CtrlK
BlogDocsLog inGet started
Tessl Logo

depmap

Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use for identifying cancer-specific vulnerabilities, synthetic lethal interactions, and validating oncology drug targets.

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 ./skills/depmap/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.

The body is information-rich and domain-specific with concrete analysis code, but is weakened by a non-executable placeholder URL, missing workflow validation checkpoints, and an orphaned reference file that is never surfaced from the main document.

Suggestions

Replace the literal "..." figshare placeholder URL with a concrete, working download link so the download code is executable as written.

Add explicit validation/verification checkpoints to the workflows (e.g., confirm cell-line alignment, check n before statistical tests, apply FDR correction and flag when it changes significance).

Link to references/dependency_analysis.md from the body (e.g., under Core Concepts) so the existing reference file is discoverable rather than orphaned.

DimensionReasoningScore

Conciseness

The ~290-line body is mostly operational domain content (thresholds, file names, code) but includes explanation Claude largely knows (Overview prose, "Co-essential genes often share biological complexes or pathways"), so it is efficient overall yet could be tightened.

2 / 3

Actionability

Substantial concrete pandas code is provided, but a non-executable placeholder URL ("figshare.com/ndownloader/files/...") and live API endpoints ("/gene", "/data/gene_dependency") of uncertain accuracy prevent full copy-paste readiness.

2 / 3

Workflow Clarity

Three workflows are sequenced as numbered steps, but none include validation or verification checkpoints for batch/genome-wide operations, which the rubric caps at 2.

2 / 3

Progressive Disclosure

A references/dependency_analysis.md bundle exists but is never linked from the body, and the ~290-line body inlines API and file-reference tables that could be split out, so structure is present but the reference is not signaled.

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.

The description is concise, third-person, and explicitly covers both capability and trigger conditions with domain-appropriate natural terms, scoring at the top of the scale across all dimensions.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("gene dependency scores (CRISPR Chronos)", "drug sensitivity data", "gene effect profiles") in third person ("Query"), matching the multi-action anchor rather than the domain-only level 2.

3 / 3

Completeness

Explicitly answers both what ("Query the Cancer Dependency Map... for...") and when ("Use for identifying cancer-specific vulnerabilities..."), with an explicit "Use for" trigger clause rather than an implied one.

3 / 3

Trigger Term Quality

Includes natural domain terms a genomics user would say ("DepMap", "CRISPR Chronos", "drug sensitivity", "synthetic lethal interactions", "oncology drug targets") with good coverage, not just technical jargon.

3 / 3

Distinctiveness Conflict Risk

A very specific niche (DepMap CRISPR cancer dependency data, synthetic lethality) with distinct triggers that would not plausibly 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
K-Dense-AI/scientific-agent-skills
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.