tooluniverse-crispr-screen-analysis

Analyze CRISPR-Cas9 genetic screens — MAGeCK gene-level scores, sgRNA count QC, replicate correlation, hit prioritization, and pathway GSEA on screen output. Use for genome-wide essentiality screens, synthetic-lethality discovery, dropout vs positive-selection screen analysis, target identification, and resistance-screen interpretation. Includes screen-QC and statistical thresholds.

Quality

78%

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 ./plugin/skills/tooluniverse-crispr-screen-analysis/SKILL.md

Quality

Content

63%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.

Well-structured with a clear sequenced workflow and real bundled reference data, but the main executable Quick Start is pseudocode and its supporting detail files are absent. Fixing the broken See Also references and providing executable phase code would lift the weaker dimensions.

Suggestions

Create the missing See Also files (ANALYSIS_DETAILS.md, USE_CASES.md, EXAMPLES.md, QUICK_START.md, FALLBACK_PATCH.md) or remove their references, since they currently dead-end.

Replace the Quick Start pseudocode with executable definitions of load_sgrna_counts, mageck_gene_scoring, etc., or inline concrete implementations instead of deferring to a non-existent file.

Add an explicit validate-fix-retry loop (e.g., if recovery_rate < 0.8 or QC fails, re-run filtering/normalization) to raise workflow clarity to 5.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes competence (no basic-concept padding), but has minor redundancy: the "Comprehensive skill for analyzing..." line repeats the description and the Overview restates the phase list.	4 / 5
Actionability	The Quick Start relies on undefined helper functions (load_sgrna_counts, mageck_gene_scoring, etc.) that are pseudocode, and the detailed implementations are deferred to ANALYSIS_DETAILS.md which is missing; concrete thresholds, tool params, and the real reference_gene_sets import partially compensate.	3 / 5
Workflow Clarity	A clear 8-phase sequence with Rule Zero pre-check and validation checkpoints (Phase 2 QC, recovery_rate > ~0.8 QC check, evidence grading); lacks an explicit validate-fix-retry loop so it sits just below 5.	4 / 5
Progressive Disclosure	Good section structure and the scripts/ bundle references resolve (reference_gene_sets.py exports core_essential/nonessential/recovery_rate), but all 5 "See Also" .md files (ANALYSIS_DETAILS.md, USE_CASES.md, EXAMPLES.md, QUICK_START.md, FALLBACK_PATCH.md) are missing, leaving broken one-level references.	3 / 5
	Total	14 / 20 Passed

Description

92%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 description that explicitly states capabilities and use-when triggers with concrete domain terms. It is comprehensive and well-niched, with only minor synonym gaps in trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists five concrete actions ("MAGeCK gene-level scores, sgRNA count QC, replicate correlation, hit prioritization, and pathway GSEA") covering the screen-analysis workflow comprehensively, matching the multiple-specific-actions anchor.	5 / 5
Completeness	Explicitly answers both what ("Analyze CRISPR-Cas9 genetic screens — ...") and when ("Use for genome-wide essentiality screens, synthetic-lethality discovery...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural trigger coverage ("genome-wide essentiality screens, synthetic-lethality discovery, dropout vs positive-selection screen analysis, resistance-screen interpretation") but misses common synonyms like "knockout screen", "fitness screen", or "loss-of-function screen".	4 / 5
Distinctiveness Conflict Risk	A clear CRISPR-Cas9 screen niche with distinct triggers (essentiality, synthetic lethality, dropout/positive-selection, resistance); minimal overlap risk with unrelated skills.	5 / 5
	Total	19 / 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: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-crispr-screen-analysis/SKILL.md
Commit: 1b02920

Reviewed: 1 day 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.