tooluniverse-immunotherapy-response-prediction

Predict patient response to immune checkpoint inhibitors (ICIs) by integrating tumor mutational burden (TMB), microsatellite instability (MSI), PD-L1 expression, HLA status, and immune-related gene expression. Outputs ICI Response Score with drug-specific recommendations and resistance-risk assessment. Use for melanoma/NSCLC/RCC immunotherapy decision support.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugin/skills/tooluniverse-immunotherapy-response-prediction/SKILL.md

Quality

Content

66%Weight 40%Scale 1-5

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

A well-structured, largely actionable workflow with a clear 11-phase pipeline and transparent scoring. Its main weakness is progressive disclosure: four referenced bundle files are cited but do not exist, so the navigation signals point to missing material.

Suggestions

Create the four referenced bundle files (INPUT_REFERENCE.md, SCORING_TABLES.md, REPORT_TEMPLATE.md, TOOLS_REFERENCE.md) under references/ so the signaled detail is actually reachable, or inline the essential content and remove the links.

Trim the 'Reasoning Before Searching' biological explanations (e.g., the neoantigen/T-cell paragraph) to thresholds and rules only, since Claude already knows the underlying biology.

Add an explicit validation checkpoint after each phase (e.g., 'Verify all required biomarker scores are populated before Phase 10 integration') to convert the report-first principle into concrete feedback loops.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely actionable with minimal padding, though the 'Reasoning Before Searching' section re-explains biology Claude already knows (e.g., 'More somatic mutations produce more neoantigens, which are recognized by T cells') and could be trimmed.	4 / 5
Actionability	Concrete tool calls with named parameters and a transparent scoring formula (TMB 5-30, MSI 5-25, penalties STK11 -10) are provided throughout, with only minor gaps such as the neoantigen estimate being a rough heuristic rather than validated code.	4 / 5
Workflow Clarity	The 11-phase workflow is clearly sequenced with per-phase numbered steps and explicit 'LOOK UP DON'T GUESS' verification guidance, but the phases lack explicit validation checkpoints confirming each phase's output before proceeding and the report-first loop is stated as a principle rather than wired into the sequence.	4 / 5
Progressive Disclosure	The body references INPUT_REFERENCE.md, SCORING_TABLES.md, REPORT_TEMPLATE.md, and TOOLS_REFERENCE.md, but none of these files exist in references/, scripts/, or assets/ — the references are dangling and the promised detail is unreachable, leaving a structured-looking but effectively broken disclosure hierarchy.	2 / 5
	Total	14 / 20 Passed

Description

88%Weight 40%Scale 1-5

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, specific description that clearly states both capability and use context with concrete biomarkers, output artifact, and named cancer types. Trigger phrasing is explicit but slightly more clinical than conversational.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'integrating tumor mutational burden (TMB), microsatellite instability (MSI), PD-L1 expression, HLA status, and immune-related gene expression' and 'Outputs ICI Response Score with drug-specific recommendations and resistance-risk assessment' — giving comprehensive, specific coverage rather than generic verbs.	5 / 5
Completeness	It answers 'what' explicitly ('Predict patient response... Outputs ICI Response Score with drug-specific recommendations and resistance-risk assessment') and 'when' explicitly ('Use for melanoma/NSCLC/RCC immunotherapy decision support'), satisfying both halves with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Natural clinical terms are present ('immunotherapy', 'immune checkpoint inhibitors', 'melanoma/NSCLC/RCC', 'ICI Response Score'), but it leans on technical jargon and omits the plain phrasings a clinician might actually say ('will this patient respond to immunotherapy?', 'checkpoint inhibitor').	4 / 5
Distinctiveness Conflict Risk	The niche is narrow and domain-specific — ICI response prediction across named biomarkers and three named cancer types — making it highly unlikely to trigger for unrelated skills.	5 / 5
	Total	19 / 20 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
relative_links	Relative link issues: 7 missing	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-immunotherapy-response-prediction/SKILL.md
Commit: 1b02920

Reviewed: 1 day 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.