Analyze checkpoint tests and suggest missing edge cases. Use after writing tests or when reviewing test coverage. Invoke with /edge-cases
.
Convert an Edge analyst report into 1-3 frozen bounded hypotheses. Use after diagnosis when the next step is to define a tighter mechanism, context filter, template choice, and…
Official level definitions and vertical curriculum architecture of EDILAB Academy (Kinder to EL600). Use when discussing levels, growth paths, curriculum alignment, or comparisons.
Use when a task needs the judgment of a Postsecondary Education Administrator (dean, department chair, provost-level, or program director) — making a program/curriculum decision,…
Education Cloud (EDA — Education Data Architecture) setup: student success hub, advisor workflows, enrollment management, academic data model.
When the user wants to plan, implement, or optimize student and education discount programs. Also use when the user mentions "student discount," "education discount," "student…
학습 질문을 받으면 공식 문서와 최신 웹 자료를 웹검색으로 병렬 조사해, 출처가 검증된 최신 학습 근거를 종합해 드립니다. 개인 튜터가 자료를 미리 조사해 오는 역할입니다. 다음과 같은 요청 시 사용하세요: - "claude cowork의 Skills와 Sub-agents 차이를 최신 정보로 조사해줘" - "이 개념…
Effect-TS specialized research via deepwiki and submodules. Query Effect-TS/effect, tim-smart/effect-atom for verified patterns.
Orchestrates rigorous consumer purchase research from need to verified recommendation. Use when the user wants to buy something and asks "what's the best X", wants product options…
面向实现闭环的工程 workflow。用于把“需求/思路/方案”转成可交付改动，强调验收标准、最小改动、立即验证、明确回滚点。冲突优先级最低：若请求同时包含“接入审计”或“修 bug/继续查”等排障闭环意图，应让位于 skill-safety-audit 或 research-execution-protocol。
Capture, structure, and score a customer interview immediately after it happens — score desperation markers, distinguish facts from interpretation, surface surprises, and update…
Prepare the user for a specific customer interview — building a focused script, surfacing the right questions for their current hypothesis, and enforcing Mom Test discipline.
Run a structured pivot-or-persevere decision. Diagnoses the failure mode in the user's data, identifies the over-performing slice if any, drafts the new value hypothesis if…
Synthesize the founder's whole journey into a 1-2 page PMF memo — insight, value hypothesis, desperation evidence, validation, metrics, the surprise, and an honest verdict.
Help the user synthesize a batch of interviews or research into clusters, patterns, and insights. Uses Pile Building, Cluster Analysis with active insight labels, stakeholder…
Maintain the founder's cross-venture learnings ledger and synthesize it into a PMF-insights view, an investment/founder-style memo, or a sharpened value-hypothesis stance.
Help the user write a PMF-grade value hypothesis — three components (what / who / how) plus a separate leap-of-faith statement.
Frame an epic as a testable hypothesis with target user, expected outcome, and validation method. Use when defining a major initiative before roadmap, discovery, or delivery…
Use when assembling the supplementary material, data-availability statement, and FAIR data deposit for an Earth and Planetary Science Letters (EPSL) manuscript.
Use when drafting or revising the literature-review section for an Economic-Research manuscript, when the Chinese / English reference balance is off, or when canonical theory…
Use when writing the theoretical analysis and hypothesis-development section of an Economic-Research manuscript — deriving testable, directional, falsifiable hypotheses that map…
Use when defending the research design of a European Sociological Review (ESR) manuscript — comparative cross-national designs, panel/longitudinal and event-history designs,…
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic r — from…
Two-stage paper screening - abstract scoring then deep dive for specific data extraction
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic r — from…
Save a short citable evidence snippet with source and note. Use when gathering facts for research tasks, saving claims for final answers, or building citation chains.
Delegate-only \u2014 Research Forge `evidence_extractor` (Wave 1). Prefer ide-bridge research-forge for Wave 1+; do not invent ledger events.
Automatically audit evidence whenever a request depends on factual accuracy, current web information, research, comparison, a consequential decision, or doubt such as "araştır",…
Erstellt strukturierte Evidenz-Matrizen für akademische Schreibprojekte im Elicit-Research-Table-Stil.
Builds B2B research assets where every number cites its source: data led post series, briefs, reports, decks, benchmark studies, white paper outlines and case studies, plus a…
Use when a user needs a source-verified research report for vendor due diligence, competitor comparison, regulatory research, partner background checks, or decision support.
Collect bounded, relevant evidence for an approved research question and source strategy without drafting conclusions.
Conduct a reproducible cross-domain review of multiple sources and produce an Evidence Synthesis with a protocol, search and screening record, evidence table, quality and…
Search, extract, and compare high-quality public sources with Exa through SandBase. Use when asked for deep web research, source discovery, current evidence, topic investigation,…
Comprehensive research skill using Exa AI tools for web search and code context retrieval. Use when conducting research on technologies, finding code examples, discoverin — from…
Use Exa AI for neural search, content retrieval, and automated deep research. Requires EXA_API_KEY.
Search the web with Exa AI — neural search, content extraction, similar page discovery, quick research with citations, and async pro research with structured output.
Design the excitation experiment for system identification — pick the input signal (step, multi-level step, PRBS, multisine, chirp), size the step magnitude, test duration, and…
Use AFTER writing-research-plan has produced a ready plan (status=ready for hermeneutic projects, status=pre-registered for quantitative/mixed).
Use when CS or AE needs expansion ideas based on reviewed evidence, fit, and customer value without wishful thinking or pressure tactics.
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.
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…
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…
Use when about to declare verdict='supported' on any experiment in a quant-research project (mandatory co-gate with bug_review; both must pass).
Best practices for designing reproducible ML experiments. Use when planning ablations, baselines, or controlled experiments.
A/B testing, randomization, sample size calculation, confounding control, and causal inference for data science.
生物实验设计、样本量和统计功效 skill。用于 omics study design、批次设计、paired/blocking、replicate、power analysis、multiple testing、randomization、covariate、time course 和统计风险评估。
Experimental design principles for scientific inquiry. Covers variable identification and control, control groups (positive and negative), randomization, blinding, sample size and…
Use when targeting Experimental Economics or deciding whether a lab- or field-experiment manuscript fits this venue.
Do experiment-driven research (hypotheses → minimal repros → evidence) and continuously improve research skills + tooling.
Activate experimenter when designing and running small, safe experiments to test improvements in skills, behavior, workflows or mental models.
Expert-level guidance for creating high-quality Claude Code skills. Use alongside Anthropic's skill-creator when creating new skills, improving existing skills, or needing…
Evaluates and improves the exploration-cycle skills, prompts, routing, and artifact quality using baseline-first, one-hypothesis iteration loops with keep-discard decisions and…
Use when a task needs the judgment of a Cooperative Extension educator — designing a farm, family/consumer-sciences, or 4-H education program, defending a county appropriation…
Future-works analysis skill with two modes. Mode audit: review one manuscript's own future-works / conclusion / limitations section (.tex/.md) — presence, testability, link to a…
Turns raw health materials (PDFs, scanned documents, images, spreadsheets, exported files) into two layers: first a faithful, fully traceable extraction of each source; then a set…