biogrid-orcs

Accesses BioGRID ORCS CRISPR screen data (organisms, screens, scores). Invoke when user needs to search CRISPR screens, get vocabulary, or retrieve gene scores.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/biogrid-orcs/SKILL.md

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 content is highly actionable with concrete, executable commands and well-structured one-level references, but it is weighed down by substantial generic boilerplate that pads the token budget without adding domain value. Trimming the process-template sections would materially improve it.

Suggestions

Remove or collapse the generic template sections ('When to Use', 'Key Features', 'Implementation Details', 'Required Inputs', 'Recommended Workflow', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling') that restate process concepts Claude already knows, keeping only BioGRID-specific guidance.

Delete the verbatim re-quoting of the description inside the 'Key Features' section, which duplicates the frontmatter at token cost.

Merge 'Quick Validation' and 'Example Usage' run plan into the concrete Usage section so validation is tied to the actual commands rather than presented as abstract steps.

Dimension	Reasoning	Score
Conciseness	The body includes many generic, padded sections ('When to Use', 'Key Features', 'Implementation Details', 'Recommended Workflow', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling') that restate process concepts Claude already knows and re-quote the description verbatim. It is not a 3 because the padding is substantial and pervasive rather than a few stray explanations.	2 / 5
Actionability	The Usage section provides seven copy-paste-ready commands with real arguments (e.g., '--organismID 9606 --cellLine hela', '--name "BRCA1\|TP53"') covering every endpoint. This matches the top anchor for fully executable, copy-paste-ready guidance covering common cases.	5 / 5
Workflow Clarity	A clear sequence exists (Example run plan, Recommended Workflow) with validation checkpoints (Quick Validation, 'validate required inputs before execution and stop early', 'final validation pass'). It is not a 5 because the workflow steps are largely generic abstractions rather than concrete, BioGRID-specific feedback loops.	4 / 5
Progressive Disclosure	Real bundle files are correctly referenced one level deep ('scripts/biogrid_client.py', 'references/api_docs.md for full API documentation'), with command details inline and bulk API docs separated. It is not a 5 because some generic boilerplate that adds no value is inlined rather than trimmed or moved.	4 / 5
	Total	15 / 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 clearly states both capability and invocation triggers with concrete, domain-specific terms. Minor improvements could add a few synonyms, but it is already near the top of the rubric.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions ('search CRISPR screens, get vocabulary, or retrieve gene scores') alongside concrete data types ('organisms, screens, scores'), with only minor coverage gaps. It is not a 5 because it does not enumerate the full action set (e.g., searching genes) comprehensively.	4 / 5
Completeness	It explicitly answers both 'what' ('Accesses BioGRID ORCS CRISPR screen data (organisms, screens, scores)') and 'when' ('Invoke when user needs to search CRISPR screens, get vocabulary, or retrieve gene scores') with concrete trigger phrases. It clearly meets the top anchor rather than the 4 anchor, whose 'when' is only weakly specified.	5 / 5
Trigger Term Quality	Phrases like 'CRISPR screens', 'gene scores', and 'get vocabulary' are natural terms a domain user would say, giving good keyword coverage. It is not a 5 because it lacks synonyms or variations beyond the core terms.	4 / 5
Distinctiveness Conflict Risk	'BioGRID ORCS CRISPR screen data' is a narrow, well-defined niche with distinct triggers, making conflict with other skills minimal. It fits the top anchor for a clear niche with minimal conflict risk.	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/biogrid-orcs/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.