sci story skill

    0

    Transform ML/CV research into rigorous, reviewer-defensible papers using claim-evidence auditing and reviewer simulation.

    Free

    4 usesSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    sci story skill

    Example session with this skill installed

    I have a draft on 3D Gaussian Splatting for dynamic scenes. Review it for potential rejection risks at CVPR and check if my claims about efficiency are backed by my current experiments.

    • Read your context and instructions
    • Compiled the sci story

    I have analyzed your draft using Mode F (Reviewer Attack) and Mode D (Claim-Evidence Audit). The narrative identifies a clear gap in temporal consistency, but the efficiency claims currently lack the necessary computational accounting to survive a skeptical review.

    Reviewer Attack & Claim Audit

    AttackSeverityEvidenceVulnerabilityRecommended Fix
    Unsupported Efficiency ClaimCriticalTable 4 only shows FPS, not FLOPs or GPU memory.Claiming "superior efficiency" without training cost or memory footprint metrics.Add a table comparing total training GPU hours and peak VRAM vs. D-NeRF.
    Missing BaselineMajorMissing comparison with TiNeuVox.Reviewers will view the benchmarking as incomplete for dynamic scenes.Include TiNeuVox in Table 1 and qualitative figures.
    Post-hoc StorytellingModerateIntroduction focuses on storage, but experiments focus on speed.The narrative and evidence are misaligned (Story Lock violation).Re-align the central insight to focus on inference speed as the primary contribution.

    Claim-Evidence Matrix

    • Claim 1: "Our method achieves real-time rendering on mobile devices."
      • Status: Inferred.
      • Issue: Evidence only shows desktop RTX 3090 benchmarks.
    • Claim 2: "Temporal smoothing significantly reduces artifacts."
      • Status: Observed.
      • Evidence: Table 2 (Ablation) shows a 2.1dB PSNR gain with the smoothing module.

    Next steps

    1. Quantify Efficiency: Run memory profile tests and training time benchmarks to support Claim 1.
    2. Baseline Expansion: Integrate TiNeuVox results into the quantitative comparison.

    Re-lock Narrative: Adjust the abstract to lead with "Inference Speed" rather than "Storage Efficiency" to match the evidence.

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

    About this skill

    Scientific papers in ML and CV often fail not because of the English, but because of weak logic, misaligned evidence, and indefensible claims. This skill transforms your research from a collection of experiments into a rigorous, reviewer-defensible narrative by applying a three-layer engineering system. It focuses on the underlying scientific argument rather than mere grammar correction.

    What it does

    • Corpus mining extracts underlying scientific argument patterns from best-paper award winners rather than just summarizing them.
    • Research architecture builds a coherent chain from research gap to central insight, hypothesis, and evidence map.
    • Claim-evidence auditing flags overclaiming by checking if claim strength exceeds evidence strength across direct and ablation results.
    • Reviewer simulation generates critical attacks from three distinct personas to identify rejection risks before submission.
    • Technical English editing refines stable manuscripts for precision, concision, and logical flow after the scientific logic is locked.

    How it works

    1. Analyze your idea or draft using the "Story Lock" mechanism to ensure the narrative remains consistent throughout the paper.
    2. Execute specific modes like Experiment Planning to design RQs that satisfy skeptical reviewers or Reviewer Attack to find vulnerabilities.
    3. Refine the manuscript based on a prioritized revision plan that fixes scientific validity before addressing language polish.

    Frameworks & tools

    Optimized for top-tier venues including NeurIPS, ICLR, ICML, CVPR, and ICCV. Expertise covers ML, Computer Vision, 3D Vision, and Generative AI domains.

    Why this beats prompting it yourself

    Generic prompts often produce "academic-sounding" fluff that obscures the actual contribution. This skill enforces a "Claim Strength ≤ Evidence Strength" rule and uses a formal Story Lock to prevent post-hoc storytelling, ensuring your paper survives rigorous peer review.

    Use cases

    • Drafting a high-impact introduction that clearly defines a research gap and central insight.
    • Auditing a finished manuscript for unfair baseline comparisons or missing ablation experiments.
    • Simulating a Rebuttal phase by generating and answering potential reviewer attacks.
    • Restructuring a "result dump" into a logical scientific argument.

    Known limitations

    Does not fabricate data, citations, or results. Requires a stable research idea or existing results to provide architectural value. English polishing is only performed on scientifically stable drafts.

    Does not fabricate data or results. Requires existing research inputs. Language polishing is restricted until scientific logic is finalized. Scope limited to ML/CV/AI domains.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    4 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Network Access
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill addresses logical vulnerabilities and 'overclaiming' by enforcing a strict claim-evidence audit, ensuring your research narrative is defensible against the specific skepticism typical of top-tier reviewers at venues like NeurIPS or CVPR.

    The skill performs best when provided with a detailed research abstract, a list of experimental results (including ablations), or a full draft in markdown/text format, as it needs to map your specific evidence against your scientific claims.

    Your purchase includes the full suite of specialized modes: Corpus Mining, Research Architecture, Claim-Evidence Auditing, Reviewer Simulation, and Technical English Editing, along with any logic updates for new conference cycles.

    Yes, the skill is optimized for current standards at major AI venues like ICLR, ICML, and ICCV, and it receives regular updates to reflect changing reviewer expectations and emerging sub-fields like Generative AI and 3D Vision.

    While this skill excels at identifying gaps in your logic and suggesting necessary ablations to support your claims, it will never fabricate data, generate fake citations, or hallucinate experimental results.

    New in Research & Analysis