322 skills · sorted by relevance
Build AI agents that automate scientific research — hypothesis generation, experiment design, data analysis, and paper writing using agentic tree search. Use when: automating research workflows, generating and testing hypotheses, building AI-powered research assistants.
The English summary is being prepared. Showing the original description.
Systematic debugging methodology - scientific method, hypothesis testing, and root cause analysis that works across all technologiesUse when "bug, debugging, not working, broken, investigate, root cause, why is this happening, figure out, troubleshoot, doesn't work, unexpected behavior, debugging, root-cause, hypothesis, scientific-method, troubleshooting, bug-hunting, investigation, problem-solving" mentioned.
The English summary is being prepared. Showing the original description.
The science of learning through controlled experimentation. A/B testing isn't about picking winners—it's about building a culture of validated learning and reducing the cost of being wrong. This skill covers experiment design, statistical rigor, feature flagging, analysis, and building experimentation into product development. The best experimenters know that every test, positive or negative, teaches something valuable. Use when "a/b test, experiment, hypothesis, statistical significance, sample size, feature flag, variant, control, treatment, p-value, conversion rate, test winner, split test, experimentation, testing, statistics, feature-flags, hypothesis, growth, optimization, learning, validation" mentioned.
The English summary is being prepared. Showing the original description.
Designing A/B tests: hypothesis docs, sample size, feature flags, significance analysis, CUPED, SRM detection, switchback experiments. Use when hypothesis validation is needed.
The English summary is being prepared. Showing the original description.
Expert guide for property-based testing (fast-check, Hypothesis) and mutation testing (Stryker, mutmut) — AI-generated test properties, invariant discovery, mutation score optimization, and test suite quality verification / Panduan ahli property-based testing (fast-check, Hypothesis) dan mutation testing (Stryker, mutmut) — properti tes yang dihasilkan AI, penemuan invarian, optimasi skor mutasi, dan verifikasi kualitas suite tes.
The English summary is being prepared. Showing the original description.
Formal oracle for abductive inference that selects the minimal hypothesis best explaining a set of observations. Provides three sub-oracles: MCMC via monad-bayes, Gemini for natural language, and propagator networks for constraint domains. Use when performing hypothesis selection, explaining observations, or solving inference-to-best-explanation problems.
The English summary is being prepared. Showing the original description.
Turns a theory into falsifiable, pre-registerable hypotheses: DGP and DAG, identification, estimands, SESOIs, test choice among NHST, equivalence, and minimum-effect tests, scope conditions, and hypothesis tiers. Use when converting a research question into testable predictions or predicting a null.
The English summary is being prepared. Showing the original description.
Use when facing unknowns, debugging without a clear cause, or making architecture decisions — enforces hypothesis-driven scientific reasoning through observation, hypothesis formulation, prediction, experiment design, and evidence-based conclusion. Use when previous attempts have failed or the problem space involves uncertainty.
The English summary is being prepared. Showing the original description.
Construct well-structured arguments using the hypothesis-argument-example triad. Covers formulating falsifiable hypotheses, building logical arguments (deductive, inductive, analogical, evidential), providing concrete examples, and steelmanning counterarguments. Use when writing or reviewing PR descriptions that propose technical changes, justifying design decisions in ADRs, constructing substantive code review feedback, or building a research argument or technical proposal.
The English summary is being prepared. Showing the original description.
Scaffold and run Karpathy-style autoresearch loops in any git repo. This skill should be used when setting up autonomous code improvement, generating adversarial eval harnesses, running hypothesis-implement-eval-keep/discard loops, or checking autoresearch progress. Triggers on "autoresearch", "autonomous improvement", "eval loop", "hypothesis loop", "self-improvement loop".
The English summary is being prepared. Showing the original description.
Hard-gated ideation for an Arbor research run. Load at the START of every IDEATE round, before drafting any hypothesis. Enforces the PI mindset (mechanism over knob), the four-question first-principles probe, the kill-filter, and the four-line hypothesis format. Ported from Arbor's idea_drafting + first_principles_probe.
The English summary is being prepared. Showing the original description.
Design a research study. Use when the user says "study design", "design my research", "what research method should I use", "how do I test this hypothesis", "research plan", "methodology section", "experimental design", "survey design", "qualitative study design", "how to structure my study", "sample size", "data collection plan", or needs to plan how to test a research question or hypothesis - even if they don't explicitly say "study design".
The English summary is being prepared. Showing the original description.
Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.
The English summary is being prepared. Showing the original description.
Expert-level statistics knowledge. Use when working with probability distributions, hypothesis testing, regression, Bayesian statistics, statistical inference, experimental design, ANOVA, or statistical modeling. Also use when the user mentions 'p-value', 'confidence interval', 'hypothesis test', 'regression', 'ANOVA', 'chi-square', 't-test', 'Bayesian', 'maximum likelihood', 'statistical significance', 'correlation', 'normal distribution', or 'sampling distribution'.
The English summary is being prepared. Showing the original description.
Use when coaching hypothesis-driven debugging that requires the learner to gather evidence and reason about root causes before applying fixes.
The English summary is being prepared. Showing the original description.
Turn any hypothesis, however fringe, into an argument map rather than a verdict: five independent lenses (consensus, skeptic, frontier, historian, experimental design), then a synthesis of for and against, evidence quality, a confidence tier and the cheapest decisive experiment. Triggers: "/research-swarm <hypothesis>", "map the arguments on X".
The English summary is being prepared. Showing the original description.
Repository または subsystem を対象に、source-only で明示的なセキュリティ監査を行う entry skill。 通常の PR セキュリティレビューとは分離し、reconnaissance、scope 固定、既存 security skill への委譲、 evidence と unresolved hypothesis、observe-only SecurityAuditCoverage、coverage critic、 structured audit artifact と repeat-run coverage を扱う。target-controlled code は実行しない。
The English summary is being prepared. Showing the original description.
Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.
The English summary is being prepared. Showing the original description.
A/B testing specialist v3 — hypothesis, sample size, statistical significance, Bayesian
The English summary is being prepared. Showing the original description.
Write a rigorous, decision-grade experiment spec — falsifiable hypothesis, primary metric, guardrails, randomisation unit, exposure definition, method (A/B, holdout, switchback, quasi-experiment, MAB), MDE/duration plan, peek policy, validity threats, and pre-committed decision rule. Platform-agnostic. Load when the user has a candidate experiment and needs to spec it before launch, or says "spec this experiment", "write the test plan", "design this A/B test", "what's the hypothesis", "how big a sample do we need", "how long should we run this", "define the metrics for this test", or when the experimentation orchestrator routes here.
The English summary is being prepared. Showing the original description.
This skill should be used when the user wants to "test a claim against data", "validate an empirical hypothesis", "refine a model/theory with evidence", "characterize a pattern and verify it", "演繹と帰納で検証", "仮説をデータで検証して更新", "実例と反例で確かめる", "弁証法ループ", "主張を現物で裏取り", "傾向分析を検証して精緻化", or mentions iteratively updating a hypothesis by deriving predictions and testing them against a real corpus. NOTE: Use this for VALIDATING/REFINING an empirical claim or model against real data through a derive→test→update loop. Use strong-inference for debugging an UNKNOWN cause, and devils-advocate for adversarially stress-testing a DESIGN proposal.
The English summary is being prepared. Showing the original description.
The science of learning through controlled experimentation. A/B testing isn't about picking winners—it's about building a culture of validated learning and reducing the cost of being wrong. This skill covers experiment design, statistical rigor, feature flagging, analysis, and building experimentation into product development. The best experimenters know that every test, positive or negative, teaches something valuable. Use when "a/b test, experiment, hypothesis, statistical significance, sample size, feature flag, variant, control, treatment, p-value, conversion rate, test winner, split test, experimentation, testing, statistics, feature-flags, hypothesis, growth, optimization, learning, validation" mentioned.
The English summary is being prepared. Showing the original description.
Turn speedup requests into a measured optimization process with limits on time, cost, and variants. Compare each change against a baseline and correctness checks, then retain the fastest safe option with reproducible commands and measurements.
Guides debugging through reproduction, comparison with working examples, hypothesis testing, and a focused fix. It starts with a repeatable check for the exact symptom and uses regression tests to verify the result.