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

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

93%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 tight, highly actionable single-purpose skill with executable examples and well-organized sections that leverage the bundled script appropriately. The only gap is the absence of an explicit validation/error-recovery loop for batch collection requests.

Suggestions

Add an explicit error-handling checkpoint, e.g. 'If ok=false, inspect error.code (network_error/invalid_input/invalid_response), adjust the request, and re-run' to support recovery on batch endpoints.

For collection endpoints with pageSize/max_items, note how to confirm truncation (record_count_available > record_count_returned) and page further when the user needs more.

Optionally show the success-output shape inline with a one-line compact example so Claude can map summary vs records fields without a round trip.

Dimension	Reasoning	Score
Conciseness	The body is lean and rule-driven with no padding or explanation of concepts Claude already knows; every line (base_url, pageSize guidance, POST+json_body, Accept header) earns its place.	5 / 5
Actionability	It provides executable, copy-paste-ready examples in the Execution section plus two concrete cBioPortal request JSON patterns, covering the common study-list and mutation-fetch cases.	5 / 5
Workflow Clarity	Operating rules, execution behavior, input, output, and a worked command are clearly sequenced, but there is no explicit validation/error-recovery checkpoint for failed or batch requests despite batch collection endpoints.	4 / 5
Progressive Disclosure	The skill is well under 50 lines, single-purpose, and correctly confines bulk logic to the bundled scripts/rest_request.py while keeping SKILL.md as a concise overview with clear section organization.	5 / 5
	Total	19 / 20 Passed

Description

67%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 specific, third-person description that clearly scopes the cBioPortal API niche and includes an explicit use-when clause. It is held back from a top score by trigger-term coverage that omits natural synonyms and explicit trigger phrases.

Suggestions

Add concrete natural trigger phrases, e.g. 'Use when a user asks about cBioPortal studies, cancer genomics data, tumor samples, or mutation/clinical data summaries'.

Include synonyms or recognizable terms users say, such as 'cancer genomics', 'tumor profiling', or 'cBioPortal study summaries', to broaden trigger coverage.

Clarify the output contract briefly in the description (e.g. 'returns concise summaries') to reinforce the distinct, single-purpose niche.

Dimension	Reasoning	Score
Specificity	"Submit compact cBioPortal API requests for studies, molecular profiles, mutations, clinical data, and samples" lists several concrete actions and named data types, with only minor coverage gaps (e.g. sample lists, structural variants).	4 / 5
Completeness	The "what" is explicit (compact cBioPortal API requests for the listed entities) and the "when" is present ("Use when a user wants concise cBioPortal summaries"), though the trigger could be more explicit with concrete phrases.	4 / 5
Trigger Term Quality	Terms like "studies," "molecular profiles," "mutations," and "clinical data" are relevant domain keywords, but it lacks common natural-language variations and file extensions that a user might actually say.	3 / 5
Distinctiveness Conflict Risk	The cBioPortal niche is specific and clearly scoped, with only minor overlap risk against other biomedical-API skills.	4 / 5
	Total	15 / 20 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: openai/plugins
Path: plugins/life-science-research/skills/cbioportal-skill/SKILL.md
Commit: 1dc1958

Reviewed: 5 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.