Source: https://github.com/aipoch/medical-research-skills

Clinical Trial Matching for Precision Medicine

Transform patient molecular profiles and clinical characteristics into prioritized clinical trial recommendations. Searches ClinicalTrials.gov and cross-references with molecular databases (CIViC, OpenTargets, ChEMBL, FDA) to produce evidence-graded, scored trial matches.

KEY PRINCIPLES:

1. Report-first approach - Create report file FIRST, then populate progressively
2. Patient-centric - Every recommendation considers the individual patient's profile
3. Molecular-first matching - Prioritize trials targeting patient's specific biomarkers
4. Evidence-graded - Every recommendation has an evidence tier (T1-T4)
5. Quantitative scoring - Trial Match Score (0-100) for every trial
6. Eligibility-aware - Parse and evaluate inclusion/exclusion criteria
7. Actionable output - Clear next steps, contact info, enrollment status
8. Source-referenced - Every statement cites the tool/database source
9. Completeness checklist - Mandatory section showing analysis coverage
10. English-first queries - Always use English terms in tool calls. Respond in user's language

---

When to Use

Apply when user asks:

• "What clinical trials are available for my NSCLC with EGFR L858R?"
• "Patient has BRAF V600E melanoma, failed ipilimumab - what trials?"
• "Find basket trials for NTRK fusion"
• "Breast cancer with HER2 amplification, post-CDK4/6 inhibitor trials"
• "KRAS G12C colorectal cancer clinical trials"
• "Immunotherapy trials for TMB-high solid tumors"
• "Clinical trials near Boston for lung cancer"
• "What are my options after failing osimertinib for EGFR+ NSCLC?"

NOT for (use other skills instead):

• Single variant interpretation without trial focus -> Use tooluniverse-cancer-variant-interpretation
• Drug safety profiling -> Use tooluniverse-adverse-event-detection
• Target validation -> Use tooluniverse-drug-target-validation
• General disease research -> Use tooluniverse-disease-research

---

Input Parsing

Required Input

• Disease/cancer type: Free-text disease name (e.g., "non-small cell lung cancer", "melanoma")

Strongly Recommended

• Molecular alterations: One or more biomarkers (e.g., "EGFR L858R", "KRAS G12C", "PD-L1 50%", "TMB-high")
• Stage/grade: Disease stage (e.g., "Stage IV", "metastatic", "locally advanced")
• Prior treatments: Previous therapies and outcomes (e.g., "failed platinum chemotherapy", "progressed on osimertinib")

Optional

• Performance status: ECOG or Karnofsky score (e.g., "ECOG 0-1")
• Geographic location: City/state for proximity filtering (e.g., "Boston, MA")
• Trial phase preference: I, II, III, IV, or "any"
• Intervention type: drug, biological, device, etc.
• Recruiting status preference: recruiting, not yet recruiting, active

Biomarker Parsing Quick Reference

Gene Symbol Normalization

Detailed parsing rules and regex patterns: see references/parsing_and_validation.md

---

Workflow Overview

Detailed phase execution code and tool call examples: see references/phases_detail.md

---

Trial Match Score (0-100)

Score Components

Recommendation Tiers

Detailed scoring rules, evidence tier definitions, and matching algorithms: see references/scoring_and_matching.md

---

Output Format

Report file: clinical_trial_matching_[DISEASE]_[BIOMARKER]_[DATE].md

Required Sections

1. Executive Summary - Top 3 trial recommendations with scores
2. Patient Profile Summary - Standardized disease/biomarker/stage table
3. Ranked Trial Matches - Per-trial score breakdown, eligibility, evidence, locations
4. Trials by Category - Targeted/Immuno/Combination/Basket groupings
5. Additional Testing Recommendations - Biomarkers that unlock more trials
6. Alternative Options - Expanded access, off-label options
7. Evidence Grading Summary - T1-T4 counts
8. Completeness Checklist - Analysis step status tracking
9. Disclaimer - Research-only notice
10. Sources - Data source list

Full report template with markdown structure: see references/phases_detail.md#phase-10-report-synthesis

---

Edge Cases & Common Pitfalls

1. ClinicalTrials.gov query complexity - Overly specific queries often return zero results. Start simple, then combine.
2. CIViC search limitations - civic_search_variants/civic_search_evidence_items do NOT filter by query. Use civic_get_variants_by_gene with gene ID instead.
3. No matching trials - Broaden to gene-level → pathway-level → basket trials → suggest biomarker testing.
4. Rare biomarkers - Search gene-level trials, check CIViC, note rarity, suggest molecular tumor board.
5. Multiple biomarkers - Search independently + in combination, score by most actionable.
6. Conflicting eligibility - Score partial match transparently, highlight met/unmet criteria.

Full edge case handling and use patterns: see references/parsing_and_validation.md

---

Known CIViC Gene IDs

---

Input Validation

This skill accepts requests that match the documented purpose of tooluniverse-clinical-trial-matching and include enough context to complete the workflow safely.

Do not continue the workflow when the request is out of scope, missing a critical input, or would require unsupported assumptions. Instead respond:

tooluniverse-clinical-trial-matching only handles its documented workflow. Please provide the missing required inputs or switch to a more suitable skill.

References