crispr-screen-analyzer

Process CRISPR screening data to identify essential genes and hit candidates. Performs quality control, statistical analysis (RRA), and hit calling for pooled CRISPR screens including viability screens and drug resistance/sensitivity studies.

Quality

65%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/crispr-screen-analyzer/SKILL.md

Quality

Content

56%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 is highly actionable with real executable code matching its bundled script, but it is markedly verbose and monolithic: generic boilerplate and repeated descriptions inflate the body, and an existing reference file is orphaned rather than linked. Workflow clarity is good though the top-level workflow is generic.

Suggestions

Move the screen-type patterns, troubleshooting, and common-pitfalls sections into reference files under references/ and link to them from SKILL.md to reduce the body and fix progressive disclosure.

Delete the generic boilerplate sections (Output Requirements, Response Template, Input Validation, Output Contract, Inputs to Collect, Validation and Safety Rules) and the verbatim description repeats in 'When to Use' / 'Key Features' to tighten conciseness.

Link the existing references/runtime_checklist.md from the References section and correct the false 'No reference files currently available' statement.

Dimension	Reasoning	Score
Conciseness	The ~1188-line body is noticeably verbose: the description is repeated verbatim in 'When to Use' and 'Key Features', and generic boilerplate sections (Output Requirements, Response Template, Input Validation, Output Contract, Validation and Safety Rules, Inputs to Collect) pad the skill with non-CRISPR-specific content.	2 / 5
Actionability	Provides mostly executable, copy-paste-ready code (qc_metrics, calculate_lfc, rra_analysis, identify_hits) that matches the actual main.py API, plus concrete CLI commands and threshold tables, with only minor gaps such as an undeclared matplotlib import and an assumed external library_annotation.csv.	4 / 5
Workflow Clarity	Clear sequenced workflows with validation checkpoints (Gini <0.4 QC check, smoke checks) and feedback loops (fallback path on failure) plus a thorough Quality Checklist, but the top-level 'Workflow' section is generic boilerplate disconnected from the concrete CRISPR execution steps.	4 / 5
Progressive Disclosure	Has section structure, but content that belongs in separate files (4 screen patterns, troubleshooting, common pitfalls) is inlined into SKILL.md, and the existing references/runtime_checklist.md is never linked — the References section even incorrectly states 'No reference files currently available'.	3 / 5
	Total	13 / 20 Passed

Description

75%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 distinctive with strong action verbs and a clear niche, but it omits any explicit 'when to use' trigger guidance, capping completeness at 3. Trigger-term coverage is good but lacks file extensions and synonyms.

Suggestions

Append a 'Use when...' clause naming concrete triggers, e.g. 'Use when analyzing pooled CRISPR screen count matrices, identifying essential genes, or running viability / drug resistance screens.'

Add natural file/term synonyms users would say, such as 'sgRNA count matrix', 'screen analysis', or relevant file extensions, to raise trigger-term coverage to 5.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'identify essential genes and hit candidates', 'quality control', 'statistical analysis (RRA)', 'hit calling' — with comprehensive coverage of the analysis pipeline, matching the score-5 anchor.	5 / 5
Completeness	Has a clear 'what' (QC, RRA, hit calling) but no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Good natural keyword coverage ('CRISPR screening data', 'essential genes', 'pooled CRISPR screens', 'viability screens', 'drug resistance/sensitivity') but missing file extensions (e.g. count matrix, .csv) and common synonyms, so it sits just below the comprehensive score-5 anchor.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (pooled CRISPR screen analysis with RRA/hit calling) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1188 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/crispr-screen-analyzer/SKILL.md
Commit: 63c61d3

Reviewed: 3 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.