CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is tooluniverse-immunotherapy-response-prediction in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

71%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-engineered operational skill: lean, cancer-specific, and packed with concrete tool calls, point-valued scoring, and an explicit phase sequence with parameter-verification checkpoints. Its one material defect is that every referenced bundle file is missing, so the deferred detail the workflow depends on (scoring tables, tool parameter reference, report template) cannot actually be loaded.

Suggestions

progressive_disclosure: Ship the four referenced bundle files (INPUT_REFERENCE.md, SCORING_TABLES.md, REPORT_TEMPLATE.md, TOOLS_REFERENCE.md) in the skill directory — every phase links to them, and the scoring tables and tool parameter tables they should contain are load-bearing for Phases 1, 2, 5, 8, and 11.

progressive_disclosure: If the bundle files cannot be provided, inline the minimal essentials (cancer-type ORR baselines, PD-L1 TPS/CPS cutoffs, and the ICI drug profile table) into SKILL.md and drop the dangling links.

workflow_clarity: Add explicit error-recovery feedback loops for tool failures — e.g., what to do when a gene ID cannot be resolved via MyGene_query_genes or when FDA/civic lookups return no evidence — so the 11-phase sequence degrades gracefully instead of implicitly assuming every call succeeds.

DimensionReasoningScore

Conciseness

The body is dense and operational — point-valued rules ('STK11 (-10), PTEN (-5), JAK1/2 (-10 each), B2M (-15)'), parameter gotchas ('use `query` (NOT `q`)'), and thresholds — with little generic explanation. Minor over-explanation remains: the 'Reasoning Before Searching' section re-states neoantigen biology Claude already knows, and the 9-item 'KEY PRINCIPLES' list repeats rules stated later in the phases. Efficient with minor trimming possible, matching anchor 4 rather than the fully lean anchor 5.

4 / 5

Actionability

Mostly executable guidance: concrete tool calls with parameters ('fda_pharmacogenomic_biomarkers(drug_name=\'pembrolizumab\')', 'HPA_get_cancer_prognostics_by_gene(gene_name=\'CD274\')'), an explicit scoring formula ('missense_count * 0.3 + frameshift_count * 1.5'), and a fully specified Phase 10 score integration. Minor gaps keep it below anchor 5: several tool calls lack full parameter signatures (deferred to TOOLS_REFERENCE.md) and there is no runnable Python snippet for the score computation despite the 'COMPUTE, DON'T DESCRIBE' mandate.

4 / 5

Workflow Clarity

The 11-phase sequence is clearly ordered with explicit input requirements, a deterministic scoring integration, and checkpoints such as 'BEFORE calling ANY tool, verify parameters', 'LOOK UP DON'T GUESS', and 'Do not default to "moderate" for unknowns — flag them explicitly'. Below anchor 5 because there are no explicit error-recovery feedback loops (e.g., what to do when a tool call fails or a gene ID cannot be resolved); above anchor 3 because checkpoints are explicit rather than implicit.

4 / 5

Progressive Disclosure

The structure pattern is good — overview phases each pointing to one-level-deep references at the point of need ('See [SCORING_TABLES.md](SCORING_TABLES.md)', '[INPUT_REFERENCE.md](INPUT_REFERENCE.md)', '[TOOLS_REFERENCE.md](TOOLS_REFERENCE.md)', '[REPORT_TEMPLATE.md](REPORT_TEMPLATE.md)') — but none of these four referenced files exist in the bundle (no references/, scripts/, or assets/ directories are present). Navigation is clearly signaled yet broken at runtime, and the deferred content (scoring tables, tool parameters) is inaccessible, which is a larger gap than anchor 4's 'minor organization gaps'.

3 / 5

Total

15

/

20

Passed

Description

83%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 description: third-person voice, specific biomarker inputs and named outputs, and an explicit 'Use for' clause with cancer-type scoping. The main gaps are trigger phrasing that mirrors what a clinician would actually say (e.g., drug names, 'will this patient respond') and a slightly terse when-clause.

DimensionReasoningScore

Specificity

Multiple concrete actions are listed: 'integrating tumor mutational burden (TMB), microsatellite instability (MSI), PD-L1 expression, HLA status, and immune-related gene expression' plus concrete outputs ('ICI Response Score', 'drug-specific recommendations', 'resistance-risk assessment'). Coverage of the domain's capabilities is comprehensive, matching the anchor-5 example's breadth; not score 4 because no meaningful actions are missing.

5 / 5

Completeness

Both are present: a clear 'what' ('Predict patient response... Outputs ICI Response Score with drug-specific recommendations and resistance-risk assessment') and an explicit 'when' ('Use for melanoma/NSCLC/RCC immunotherapy decision support'). Not score 5 because the 'when' clause names use contexts rather than concrete user trigger phrases, which anchor 5 requires; clearly above anchor 3 since the 'when' is explicit, not merely implied.

4 / 5

Trigger Term Quality

Good keyword coverage including natural clinical terms ('immune checkpoint inhibitors', 'immunotherapy', 'PD-L1', 'melanoma/NSCLC/RCC') with abbreviations spelled out. A few natural terms users would say are missing — no drug names (pembrolizumab, nivolumab) and no phrasings like 'respond to immunotherapy' — so it falls between anchor 4 and 5, closer to 4.

4 / 5

Distinctiveness Conflict Risk

A clear niche — quantitative ICI response prediction from a named biomarker panel with a named output score — with cancer types (melanoma/NSCLC/RCC) that further bound it. Distinct triggers and minimal overlap with adjacent oncology or general prediction skills.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 7 missing

Warning

Total

15

/

16

Passed

Repository

mims-harvard/ToolUniverse

Path

plugins/tooluniverse/skills/tooluniverse-immunotherapy-response-prediction/SKILL.md

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.