CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

86%

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

72%

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

The body is highly actionable and well-organized as a self-contained single file, with concrete tool calls and a scoring rubric. It loses points on conciseness (intro/Chronos duplication) and workflow clarity (no explicit validation checkpoints for a batch operation, and a Phase 5 detail gap).

Suggestions

Drop or condense the opening paragraph that restates the frontmatter description, and remove the duplicated Chronos threshold line so the essentiality cutoffs appear once.

Add explicit validation checkpoints between phases (e.g., confirm DepMap/STRING results are non-empty before scoring, and a verify→fix→retry loop for the per-cell-line Chronos fetch) since this is a batch operation on hit lists.

Add a brief Phase 5 (Literature) detail section or remove it from the workflow diagram so the documented sequence is complete.

DimensionReasoningScore

Conciseness

Mostly lean and information-dense (terse tool signatures, scoring table, edge cases), but the opening paragraph nearly duplicates the frontmatter description and the Chronos thresholds ("< -0.5", "< -1.0") appear twice, so it could be tightened rather than scoring the every-token-earns-its-place anchor.

2 / 3

Actionability

Provides exact, executable tool calls with parameter signatures (e.g. `STRING_get_network(identifiers="GENE1\rGENE2\rGENE3", species=9606)`, `civic_search_evidence_items(molecular_profile=gene)` with the "NOT query" caveat) and copy-paste bash commands, fully matching the executable/copy-paste-ready anchor.

3 / 3

Workflow Clarity

The Phase 0–6 sequence is clearly laid out with a diagram and per-phase detail, but for a batch hit-list operation there are no explicit validate→fix→retry checkpoints in the main flow, and Phase 5 (Literature) appears in the diagram yet is absent from Phase Details, leaving the sequence with implicit/missing gates.

2 / 3

Progressive Disclosure

A single well-organized file with clear sections (Workflow, Phase Details, Edge Cases, Limitations) and no nested references; the one external pointer (the cell-line-profiling depmap script) is clearly signaled with usage examples and a fallback, giving easy navigation.

3 / 3

Total

10

/

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.

The description is specific, third-person, and explicitly states both capability and use-cases with a clear "Use for" trigger. It carves out a distinctive niche with natural domain keywords. No changes needed.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "integrating DepMap essentiality, gnomAD constraint scores, pathway context..., druggability..., and clinical evidence" plus "screen-hit prioritization, essentiality ranking, and turning a list of screen hits into a prioritized target shortlist" — matching the multiple-specific-actions anchor; it is comprehensive, not partial.

3 / 3

Completeness

Answers both what ("Interpret hits... by integrating...") and when via an explicit "Use for screen-hit prioritization, essentiality ranking, and turning a list of screen hits into a prioritized target shortlist" trigger clause, satisfying the explicit-trigger anchor.

3 / 3

Trigger Term Quality

Covers natural domain terms a user would actually say — "CRISPR-KO/CRISPRi/shRNA screens", "DepMap", "gnomAD", "screen-hit prioritization", "essentiality ranking" — with good coverage of variations (three screen modalities); not jargon-only or generic.

3 / 3

Distinctiveness Conflict Risk

A clearly bounded niche (genetic-screen hit interpretation across five named evidence layers) with distinct triggers unlikely to fire for unrelated skills; far above the generic-overlap anchor.

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.