Hypothesis-Driven Experimental Design & Troubleshooting
Design rigorous experiments with anticipated failure modes and structured troubleshooting logic
What You Can Do
You can systematically design experiments from hypothesis to protocol, anticipate technical and biological failure modes before lab work begins, and troubleshoot failed assays with structured diagnostic logic. This skill helps you validate experimental logic, specify comprehensive controls (positive, negative, vehicle), define acceptance criteria and detection limits, and document decision points—ensuring your team invests reagents and time only on scientifically sound approaches.
Features
Structure your research question, predicted outcome, and testable null hypothesis before protocol design
Specify positive controls, negative controls, vehicle controls, and internal standards tailored to your assay type
Identify anticipated technical failures (instrumentation, reagent degradation, sample handling) and biological confounders before experiments start
Generate SOPs with explicit acceptance criteria, troubleshooting checkpoints, and go/no-go decision points
Systematically rule out instrumental, reagent, or technical causes versus true biological signal when experiments fail
Design factorial or sequential experiments for compound/candidate screening with interpretation logic
Structure one-factor-at-a-time (OFAT) or factorial designs for parameter optimization (pH, temperature, incubation time, dose ranges)
Map raw results to biological conclusions with explicit reasoning for what results support or refute your hypothesis
Example Output
Example 1: Receptor Binding Assay Protocol
Input: "Design a cell-based assay to measure compound potency against the X7 receptor using fluorescence readout."
Output:
- Hypothesis: Compounds with >50% receptor occupancy at nanomolar concentrations will show ≥2-fold fluorescence increase
- Positive control: Known agonist (EC50 = 5 nM); negative control: known antagonist; vehicle control: DMSO only
- Failure modes: (1) Fluorescent signal too low—troubleshoot: increase cell density, extend incubation time, validate antibody lot; (2) High vehicle background—troubleshoot: optimize cell wash steps, reduce DMSO %, validate reagent freshness
- Acceptance criteria: Positive control EC50 = 3–7 nM, Z-factor ≥0.5, CV <15% within plate
Example 2: Failed In Vivo Study Troubleshooting
Input: "Our compound X showed 80% in vitro activity but zero efficacy in the mouse model. Help me rule out causes systematically."
Output:
- Technical diagnostics: Was dosing correct? Confirm PK sampling shows compound reaches target tissue. Was the route (oral vs. IV) appropriate for bioavailability?
- Assay validation: Confirm positive control compound works in same model. Is the efficacy readout (imaging, biomarker, behavior) sensitive enough?
- Biological factors: Does compound have off-target toxicity? Did animal cohort have sufficient disease phenotype? Is the target engaged at intended dose?
- Next step decision tree: If PK is low → reformulation; if target engaged but no efficacy → mechanism of action issue; if positive control also fails → model validity issue
What's Included
- SKILL.md instruction file: Core framework for hypothesis validation, control design, and failure mode analysis
- Experimental Design Template: Structured worksheet for hypothesis, predicted outcomes, control specifications, and acceptance criteria
- Failure Mode & Effects Analysis (FMEA) Checklist: Systematic list of technical, reagent, and biological failure modes by assay type (cell-based, biochemical, in vivo)
- Troubleshooting Decision Tree: Flowchart for ruling out instrumental vs. reagent vs. biological causes when experiments fail
- Protocol Documentation Framework: SOP template with decision points, go/no-go criteria, and interpretation logic built in
Who It's For
- Research Scientists in pharma/biotech designing and validating new assays, screens, or in vivo studies
- Assay Development Scientists optimizing biochemical, cell-based, or phenotypic readouts for compound/candidate evaluation
- Preclinical Project Leads troubleshooting failed experiments and documenting protocols for team handoff
- Process Development Scientists designing factorial experiments for manufacturing scale-up and optimization
- Biomarker Development Teams validating new diagnostic or predictive assays with rigorous controls and failure mode planning
Best For
- New assay design and validation — Define controls, detection limits, and acceptance criteria before lab setup
- Experimental troubleshooting — Systematically rule out technical causes from true biological signal in failed experiments
- Protocol documentation — Write SOPs with explicit decision points, acceptance criteria, and interpretation logic
- Compound or candidate screening — Design multi-endpoint evaluation frameworks with go/no-go criteria
- Assay optimization — Structure factorial or sequential designs for parameter optimization (dose ranges, incubation times, reagent concentrations)
You might also like
This skill systematically analyzes your product designs to identify manufacturability issues early, saving costly revisions and manufacturing delays. It evaluates geometry, material selection, tolerances, assembly feasibility, and production process constraints. You get actionable feedback on cost drivers, process risks, and design optimizations before committing to production.
by kody-w
You can submit tool designs—drawings, specifications, or descriptions—and Claude will evaluate manufacturability constraints, identify potential failure modes using structured frameworks, and recommend cost-reduction opportunities. You'll receive a prioritized report covering structural analysis, production feasibility, material efficiency, and design trade-offs.
by kody-wThis skill interprets your FEA simulation results and extracts actionable design improvements. You can pinpoint stress concentrations, validate designs against safety factors and material limits, and receive specific geometry recommendations to reduce weight or improve performance. By automating FEA post-processing, you compress design iteration cycles and make engineering decisions faster.
by kody-w
Get comprehensive PCB design analysis covering power delivery networks, signal integrity, thermal management, and manufacturing constraints. Claude identifies potential issues early and provides specific, actionable optimization recommendations to reduce cost, improve reliability, and accelerate time-to-market. Suitable for designs from initial concept through production-ready layouts.
by kody-w
You consolidate parallel data streams from preclinical toxicology studies (clinical pathology, histopathology, body weight changes, organ weights, clinical observations, mortality) into coherent regulatory-compliant narratives. This skill synthesizes findings across 6–12 endpoints simultaneously, identifies NOAEL/LOAEL with biological justification, determines safety margins, interprets species-specific or sex-specific signals, and produces Results & Discussion sections that satisfy FDA/EMA reviewers while supporting appropriate dosing decisions for IND-enabling studies.
by kody-w
Analyze your PLC code and ladder logic to identify logic errors, safety violations, and inefficiencies before they reach production. You'll get detailed diagnostics of control system failures, safety compliance verification against IEC 61131 standards, and optimization recommendations for automation sequences. This skill helps you prevent costly downtime, ensure worker safety, and improve system performance across manufacturing operations.
by kody-w
You can translate raw variant catalogs and NGS data into actionable target hypotheses by synthesizing variant effect predictions, population frequency metrics, disease association evidence, and protein interaction networks. This skill automates the connection between molecular findings and clinical relevance, producing comprehensive variant assessments that justify target selection across pharmaceutical development stages and support regulatory submissions.
by kody-w
You can analyze equipment sensors, operational logs, and historical maintenance data to predict failures weeks in advance. Claude generates actionable maintenance schedules, identifies high-risk assets, and calculates the financial impact of preventive vs. reactive maintenance. This skill transforms raw operational data into strategic maintenance decisions that minimize downtime and extend asset life.
by kody-w