CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-precision-oncology

Cancer treatment recommendations from molecular profile (mutations + cancer type + biomarkers) — FDA-approved + investigational therapies, resistance mechanisms, matching clinical trials, prognosis. Uses CIViC, ClinVar, OpenTargets, ClinicalTrials.gov. Use for tumor-board treatment recommendations, evidence-tiered actionability assessment, and FDA-precedent-driven therapy selection.

64

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/tooluniverse/skills/tooluniverse-precision-oncology/SKILL.md

The canonical home for this skill is tooluniverse-precision-oncology 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 dense, actionable, well-sequenced clinical workflow with concrete tool+parameter guidance and a mandatory safety gate. Its chief weakness is progressive disclosure: the six referenced detail files are missing from the bundle, breaking the navigation the overview promises.

Suggestions

Ship the six referenced files (TOOLS_REFERENCE.md, API_USAGE_PATTERNS.md, TREATMENT_ALGORITHMS.md, REPORT_TEMPLATE.md, EXAMPLES.md, CHECKLIST.md) or remove their links — dead references undermine the overview's promised navigation.

Move the full biomarker-to-drug and resistance-mapping tables into TREATMENT_ALGORITHMS.md and keep only a compact pointer in SKILL.md to remove the duplication noted in TREATMENT_ALGORITHMS.md's own description.

Add at least one inline validate->fix->retry feedback loop (e.g. OncoKB token missing -> fall back to CIViC as primary evidence) to raise workflow clarity.

DimensionReasoningScore

Conciseness

Dense and information-rich with no padding about basic biology, assuming Claude's competence; however the inline biomarker-to-drug and resistance tables duplicate content the body itself says lives in TREATMENT_ALGORITHMS.md ('cancer type mappings'), a minor instance of over-inlining that could be trimmed.

4 / 5

Actionability

Gives concrete tool names with correct parameters (e.g. civic_search_evidence_items with molecular_profile="EGFR C797S", search_clinical_trials with condition, OpenTargets ensemblId camelCase) plus specific drug regimens; full worked call sequences are deferred to EXAMPLES.md, leaving a minor gap versus copy-paste-ready completeness.

4 / 5

Workflow Clarity

A clear Phase 0–6 sequence with a diagram, per-phase tool mapping, a Phase 0 tool-verification table, and an explicit MANDATORY FAERS gate before finalizing; lacks explicit validate->fix->retry feedback loops, a minor validation gap.

4 / 5

Progressive Disclosure

The References section is well-signaled and one-level-deep across six files, but none of those referenced files (TOOLS_REFERENCE.md, API_USAGE_PATTERNS.md, TREATMENT_ALGORITHMS.md, REPORT_TEMPLATE.md, EXAMPLES.md, CHECKLIST.md) actually exist in the bundle, so navigation leads to dead links; the present scripts/gdsc_drug_response.py is unreferenced and the cross-skill pharmacology_ref.py path is also absent.

3 / 5

Total

15

/

20

Passed

Description

85%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, third-person description that clearly states both capabilities and trigger conditions for a well-defined niche. Its main weakness is a trigger clause written in clinical jargon rather than the natural language users would actually say.

Suggestions

Rewrite the 'Use for' clause with natural trigger phrases a user would say, e.g. 'Use when a user asks for treatment options for a cancer with a specific mutation, what to try after a drug stops working, or matching clinical trials'.

Add common synonyms a patient or clinician might use ('treatment options', 'what drugs for [mutation]', 'therapy for [cancer]') alongside the existing tumor-board framing.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'Cancer treatment recommendations from molecular profile', 'FDA-approved + investigational therapies', 'resistance mechanisms', 'matching clinical trials', 'prognosis' — giving comprehensive coverage of the domain, matching the score-5 anchor.

5 / 5

Completeness

Clearly answers 'what' (recommendations/therapies/resistance/trials/prognosis from molecular profile) and explicitly answers 'when' via the 'Use for ...' trigger clause with concrete use cases, satisfying the score-5 anchor.

5 / 5

Trigger Term Quality

The 'Use for tumor-board treatment recommendations, evidence-tiered actionability assessment, and FDA-precedent-driven therapy selection' clause is clinical jargon rather than the natural phrasing a user would say (e.g. 'treatment options for EGFR-mutant lung cancer'); some relevant keywords exist but common variations are missing.

3 / 5

Distinctiveness Conflict Risk

The precision-oncology-from-molecular-profile niche tied to named databases (CIViC, ClinVar, OpenTargets, ClinicalTrials.gov) is a clear, distinct niche with minimal overlap risk against other 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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 6 missing

Warning

Total

15

/

16

Passed

Repository
mims-harvard/ToolUniverse
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.