CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, domain-rich body with concrete thresholds, tool parameters, and a well-sequenced eight-phase workflow, plus correctly bundled reference gene sets. Its main weaknesses are redundancy with the description, a Quick Start whose helper functions are undefined, dead 'See Also' links, and the absence of explicit inter-phase validation feedback loops.

Suggestions

Tighten conciseness: drop the restated intro line and the 'CRISPR screens enable genome-wide functional genomics…' concept sentence, and collapse the Overview phase list into the Core Workflow to avoid duplicating the eight phases.

Make the Quick Start executable: either define or import the helper functions it calls (load_sgrna_counts, mageck_gene_scoring, enrich_essential_genes, prioritize_drug_targets, generate_crispr_report), or label them explicitly as illustrative pseudocode and point to where the real implementations live.

Resolve progressive disclosure: create the referenced 'See Also' files or remove the dead links, and consider moving the detailed per-phase code and tool-param tables into ANALYSIS_DETAILS.md so SKILL.md stays an overview.

DimensionReasoningScore

Conciseness

Mostly efficient domain content, but 'Comprehensive skill for analyzing CRISPR-Cas9 genetic screens…' restates the description, 'CRISPR screens enable genome-wide functional genomics…' explains a concept Claude knows, and the Overview re-lists the eight phases that are re-detailed in Core Workflow.

2 / 3

Actionability

Concrete thresholds and tool params (LFC < -1.0, BF > 5, 50/30/20 weights, real reference_gene_sets import) are actionable, but the Quick Start calls undefined helper functions (load_sgrna_counts, mageck_gene_scoring, …) that are not importable, so the headline example is not copy-paste ready.

2 / 3

Workflow Clarity

A clear eight-phase sequence exists with checkpoints (RULE ZERO pre-check, Phase 2 QC, recovery_rate, evidence grading), but there are no explicit inter-phase 'validate → fix → retry' feedback loops tying the phases together.

2 / 3

Progressive Disclosure

Real one-level-deep script references exist and are correctly linked (scripts/reference_gene_sets.py, CEGv2/NEGv1 files verified present), but the five 'See Also' files (ANALYSIS_DETAILS.md, USE_CASES.md, EXAMPLES.md, QUICK_START.md, FALLBACK_PATCH.md) do not exist in the bundle, and the core workflow remains largely inline.

2 / 3

Total

8

/

12

Passed

Description

100%

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 states concrete capabilities and pairs them with an explicit 'Use for' trigger clause covering the main screen types. It is specific, complete, and clearly distinct from other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'MAGeCK gene-level scores, sgRNA count QC, replicate correlation, hit prioritization, and pathway GSEA' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Answers both what ('Analyze CRISPR-Cas9 genetic screens — …') and when via an explicit 'Use for …' trigger clause, satisfying the top anchor for completeness.

3 / 3

Trigger Term Quality

'Use for genome-wide essentiality screens, synthetic-lethality discovery, dropout vs positive-selection screen analysis, target identification, and resistance-screen interpretation' gives natural domain terms a CRISPR researcher would actually say, with good coverage of common phrasings.

3 / 3

Distinctiveness Conflict Risk

The CRISPR-screen niche and its specific triggers (essentiality screens, synthetic lethality, resistance screens) are clearly distinct and unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mims-harvard/ToolUniverse
Reviewed

Table of Contents

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.