and samples" names several concrete data domains with a clear action. It falls short of a 5 because the action verb stays generic ("submit requests") without covering what is done per domain.

4 / 5

Completeness

Both a clear "what" (submit compact cBioPortal API requests for five data types) and an explicit "when" ("Use when a user wants concise cBioPortal summaries") are present. Not a 5 because the "when" clause is narrow and near-circular, covering only summary requests and omitting trigger phrases for the mutation-fetch and clinical queries the skill body supports.

4 / 5

Trigger Term Quality

"cBioPortal" plus "studies", "mutations", "clinical data", and "samples" are relevant keywords, but common natural variations users would say ("cancer study", "genomic data", "gene mutations", "patient data") are missing. Better than 2 since the niche-defining term is present; below 4 due to missing synonyms.

3 / 5

Distinctiveness Conflict Risk

"cBioPortal" is a specific named platform with distinct triggers (studies, molecular profiles, mutations, clinical data), giving the skill a clear niche with minimal overlap risk against any other skill category.

5 / 5

Total

16

/

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

openai/plugins

Path

plugins/life-science-research/skills/cbioportal-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.