tooluniverse-immunotherapy-response-prediction

Predict patient response to immune checkpoint inhibitors (ICIs) using multi-biomarker integration. Given a cancer type, somatic mutations, and optional biomarkers (TMB, PD-L1, MSI status), performs systematic analysis across 11 phases covering TMB classification, neoantigen burden estimation, MSI/MMR assessment, PD-L1 evaluation, immune microenvironment profiling, mutation-based resistance/sensitivity prediction, clinical evidence retrieval, and multi-biomarker score integration. Generates a quantitative ICI Response Score (0-100), response likelihood tier, specific ICI drug recommendations with evidence, resistance risk factors, and a monitoring plan. Use when oncologists ask about immunotherapy eligibility, checkpoint inhibitor selection, or biomarker-guided ICI treatment decisions.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

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

A highly actionable, clearly sequenced 11-phase workflow with executable tool calls, scoring formulas, and a full report template. Its main weakness is token efficiency and progressive disclosure: a large monolithic body restate reference knowledge Claude already has instead of splitting it into referenced files.

Suggestions

Move the large reference tables (Phase 0 tool-parameter reference, ICI drug profiles, ChEMBL/EFO ID lookups, cancer baseline ORR tables) into reference files under ./references/ and link to them from SKILL.md to improve progressive disclosure and reduce inline tokens.

Trim hardcoded domain knowledge Claude already knows (e.g., what each ICI targets, standard FDA indications) and keep only the non-obvious tool quirks, gotchas, and cancer-specific thresholds that justify the skill's existence.

Add an explicit validate-then-fix feedback loop around the report-writing step (e.g., re-run the completeness checklist and fix missing sections before declaring the report final) to strengthen the verification checkpoint.

Dimension	Reasoning	Score
Conciseness	The 866-line body is mostly efficient and the verified tool-parameter table earns its place, but large hardcoded reference tables (ICI drug profiles, ChEMBL IDs, EFO IDs, cancer baseline ORRs) restate knowledge Claude already has and could be tightened or moved out.	2 / 3
Actionability	Provides concrete, copy-paste-ready tool-call snippets, explicit scoring formulas with point values, cancer-specific thresholds, and a complete report template — fully executable guidance.	3 / 3
Workflow Clarity	An 11-phase pipeline is clearly sequenced, anchored by a 'report-first' principle and a final completeness checklist that acts as an explicit verification checkpoint before finalizing.	3 / 3
Progressive Disclosure	Sections are well organized, but the skill is a monolithic 866-line file with no bundle references; reference data (tool params, drug tables, report template) that should be split into separate files is kept inline.	2 / 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.

A strong, third-person description that concretely names the skill's actions and outputs and pairs them with an explicit, natural-language trigger clause for oncology decision support. It is distinguishable from other skills and free of vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('TMB classification, neoantigen burden estimation, MSI/MMR assessment, PD-L1 evaluation, immune microenvironment profiling, mutation-based resistance/sensitivity prediction, clinical evidence retrieval, and multi-biomarker score integration') and concrete outputs (ICI Response Score 0-100, drug recommendations, monitoring plan), in third person.	3 / 3
Completeness	Explicitly answers both what (predicts response, generates score/recommendations/monitoring plan) and when via an explicit 'Use when oncologists ask about...' clause.	3 / 3
Trigger Term Quality	Natural domain terms an oncologist would say appear in the trigger clause: 'immunotherapy eligibility, checkpoint inhibitor selection, or biomarker-guided ICI treatment decisions', plus 'immune checkpoint inhibitors' and 'ICI'.	3 / 3
Distinctiveness Conflict Risk	Clear niche (ICI/immunotherapy response prediction via multi-biomarker integration) with distinct clinical triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (866 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/med/tooluniverse-immunotherapy-response-prediction/SKILL.md
Commit: df37802

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.