Protocol Design
animal-and-cell-validation-planner
Designs cell-based and animal-based validation plans that translate computational, omics, biomarker, genetic, or clinical findings into experimentally testable validation routes. Always use this skill whenever a user wants to move from an in silico, statistical, or clinical assoc
88100Total Score
Core Capability
92 / 100
Functional Suitability
12 / 12
Reliability
10 / 12
Performance & Context
7 / 8
Agent Usability
16 / 16
Human Usability
7 / 8
Security
12 / 12
Maintainability
11 / 12
Agent-Specific
17 / 20
Medical Task
25 / 25 Passed
90Validate a computational target (KEAP1) in lung cancer cells before animal escalation
5/5
88Validate a scRNA-seq-derived immune resistance state in patient-derived NSCLC organoids
5/5
87Drug-response validation for a repurposed compound in syngeneic mouse model
5/5
84Biomarker-linked functional validation when only limited primary cells are available
5/5
81Multi-claim validation: expression confirmation + mechanism + translational support in parallel
5/5
Veto GatesRequired pass for any deployment consideration
Skill Veto✓ All 4 gates passed
✓
Operational Stability
System remains stable across varied inputs and edge cases
PASS✓
Structural Consistency
Output structure conforms to expected skill contract format
PASS✓
Result Determinism
Equivalent inputs produce semantically equivalent outputs
PASS✓
System Security
No prompt injection, data leakage, or unsafe tool use detected
PASSResearch Veto✅ PASS — Applicable
| Dimension | Result | Detail |
|---|---|---|
| Scientific Integrity | PASS | No fabricated references, DOIs, PMIDs, statistical values, or clinical data detected. |
| Practice Boundaries | PASS | Skill explicitly prohibits fabricating model availability, species relevance, or assay feasibility |
| Methodological Ground | PASS | No methodological fallacies detected; ethical compliance requirements noted where applicable. |
| Code Usability | N/A | No bioinformatics/statistical code generated; Category 2, wet-lab design only |
Core Capability92 / 100 — 8 Categories
Functional Suitability
Full marks (12/12); no significant issues detected.
12 / 12
100%
Reliability
Explicit follow-up question mandate when resource situation is unclear; one gap: no explicit fallback when all models are unavailable
10 / 12
83%
Performance & Context
263 lines is efficient; nine reference modules add depth without bloating SKILL.md
7 / 8
88%
Agent Usability
Full marks (16/16); no significant issues detected.
16 / 16
100%
Human Usability
Description is detailed and trigger-rich; slightly technical for non-specialist users
7 / 8
88%
Security
Full marks (12/12); no significant issues detected.
12 / 12
100%
Maintainability
Nine reference modules well separated; workflow-step-template enforces consistency
11 / 12
92%
Agent-Specific
Strong trigger precision and escape hatches; composability moderate — Section K reference-integrity note could be standardized
17 / 20
85%
Core Capability Total92 / 100
Medical TaskExecution Average: 86 / 100 — Assertions: 25/25 Passed
90
Canonical
Validate a computational target (KEAP1) in lung cancer cells before animal escalation
5/5 ✓
88
Variant A
Validate a scRNA-seq-derived immune resistance state in patient-derived NSCLC organoids
5/5 ✓
87
Variant B
Drug-response validation for a repurposed compound in syngeneic mouse model
5/5 ✓
84
Edge
Biomarker-linked functional validation when only limited primary cells are available
5/5 ✓
81
Stress
Multi-claim validation: expression confirmation + mechanism + translational support in parallel
5/5 ✓
90
Canonical✅ Pass
Validate a computational target (KEAP1) in lung cancer cells before animal escalation
5/5 assertions passed.
Basic 36/40|Specialized 54/60|Total 90/100
✅A1Primary claim to validate is explicitly stated before model selection
✅A2Four workload configurations (Lite/Standard/Advanced/Publication+) are present
✅A3Animal experiments presented as conditional on cell-level rationale, not assumed available
✅A4No fabricated model availability or species relevance presented
✅A5Go/no-go criteria for escalation explicitly defined
Pass rate: 5 / 5
88
Variant A✅ Pass
Validate a scRNA-seq-derived immune resistance state in patient-derived NSCLC organoids
5/5 assertions passed.
Basic 35/40|Specialized 53/60|Total 88/100
✅A1Model system selection justified with explicit strengths and limitations
✅A2Association-support experiments distinguished from mechanism-testing experiments
✅A3Perturbation strategy and controls specified
✅A4No overstatement of translational relevance from in vitro results alone
✅A5Self-critical risk review present including false-positive source
Pass rate: 5 / 5
87
Variant B✅ Pass
Drug-response validation for a repurposed compound in syngeneic mouse model
5/5 assertions passed.
Basic 35/40|Specialized 52/60|Total 87/100
✅A1Animal model choice explicitly justified over cell-only alternative
✅A2Baseline characterization step separated from perturbation confirmation
✅A3Evidence escalation logic defined
✅A4Interpretation boundaries stated: in vivo consistency does not prove clinical translation
✅A5No fabricated effect sizes or expected phenotype penetrance
Pass rate: 5 / 5
84
Edge✅ Pass
Biomarker-linked functional validation when only limited primary cells are available
5/5 assertions passed.
Basic 34/40|Specialized 50/60|Total 84/100
✅A1Resource constraints explicitly addressed and minimum viable model recommended
✅A2Feasibility-friendly first-pass validation separated from publication-grade evidence stack
✅A3Fallback sequencing proposed when disease relevance and feasibility conflict
✅A4No assumption that animal work is automatically available
✅A5Claim boundaries explicitly stated for each experiment tier
Pass rate: 5 / 5
81
Stress✅ Pass
Multi-claim validation: expression confirmation + mechanism + translational support in parallel
5/5 assertions passed.
Basic 35/40|Specialized 46/60|Total 81/100
✅A1Multiple claims separated and primary claim identified before model selection
✅A2Expression confirmation explicitly distinguished from causal validation
✅A3Perturbation specificity boundaries stated
✅A4Rescue experiment necessity assessed for claims requiring specificity proof
✅A5Output does not imply translational relevance from model consistency alone
Pass rate: 5 / 5
Medical Task Total86 / 100
Key Strengths
- Explicit mandatory follow-up question rule when resource situation is unclear prevents false assumptions about animal availability
- Four workload configurations (Lite/Standard/Advanced/Publication+) provide practical scalability for different resource profiles
- Twelve hard rules specifically prevent the most dangerous validation design errors (expression confusion, translational overclaim, rescue omission)
- Nine well-organized reference modules covering all critical validation design components with clear section mapping