Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    Systematic Research Architect

    1

    Rigorous framework for research proposals, computational investigations, and experimental design with clear falsification.

    $15

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Systematic Research Architect

    Systematic Research Architect

    Example session with this skill installed

    I have a hypothesis that changing the cooling fin geometry from straight to serrated will increase heat dissipation by 15%. Design a computational study to test this.

    • Read your context and instructions
    • Compiled the systematic research architect

    I have designed a computational investigation to test the effect of serrated fin geometry on heat dissipation. The plan focuses on distinguishing geometric effects from numerical artifacts.

    Computational Investigation Design: Fin Geometry

    ComponentSpecification
    ClaimSerrated fins increase heat dissipation (Q) by 15% vs. straight fins at Re=5000.
    ObservableSteady-state surface temperature (T_s) and total heat flux (q").
    Model Level3D Steady-state RANS simulation with k-omega SST turbulence model.
    ComparisonBaseline straight fin geometry under identical boundary conditions.
    Success CriteriaQ_serrated > 1.15 * Q_straight with convergence at 1e-6 residuals.
    Auxiliary TestsMesh sensitivity study (3 levels) to ensure results are not grid-dependent.
    
### Implementation Roadmap: Stage 1
1. **Geometric Parametrization**: Define serration depth (d) and frequency (f) as independent variables.
2. **Mesh Validation**: Perform GCI (Grid Convergence Index) calculation on baseline straight fin.
3. **Stochastic Sweep**: Run 10 simulations across a range of Reynolds numbers (2000-8000).
4. **Outcome Extraction**: Integrate local heat transfer coefficients across the total wetted area.

    Next steps

    • Finalize the CAD parameters for the "serration frequency" variable.
    • Define the thermal properties of the specific alloy to be used in the simulation.
    • Run the mesh independence study on the straight fin baseline.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Research and development often stalls because of vague hypotheses, weak falsification criteria, or messy implementation paths. This skill enforces rigorous scientific and technical standards to move projects from raw ideas to verifiable results. It stops you from wasting resources on simulations that look good but prove nothing.

    What it does

    • Formalizes hypotheses by defining clear prediction models, observable variables, and specific falsification criteria.
    • Selects methodology by identifying the most cost-effective investigation level, from symbolic analysis to high-fidelity simulations.
    • Builds roadmaps through a structured maturity path that identifies prerequisites, output artifacts, and next executable steps.
    • Designs experiments with detailed protocols for independent/dependent variables, control groups, and noise source identification.
    • Drafts proposals covering mathematical architecture, literature gaps, and resource dependencies without inventing data.

    How it works

    1. Define claims using the outcome criteria framework to establish what success or failure looks like.
    2. Execute investigation by choosing between computational models or observational study designs.
    3. Map the path using the implementation roadmap to sequence work packages and acceptance criteria.
    4. Plan propagation by building a dependency tree for follow-on research and replication.

    Frameworks & tools

    This skill is framework-agnostic, focusing on the logic of scientific inquiry, mathematical consistency, and reproducible engineering. It integrates with symbolic math tools, stochastic simulators, and data analysis pipelines.

    Why this beats prompting it yourself

    Standard prompts often produce generic research summaries that lack the rigor needed for actual lab or engineering work. This skill forces the AI to distinguish between model effects and numerical artifacts, preventing "visually similar" results from being mistaken for valid mechanisms.

    Use cases

    • Design a minimal viable simulation to test a new fluid dynamics hypothesis.
    • Draft a formal research proposal for a grant application or internal R&D board.
    • Create a troubleshooting branch for an experiment that yielded inconclusive data.
    • Map the technical dependencies for scaling a proof-of-concept into a validation phase.

    Known limitations

    Does not perform external lab work, real-time data collection, or actual literature searches. Requires the user to provide the initial empirical claims or raw data for analysis.

    How to use

    Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scanned

    Verified clean 10 days ago

    • Passed all security checks, Safe to install

    Listed10 days ago

    What's inside

    Frequently Asked Questions