in-silico-perturbation-oracle
Virtual gene knockout simulation using foundation models to predict transcriptional changes
52
33%
Does it follow best practices?
Impact
80%
2.35xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Data analysis/in-silico-perturbation-oracle/SKILL.mdQuality
Discovery
40%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 description identifies a specialized bioinformatics capability but suffers from missing explicit trigger guidance and limited natural language keywords. While the technical domain is clear and distinctive, the lack of a 'Use when...' clause and absence of common user phrasings significantly limits Claude's ability to reliably select this skill when appropriate.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user asks about gene knockout effects, perturbation analysis, or predicting gene expression changes'
Include natural language variations users might say: 'knock out genes', 'gene expression prediction', 'in silico perturbation', 'what happens if gene X is deleted'
Expand specific capabilities: mention input types (gene lists, cell types), output types (expression predictions, pathway effects), and supported model types
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (gene knockout simulation) and a specific action (predict transcriptional changes), but lacks comprehensive detail about what concrete operations are performed (e.g., input/output formats, specific analysis types). | 2 / 3 |
Completeness | Describes what the skill does (simulate gene knockouts, predict transcriptional changes) but completely lacks any 'Use when...' clause or explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Contains relevant technical terms like 'gene knockout', 'transcriptional changes', and 'foundation models', but these are specialized jargon. Missing common variations users might say like 'knock out genes', 'gene expression prediction', 'in silico knockout', or 'perturbation analysis'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specialized niche in computational biology/bioinformatics. The combination of 'virtual gene knockout', 'foundation models', and 'transcriptional changes' is distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill content is heavily padded with boilerplate sections (risk assessment, security checklists, lifecycle status, citations) that consume tokens without teaching Claude anything actionable. While it provides some code examples, the disclaimer undermines their utility, and the lack of progressive disclosure creates an overwhelming document that buries the actual instructions.
Suggestions
Remove boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Citation) that don't provide actionable guidance for performing the task
Move detailed reference content (architecture, validation benchmarks, cell type mappings, roadmap) to separate linked files and keep SKILL.md as a concise overview
Add explicit validation steps integrated into the workflow (e.g., 'After running prediction, verify output with: oracle.validate_results()')
Either provide complete working code with actual model integration or clearly scope the skill to just the API interface patterns without implying full functionality
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive boilerplate (risk assessment tables, security checklists, lifecycle status, citation blocks) that add no instructional value. The overview explains what foundation models are and includes marketing-style feature tables instead of actionable guidance. | 1 / 3 |
Actionability | Provides code examples for CLI and Python API usage that appear executable, but the disclaimer notes actual predictions require external model integration not shown. The code is illustrative rather than truly copy-paste ready without significant setup not documented. | 2 / 3 |
Workflow Clarity | Steps for running predictions are listed but lack validation checkpoints. No explicit feedback loops for error recovery. The 'Quality Control' section mentions checks but doesn't integrate them into a clear workflow sequence. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files for detailed content. Everything is inline including architecture diagrams, validation benchmarks, roadmaps, and citation blocks that should be in separate reference documents. | 1 / 3 |
Total | 6 / 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.