Evolutionary optimize-by-metric loop — mutate a target, evaluate against fixed criteria, KEEP if the score improves (commit) or REVERT if it doesn't (git checkout), repeat,…
Generates complete FAERS pharmacovigilance study designs for one-drug whole-profile safety mapping using signal detection, subgroup analysis, onset/seriousness characteri — from…
Generates complete conventional single-gene oncology research designs from a user-provided cancer context, target gene, and validation direction.
Continuously tests and improves Claude Code skills using A/B experimentation and Auto Research ML loop.
Evaluates agent skills against Anthropic's best practices. Use when asked to review, evaluate, assess, or audit a skill for quality.
Diagnose and optimize Agent Skills (SKILL.md) with real session data and research-backed static analysis. Works with Claude Code, Codex, and any Agent Skills-compatible agent.
Requires durable citations when authoring or researching Agent Skills—maintain references/sources.md per skill, link external research, and record provenance in PRs.
Structures research progress into focused and actionable slides for lab meetings or project reviews without inventing missing content.
Core methods for empirical social science research including surveys and expe...
6 social science skills. Trigger: survey research, social networks, psychology, behavioral studies. Design: quantitative and qualitative methods for social science research.
Use for social science academic paper drafting, outlining, diagnosis, review, and revision. Trigger for topic diagnosis, research question refinement, literature review planning,…
Evaluate source quality, build annotated bibliographies, and maintain curated reference collections. Covers the CRAAP test, source classification, citation management, and…
Produces a structured pre-interview research brief on a potential source, covering their professional background, public positions, known biases, potential conflicts of interest,…
Spezialisierter Agent für Abenteuerstruktur, Akte, Szenen, Spannungsbögen und Abenteuer-Hooks. Erstellt das Grundgerüst eines Pen-&-Paper-Abenteuers nach bewährten dramaturgischen…
Use when defending the research design of a Social Psychology Quarterly (SPQ) manuscript — laboratory and survey experiments (group processes, status), survey and secondary-data…
Unified workflow that delegates failed web searches to shell_agent for resilient data gathering, then applies anchored spreadsheet proof gates for verified Excel output
Use when framing or sharpening the research problem (问题意识 / problematic) for 《中国社会科学》 (Social Sciences in China) — elevating a topic from a narrow empirical question to a…
Compile the research-plan tree under metds/plans/ into paper-ready method documents under metds/. Invoked as /star-metd-summarize [OPT] where OPT is overview, dataset, framework,…
在由 market-research-landing-lab 底座派生出的新项目中启动项目调研。当用户说"开始这个项目"、"启动项目"、"初始化这个项目"、"start this project"等语义时触发。通过访谈收集执行人前提（核心技能、渠道现状、长期护城河方向、启动约束），并把答案写入 docs/00-research-question.md…
When the user has raw customer interview transcripts, survey responses, support tickets, or other qualitative data and needs to extract actionable insights.
Activate methodical coding stance. Research-backed emotional mode from claude-temper.
A 股个股深度研究报告生成。当用户需要对某只股票生成完整的研究报告 (Markdown 格式, 涵盖技术/基本面/资金/估值/股东/情绪全维度) 时,Claude 应使用此 Skill。可整合所有 Layer 1-4 数据。
Conduct source-grounded STORM research with perspective-guided retrieval, standard four-file artifacts, citation verification, adaptation of a user-provided local runner, and a…
Build and revise executable study designs for quantitative empirical political science. Use when translating a research problem and theory into a descriptive, associational,…
Use study limitations drafter for academic writing workflows that need structured execution, explicit assumptions, and clear output boundaries.
Generates a structured research brief on a documentary subject before the first filming session, covering their background, their relationship to the film's subject, their…
Use when an agent needs deep research from subscription sources, local research workspaces, archived evidence, evidence briefs, source-backed research memos, hypothesis tracking,…
Generate a research-grounded execution plan for any coding task. ALWAYS reads the project, then searches the web via `surf-search-skill` (the skill must be installed), interviews…
Growth experiment design — structure a growth hypothesis, define metric, baseline, expected lift, and kill condition for a single experiment.
Design, deploy, and analyze surveys for social science and organizational res...
Recognize and extract text from images or PDFs using Surya OCR (datalab-to/surya). Use when a user uploads a document, screenshot, scan, or photo and wants the text extracted or…
Parameter and forcing uncertainty propagation and sensitivity analysis for EPA SWMM. Use when an agent needs to (1) propagate parameter uncertainty through SWMM (fuzzy alpha-cut…
Master research synthesis including qualitative analysis, affinity diagramming, theme identification, pattern recognition, and insight extraction.
Use AI personas for early-stage research signal — with hard guardrails on what synthetic methods can and cannot validate.
Write system prompts, tool docs, and agent definitions. Combines research-backed prompt engineering (+15-30% measured improvements) with project XML conventions.
Systematic debugging techniques for unclear root causes. Use when a bug's origin is unknown, multiple hypotheses need testing, you need to narrow down a failing area, end-to-end…
TA（主题分析）研究全流程AFP工作流协调器。采用心跳信号、HUD仪表盘、 原子级单步输出、硬停止确认、多方案选择等AFP设计理念，共12个检查点。 关键决策节点（理论定位、叙事结构、标题/摘要/关键词）提供多方案+理由供选择。 每步暂停等待用户确认，所有写作工作由专项skill完成。 当用户明确提到主题分析（TA）相关的全流程时触发，例如：…
Convergent need-alignment system. Before executing any non-trivial request, ask questions (1–3 per turn, each with a recommended answer) until the user's outcome, constraints, and…
Use when targeting 《税务研究》(Taxation Research — 中国税务杂志社主办的税务学术月刊, 在线投约稿系统 tg.ctax.org.cn) or deciding whether a Chinese tax/public-finance manuscript fits this venue.
Use only after a TDL paper section or result set is stable — to convert it into public-facing web pages, talks, posters, slide decks, graphical abstracts, or explainer material.
Use when designing a course, assessment, or student-feedback workflow and deciding where AI assistance is acceptable, when grading or feedback must stay within academic-integrity…
Use when you have a hunch, a candidate optimization, a novel technique, or an "I think X is faster/better/possible" idea for tensor-grep and must turn it into an ACCEPTED result…
Expert guidance for user research, helping product teams conduct interviews, create personas, design surveys, run usability tests, and synthesize findings into actionable…
A local text formatting organizer for biomedical/academic writing; use it when you need to clean whitespace/line endings while preserving Markdown structures or when normalizing…
Build a defensible thesis or dissertation outline — argument-first structure, chapter by chapter, with the through-line visible.
Combined research, decision, and codification workflow. Use when: (1) Exploring a question before committing (2) Making a decision that needs documentation (3) User says — from…
Analysis of Competing Hypotheses. Operationalizes Richards Heuer's CIA-tradition technique for systematically narrowing among multiple hypotheses against evidence.
Researches a thinking framework end to end and produces a schema-valid proposed registry entry plus a learning dossier, grading the evidence on the seven-tier model and assessing…
First-person rigor patterns for non-trivial work — type/dimension check, decompose, bound-then-refine, sanity at limits, falsifiability.
Multi-mode analytical thinking — first principles decomposition, iterative depth analysis, multi-agent council debates, adversarial red teaming, and scientific hypothesis testing.
Apply parsimony principle to prefer simpler explanations with fewer assumptions. Use for hypothesis selection in debugging, architecture decisions, and choosing between competing…
Hypothesis → Prediction → Test → Revise with explicit falsification. Use for debugging, feature experimentation, performance investigation, and A/B testing design.
Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or problems where simple prompting…
Day 2 end capstone move of a Foundation Sprint. Compresses the sprint's full strategic frame into a single canonical sentence (the Founding Hypothesis) plus an assumption…
Research-backed CLI tool refresh workflow for updating existing tools with TDD checkpoints and CLI invocation validation.
Identify which processes, connections, and remote hosts are actually using bandwidth before you chase the wrong incident hypothesis.
Generate falsifiable trade strategy hypotheses from market data, trade logs, and journal snippets. Use when you have a structured input bundle and want ranked hypothesis cards…
Front-door skill for selecting and coordinating Claude Trading Skills inside Hermes for market research, earnings triage, risk review, and journaling.
Research the Israeli traffic statute behind a specific offense — find the regulation/section, number of points, fine tier, applicable appeal route (legacy vs.
Research and recommend hotels, resorts, Airbnbs, and villas for client travel. Covers family-friendliness assessment, luxury evaluation, price-range estimation, and compiling with…