CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tooluniverse-functional-genomics-screens

Interpret hits from CRISPR-KO/CRISPRi/shRNA screens by integrating DepMap essentiality, gnomAD constraint scores, pathway context (Reactome, STRING), druggability (DGIdb), and clinical evidence (CIViC, COSMIC). Use for screen-hit prioritization, essentiality ranking, and turning a list of screen hits into a prioritized target shortlist.

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 dense, expert-facing skill body: executable tool calls with parameter-level gotchas, a concrete scoring rubric, and edge-case fallbacks, organized into a clear phase pipeline. The main gaps are a duplicated Chronos threshold note, missing call syntax for two phases, and an unverified cross-skill script dependency standing in for a proper bundle reference.

Suggestions

Consolidate the Chronos threshold guidance, which currently appears twice in Phase 1 (in the Classification line and again in the DepMap per-cell-line paragraph), into a single statement.

Add copy-paste call syntax for Phase 0 (Input Processing) and Phase 5 (Literature/PubMed) to match the executable detail given for Phases 1-4.

Clarify the cross-skill dependency on 'tooluniverse-cell-line-profiling/scripts/depmap_gene_dependency.py' — either verify it exists when this skill is installed, or bundle a local fallback script under scripts/ — and add explicit per-phase validation checkpoints (e.g., require hits to pass Phase 1 validation before Phase 2 enrichment).

DimensionReasoningScore

Conciseness

Lean and dense throughout — tool signatures, thresholds, and edge cases with zero concept explanations — earning a 5, except the Chronos threshold guidance is stated twice ('Chronos < -0.5 = likely essential, < -1.0 = strongly essential' and again 'Chronos < -0.5 ≈ dependency, < -1.0 strongly essential' two paragraphs later). This minor duplication places it at the 4 anchor: efficient with a small trim opportunity.

4 / 5

Actionability

Tool calls are copy-paste ready with exact parameter quirks (STRING 'carriage-return separated', 'civic_search_evidence_items(molecular_profile=gene) -- NOT query', bash examples for the DepMap script) plus a concrete 0-18 scoring table. Not 5: Phase 0 (Input Processing) and Phase 5 (Literature) give no call syntax, so specific examples do not fully cover the common cases.

4 / 5

Workflow Clarity

A clearly sequenced 7-phase pipeline with error-recovery paths ('gnomAD overloaded: Retry once, proceed without, note gap'; 'Gene not in DepMap: Fall back to gnomAD + UniProt') and a tiered scoring checklist. Not 5: there are no explicit per-phase validation checkpoints before proceeding (e.g., confirming hits passed Phase 1 validation before pathway enrichment) — checkpoints are implicit in the guiding principles.

4 / 5

Progressive Disclosure

Good section structure (principles, phases, edge cases, limitations) with everything inline and appropriate for a ~100-line single-file skill; no bundle files exist to navigate. Not 5: the only file pointer is an unverified cross-skill dependency ('tooluniverse-cell-line-profiling/scripts/depmap_gene_dependency.py', not present in this bundle), and the dense tool-API syntax is reference material that could be split out.

4 / 5

Total

16

/

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: concrete capabilities, an explicit 'Use when' clause with natural trigger phrases, and a well-delineated niche backed by named databases. The only weakness is slightly thin synonym coverage for how users refer to screens (pooled screen, functional-genomics screen, hit list).

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'integrating DepMap essentiality, gnomAD constraint scores, pathway context (Reactome, STRING), druggability (DGIdb), and clinical evidence (CIViC, COSMIC)' — with comprehensive coverage of the pipeline's capabilities. Not 4: there are no minor gaps in coverage; each clause names a distinct, concrete capability.

5 / 5

Completeness

Explicitly answers both: what ('Interpret hits from CRISPR-KO/CRISPRi/shRNA screens by integrating DepMap essentiality, gnomAD constraint scores, pathway context...') and when ('Use for screen-hit prioritization, essentiality ranking, and turning a list of screen hits into a prioritized target shortlist'). Matches the score-5 anchor with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural-term coverage: 'CRISPR-KO/CRISPRi/shRNA screens', 'screen hits', 'screen-hit prioritization', 'essentiality ranking', 'prioritized target shortlist'. Not 5: common variations users would say — 'pooled screen', 'functional genomics screen', 'hit list', 'MAGeCK' — are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche — genetic screen hit interpretation — anchored by named resources (DepMap, gnomAD, Reactome, STRING, DGIdb, CIViC, COSMIC), giving distinct triggers and minimal conflict risk with other skills. Not 4: the specificity of the trigger vocabulary leaves virtually no overlap risk.

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

mims-harvard/ToolUniverse

Path

plugin/skills/tooluniverse-functional-genomics-screens/SKILL.md

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.