Rules and workflow for exp008 RL walking experiments with narrow torso model. Applies when working on droid_env_unitree.py, droid_train_narrow_v*.py, exp008 reports, or any…
Perpetual disease expansion - research, validate, integrate new diseases into DxEngine
Use when CS or AE needs expansion ideas based on reviewed evidence, fit, and customer value without wishful thinking or pressure tactics.
Use when the credibility of an Experimental Economics (ExpEcon) manuscript rests on experimental control — incentive compatibility, randomization, the no-deception gate, and clean…
Use when responding to a revise-and-resubmit or referee report for an Experimental Economics (ExpEcon) manuscript — including when a referee demands a new treatment, more…
Use when assembling the data, code, instructions, and experiment software for an Experimental Economics (ExpEcon) manuscript to meet the ESA reproducibility standard.
Use when an Experimental Economics (ExpEcon) result may be a power artifact, multiple-comparisons artifact, or sensitive to the inference unit, exclusions, or design choices.
Use when an Experimental Economics (ExpEcon) manuscript's exhibits must make the treatment contrast and its uncertainty visible at a glance.
Use when turning the behavioral or game-theoretic argument behind an Experimental Economics (ExpEcon) manuscript into pre-specified, testable predictions.
Use when deciding whether a question is a method-defined fit for an Experimental Economics (ExpEcon) manuscript and which treatment contrast to build it around.
Use when deciding which expecon-* sub-skill to invoke next, or when sequencing manuscript work from design through rebuttal for an Experimental Economics (ExpEcon) submission.
Use when the prose of an Experimental Economics (ExpEcon) manuscript buries the design or the result, or when the intro/abstract do not land for an experimentalist reader.
A/B test design, hypothesis documentation, sample size calculation, feature flag implementation, and statistical significance analysis.
Given a research goal, use existing skills, training reports, and references to propose a small, concrete experiment plan.
Use when analyzing experiment results, interpreting CSVs from data/raw/ or data/processed/, writing results sections, calculating any of the 12 thesis metrics, running statistical…
Analyze GRPO training runs for learning dynamics and pipeline performance. Use when diagnosing training issues, reviewing Elo progression, checking throughput, or updating…
Analyze completed experiments and craft executive-ready summaries with insights and recommendations. — from science/math-stats
Analyze completed experiments and craft executive-ready summaries with insights and recommendations. — from majiayu000/claude-skill-registry
Use when the task involves A/B testing, experiment design, statistical comparison, or causal claims from controlled or quasi-controlled comparisons.
Fetch results for a GrowthBook experiment, refresh the snapshot only when the cached data is over 24 hours old, then interpret.
Analyze completed growth experiment results, validate hypotheses, generate insights, and suggest follow-up experiments.
Propose new experiment ideas grounded in the team's past stopped experiments via the GrowthBook REST API.
Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results.
Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results.
Prepare an experiment brief outlining hypothesis, design, success metrics, and operational plan.
Recommends using Hydra or YAML for experiment configuration to ensure clarity and reproducibility.
Design and run lean experiments — hypothesis, cheapest test, success criteria, decision. Use when you need to validate before you build.
管理與商學實驗設計架構師(Q1 標準):組間/組內/混合設計選型、隨機分派與對抗平衡(counterbalancing:完全對抗/拉丁方陣,處理順序效果與練習效應)、情境實驗(experimental vignette methodology, Aguinis & Bradley 2014)的情境撰寫與擬真度、操弄檢核(manipulation…
Design experiments with controls, randomization, confound awareness, and pre-registered analysis. Use when testing a hypothesis empirically and needing the result to actually mean…
Generates a rigorous experiment design given a hypothesis. Use when asked to design experiments, plan experiments, create an experimental setup, or figure out how to test a…
Design, evaluate, and document experiments, A/B tests, product tests, growth tests, validation tests, hypotheses, primary metrics, guardrails, sample considerations, decision…
Use when planning product experiments, writing testable hypotheses, estimating sample size, prioritizing tests, or interpreting A/B outcomes with practical statistical rigor.
Compare experimental method details between two Zotero PDF papers, identify protocol differences (ratios, dosages, timing, conditions), search supporting literature to explain why…
Otonom deney dongusu. Kod degisikligi yap, olc, karsilastir, kabul et veya geri al. Metrik bazli karar verme ile performans, boyut veya kalite optimizasyonu.
Systematically analyze experiment failures and optimization setbacks to identify root causes and define validation plans before abandonment decisions.
Finalize an experiment session into clean, reviewable branches. Use when asked to "finalize experiment", "clean up experiments", or "prepare experiment for review".
Generic experiment workflow guard: sync configured upstream remote and base branch, stop immediately on merge conflicts, prefer containerized verification when…
Author pre/post-iteration hooks for an experiment session. Use when the user asks to add research fetching, Slack/webhook notifications, persistent learnings, auto-tagging,…
Launch a GrowthBook A/B test end-to-end via the REST API — create the experiment, prep the feature flag, wire the experiment-ref rule, and start the experiment.
Reproducibility provenance for a single run: executes a command and appends ONE JSON line — ISO timestamp, cwd, cmd, exit, duration, git {commit, dirty}, node/python versions,…
Log ML experiments with hyperparameters, metrics, and plots; human interprets results and plans next experiments
Apply the scientific method to any CEO initiative — define a metric, make ONE change per cycle, measure impact, keep or discard, repeat.
Use when before initiating raw file conversion or feature extraction, when you have a heterogeneous collection of raw LC-MS files (.raw or .mzML) and sample information scattered…
STEDII framework for selecting trustworthy experiment metrics. Ensures metric validity and reliability.
[Experiment Type] Skill. Usage: (1) [Scenario 1], (2) [Scenario 2], (3) [Scenario 3]. Tested on [Verification Model/Environment].
Ontwerp een experiment om je aanname zo snel en makkelijk mogelijk te valideren. Twee routes: nieuw product of bestaand product.
Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experi — from…
Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experi — from…
Analyse a finished A/B test and write an honest results readout with real statistics. Use when asked to read out an A/B test, analyse experiment results, check if a result is…
Analyze completed experiment results with effect sizes, uncertainty, guardrails, limitations, and evidence-based next steps.
Interpret A/B test results in plain language and get a ship/rollback/extend recommendation with a stakeholder summary.
Use when about to declare verdict='supported' on any experiment in a quant-research project (mandatory co-gate with bug_review; both must pass).
Create a new experiment workspace directory: initialize git, write an AGENTS.md goal doc, and create references/ with index.md + notes/links markdown plus GitHub repos cloned…
Use when designing experiments to test whether a Claude Code skill is effective, or when planning how to validate a new or improved skill
Stop a running GrowthBook experiment via the REST API, optionally declaring a winning variation and rolling it out to 100% of eligible traffic.
Use when the user has a research question and needs a complete experiment package — design document, runnable code, results (measured or simulated with honest provenance),…
Expert in ML hyperparameter orchestration. Converts scripts to use Hydra/OmegaConf and sets up Weights & Biases Sweeps. Authored by João P. M. Silva.
Create a compact, self-contained HTML table for experiment comparisons, ablations, baselines, or guardrails that will be attached to an iamyourboss report.
Manages ML experiment tracking with MLflow, Weights & Biases, or SpecWeave's built-in tracking. Activates for "track experiments", "MLflow", "wandb", "experiment logging" — from…
Manages ML experiment tracking with MLflow, Weights & Biases, or SpecWeave's built-in tracking. Activates for "track experiments", "MLflow", "wandb", "experiment logging" — from…