chea-api

Access ChEA3 and Harmonizome ChEA data for transcription factor enrichment analysis and metadata retrieval. Use when the user needs to perform ChEA3 enrichment analysis on a gene set, get metadata about the ChEA dataset, or retrieve information about a specific transcription factor (attribute).

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/chea-api/SKILL.md

Quality

Content

53%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 skill delivers executable code examples that align with its bundled script, but is weighed down by large amounts of generic process boilerplate and an inaccurate `--help` validation section. Tightening the body to ChEA-specific guidance would substantially improve it.

Suggestions

Remove or collapse the generic boilerplate sections (When to Use, Implementation Details, Recommended Workflow, Output Contract, Validation and Safety Rules, Failure Handling) into a few ChEA-specific sentences; they restate generic process guidance Claude already applies.

Fix the 'Quick Validation' section: the script does not support `--help` (it prints 'Unknown command: --help') — either add a real `--help` handler or replace the fabricated 'Expected output format' with the actual CLI usage the script prints.

Replace the hardcoded example path 'cd 20260316/scientific-skills/Evidence Insight/chea-api' with a generic, portable working-directory instruction.

Dimension	Reasoning	Score
Conciseness	Roughly half the body is generic boilerplate ('Execution model: validate the request, choose the packaged workflow', 'Use this skill when the request matches its documented task boundary') that adds no ChEA-specific knowledge and noticeably pads the document.	2 / 5
Actionability	Provides executable, copy-paste-ready Python and CLI examples for all three operations that match the real `scripts/chea_client.py`, but the 'Quick Validation' `--help` path does not work as described (the script reports 'Unknown command: --help') and the 'Expected output format' is fabricated.	4 / 5
Workflow Clarity	A sequenced 'Recommended Workflow' exists, but its validation checkpoints are generic ('Run a final validation pass for completeness') rather than concrete steps tied to the actual ChEA operations, leaving checkpoints implicit.	3 / 5
Progressive Disclosure	Sections are well-organized with clear headers and the sole bundle file `scripts/chea_client.py` is a real, one-level-deep reference; the body is somewhat monolithic and could be leaner but is appropriately structured for a simple API skill.	4 / 5
	Total	13 / 20 Passed

Description

87%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 strong, third-person description that explicitly covers both capabilities and trigger conditions for a well-scoped bioinformatics API skill. Minor improvement would come from adding common synonyms like 'TF' or 'gene list'.

Dimension	Reasoning	Score
Specificity	Names three concrete actions — 'transcription factor enrichment analysis', 'metadata retrieval', and 'retrieve information about a specific transcription factor (attribute)' — which is comprehensive for its niche but wrapped in a slightly generic 'Access... data' phrasing.	4 / 5
Completeness	Clearly states both what it does ('Access ChEA3 and Harmonizome ChEA data for... enrichment analysis and metadata retrieval') and when to use it via an explicit 'Use when the user needs to...' clause with three concrete trigger conditions.	5 / 5
Trigger Term Quality	Includes natural bioinformatics terms a user would say ('ChEA3 enrichment analysis on a gene set', 'transcription factor', 'ChEA dataset'), but omits common synonyms such as 'TF', 'over-representation analysis', or 'gene list'.	4 / 5
Distinctiveness Conflict Risk	Targets a clearly distinct niche (ChEA3/Harmonizome transcription factor enrichment) with specialized triggers, making overlap with unrelated skills minimal.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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/chea-api/SKILL.md
Commit: 63c61d3

Reviewed: 4 hours 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.