encode-api

Access the ENCODE Project REST API to search for and retrieve biological data (biosamples, experiments, etc.). Use this skill when the user needs to query ENCODE data, search by keywords, or retrieve specific objects by accession ID.

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/encode-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 body delivers concrete, executable ENCODE examples and a well-sectioned structure, but is weighed down by substantial generic boilerplate, a duplicated description, and a non-functional --help validation command. Tightening the template sections and fixing the verification step would materially improve it.

Suggestions

Remove or collapse the generic boilerplate sections (When to Use, Implementation Details, Required Inputs, Recommended Workflow, Output Contract, Validation and Safety Rules, Failure Handling) into ENCODE-specific guidance, and drop the verbatim description repeat in 'Key Features'.

Fix the broken validation path: the script's __main__ runs hardcoded tests with no argparse, so 'python scripts/encode_client.py --help' fails — either add a real CLI/argparse interface or replace the Quick Validation step with an actual working check.

Correct the cross-reference in 'Example Usage' ('See ## Usage above') since the Usage section appears below it, and remove the odd hardcoded cd path '20260316/scientific-skills/Evidence Insight/encode-api'.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: large generic boilerplate sections ('When to Use', 'Implementation Details', 'Required Inputs', 'Recommended Workflow', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling') add little ENCODE-specific value and the description is repeated verbatim in 'Key Features', fitting the 'several unnecessary padded sections' anchor rather than the mostly-efficient 3.	2 / 5
Actionability	Provides two concrete, executable Python examples (search_encode, get_object) that match the real script, plus API reference details, but the 'python scripts/encode_client.py --help' validation command is non-functional since the script has no argparse and runs hardcoded tests on __main__ — a minor gap keeping it below 5.	4 / 5
Workflow Clarity	A sequenced 'Recommended Workflow' and validation language exist, but the checkpoints are generic boilerplate rather than ENCODE-specific and the 'Quick Validation' step relies on a broken --help command, fitting the 'steps listed but validation gaps / checkpoints implicit' anchor.	3 / 5
Progressive Disclosure	Well-organized with clear section headers and a real, clearly-signaled script reference (scripts/encode_client.py); minor gaps are the broken cross-reference ('See ## Usage above' when Usage is below) and inlined generic boilerplate, so it sits above the under-organized 3 but below the clean one-level-deep 5.	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, well-structured description that clearly states both capability and trigger conditions with concrete, domain-specific language. The only weak spot is trigger-term breadth, where a few synonyms would make it fully comprehensive.

Dimension	Reasoning	Score
Specificity	Names the ENCODE domain and several concrete actions — 'search for and retrieve biological data', 'search by keywords', 'retrieve specific objects by accession ID' — with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	Explicitly answers both 'what' (Access the ENCODE REST API to search/retrieve biological data) and 'when' ('Use this skill when the user needs to query ENCODE data, search by keywords, or retrieve specific objects by accession ID') with concrete trigger phrases, matching the anchor 5 example structure.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('ENCODE data', 'search by keywords', 'accession ID', 'biosamples, experiments') that users would plausibly say, but missing some synonyms and file-extension-style variants that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	ENCODE Project is a narrow, well-defined niche with distinct triggers ('ENCODE', 'accession ID', 'biosamples') and minimal overlap risk with other skills.	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/encode-api/SKILL.md
Commit: 63c61d3

Reviewed: 6 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.