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.

65

Quality

78%

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

The canonical home for this skill is tooluniverse-crispr-screen-analysis in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

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.

A well-structured, mostly actionable CRISPR-screen workflow with explicit phases, thresholds, and validation checkpoints, but it carries some redundant background prose and its progressive-disclosure is undermined by five missing referenced files.

Suggestions

Trim the Overview/intro paragraph and the 'Domain Reasoning' background; keep only skill-specific thresholds and tool conventions to tighten conciseness.

Either create the five missing See Also files (ANALYSIS_DETAILS.md, USE_CASES.md, EXAMPLES.md, QUICK_START.md, FALLBACK_PATCH.md) or remove the dead links so navigation is not broken.

Define or point to the undefined Quick Start helpers (load_sgrna_counts, filter_low_count_sgrnas, mageck_gene_scoring, etc.) so the example code is fully executable rather than calling opaque functions.

DimensionReasoningScore

Conciseness

Mostly efficient and skill-specific (tool names, thresholds, conventions), but the Overview paragraph and intro restate scope already covered by RULE ZERO and the phase list, and the 'Domain Reasoning' section is discursive background Claude largely knows.

3 / 5

Actionability

Quick Start gives concrete Python, tool calls are paired with specific parameters, and thresholds (LFC < -1.0, delta-LFC > 1.5, p < 0.001) are explicit; minor gaps come from helper functions (load_sgrna_counts, mageck_gene_scoring) being called but never defined.

4 / 5

Workflow Clarity

The 8-phase workflow is clearly sequenced, RULE ZERO is an explicit validation checkpoint, QC phases and the evidence-grading table provide checkpoints; the batch-analysis validate->fix->retry loop on the core re-analysis is only implicit rather than a hard gate.

4 / 5

Progressive Disclosure

Structure and a 'See Also' section signal one-level-deep references, and the scripts/ gene-set bundle is real and correctly referenced, but five of the six See Also files (ANALYSIS_DETAILS.md, USE_CASES.md, EXAMPLES.md, QUICK_START.md, FALLBACK_PATCH.md) do not exist in the bundle, breaking navigation.

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, specific description with concrete actions and an explicit 'Use for ...' trigger clause covering multiple screen types. It is clearly distinct from other skills; only minor synonym coverage in trigger terms keeps it from being perfect.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'MAGeCK gene-level scores, sgRNA count QC, replicate correlation, hit prioritization, and pathway GSEA' — giving comprehensive coverage of what the skill performs.

5 / 5

Completeness

Explicitly answers both 'what' (the listed analysis actions) and 'when' via a clear 'Use for ...' trigger clause enumerating concrete scenarios.

5 / 5

Trigger Term Quality

Strong natural terms users would say ('CRISPR-Cas9 genetic screens', 'genome-wide essentiality screens', 'synthetic-lethality', 'resistance-screen'), but the list leans technical and is missing a few common lay synonyms/screen-type variations.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (CRISPR screen analysis) with distinct triggers and screen-type qualifiers, minimizing overlap with other skills.

5 / 5

Total

19

/

20

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.