crispr-screen-analyzer
Process CRISPR screening data to identify essential genes and hit candidates. Performs quality control, log fold change calculation, z-score-based sgRNA scoring, and hit calling for pooled CRISPR screens including viability, drug resistance, and synthetic lethality studies.
78
Quality
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Data analysis/crispr-screen-analyzer/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, technically specific description that clearly defines the domain (CRISPR screening) and lists concrete analytical capabilities. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The domain-specific terminology provides excellent distinctiveness.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user mentions CRISPR screens, sgRNA analysis, gene essentiality, or pooled screening data.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'quality control, log fold change calculation, z-score-based sgRNA scoring, and hit calling' along with specific study types (viability, drug resistance, synthetic lethality). | 3 / 3 |
Completeness | Clearly answers 'what does this do' with detailed capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The when is only implied through the domain context. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'CRISPR screening', 'essential genes', 'hit candidates', 'sgRNA', 'pooled CRISPR screens', 'viability', 'drug resistance', 'synthetic lethality' - comprehensive coverage of domain terminology. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specialized niche with distinct triggers like 'CRISPR screening', 'sgRNA scoring', 'pooled CRISPR screens' - very unlikely to conflict with other skills due to the specific scientific domain. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides strong actionable guidance with executable commands, clear parameter documentation, and specific QC thresholds. However, the workflow section is generic rather than domain-specific, and there's notable redundancy between output-related sections. The skill would benefit from a more explicit analytical workflow with validation checkpoints between QC, normalization, and hit-calling steps.
Suggestions
Replace the generic 5-step workflow with a CRISPR-specific analytical sequence: (1) Load and validate inputs → (2) Run QC checks → (3) If QC passes, calculate LFC → (4) Score sgRNAs → (5) Call hits with FDR correction, with explicit validation gates between steps.
Consolidate 'Output Requirements', 'Response Template', and 'Stress-Case Output Structure' into a single section to reduce redundancy.
Add a validation checkpoint after QC assessment that explicitly gates whether to proceed with differential analysis (e.g., 'If Gini > 0.3 or correlation < 0.7, stop and report QC failure before LFC calculation').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains useful information but includes some redundancy (e.g., the 'Output Requirements' and 'Response Template' sections overlap significantly, and the 'Stress-Case Output Structure' duplicates guidance). The workflow section is generic and could be tightened. | 2 / 3 |
Actionability | Provides fully executable commands with concrete examples, clear parameter tables with types and defaults, specific QC thresholds with action items, and copy-paste ready usage examples for both QC-only and full analysis modes. | 3 / 3 |
Workflow Clarity | The workflow section is too abstract and generic (not specific to CRISPR analysis). While there's a good fallback template and error handling section, the actual analytical workflow (QC → LFC → scoring → hit calling) is not explicitly sequenced with validation checkpoints between steps. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections and tables, but everything is inline in one file. References to upstream/downstream tools are mentioned but not linked. Some sections (Output Requirements, Response Template, Stress-Case Output Structure) could be consolidated or moved to a separate reference file. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
ca9aaa4
- 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.