Use BEFORE running a confirmatory analysis, an experiment readout, an A/B test, a policy evaluation, or any study whose credibility depends on not having fished for the result —…
Use before starting implementation - research repository documentation, codebase patterns, and external resources to inform the approach
Production-ready decentralized search for AI agents. Privacy-first, uncensored web search via distributed node infrastructure.
primary-source-verification (psv) — a read-only, source-grounded, per-claim verifier that FETCHES each cited primary source and adjudicates a doc's factual/citation claims…
Search patent databases and academic literature for prior art relevant to an invention. Use when user says "现有技术检索", "prior art search", "专利检索", "check patents", or wants — from…
Discovery group skill. Restates the client's problem, target user, current workaround, success signal, and renders a falsifiable hypothesis.
Turn vague problem observations into testable hypothesis statements with specific who/when/severity/current-workaround dimensions.
Systematic problem-solving toolkit: root cause analysis, hypothesis testing, debugging strategies, critical thinking frameworks.
Process all unprocessed PDF files in the papers/ root directory. If subagents are available, parallelize across papers immediately after listing them; otherwise process…
Generates complete process-related diagnostic biomarker bioinformatics research designs from a user-provided disease context, gene-family or pathway theme, and validation — from…
Synthesize qualitative and quantitative user research into structured insights and opportunity areas.
Synthesize qualitative and quantitative user research into structured insights and opportunity areas.
Entity-profile graph edges + embedding similarity for a research corpus — profile→REF edges (first-class adjacency, reconciled against the citation graph) and text-embedding…
Teach and assess programming through bounded hands-on exercises, executable feedback, progressive hints, debugging, tests, and learner reflection.
Use when targeting Progress in Energy and Combustion Science or deciding whether an energy/combustion review manuscript fits this venue.
Use when a bug has multiple plausible causes across layers — competing hypotheses, validation loops, evidence-based conclusions — even when the user just says 'why is this…
Project management specialist routing for studio operations, cross-functional shepherding, experiment tracking, realistic scoping, and Jira workflow discipline.
Research workflow patterns specific to {project}. Covers research agent coordination, source management, and synthesis strategies. — from bg-szy/TOP-SKILLS
Systematic prompt engineering methods for AI-assisted academic research workf...
Execute complete FPF cycle from hypothesis generation to decision
Use when task is to run or resume an iterative IMC Prosperity research loop: generate or refine hypotheses, check prior attempts, evaluate candidate signals or portfolio ideas,…
Research-driven critique and enhancement of Amelia architecture or ideas docs. Use with GPT-5.2 when given a design/architecture doc to analyze concepts, find sources, an — from…
Feature geliştirme için Plan-Research-Plan framework'ü. Codebase analizi, pattern araştırma, güven skoru, blueprint oluşturma ve uygulama döngüsü.
pschool プロジェクト専用のコース・カリキュラム自動生成 skill (schema v2 = state machine DAG)。 Udemy / 技術学習プラットフォーム型の 1 コース = フラット chapters[] + sections[] view group 構成で、 各 chapter は lecture / mixed /…
Psilocybin phenomenological state simulation. Transforms Claude's cognition, perception, language, emotion, and sense of self across low/medium/high intensity levels.
Use when deciding whether a question is review-worthy and meta-analyzable for Psychological Bulletin and which synthesis type fits (meta-analysis, systematic review,…
Use as the entry point for any Psychological Bulletin manuscript. Routes to the right psychbull sub-skill based on where you are in the research-synthesis lifecycle and which…
Use when a task needs the judgment of a tenure-track/tenured Psychology Professor — deciding whether a student's or your own "significant" finding is trustworthy before it's…
PUA Loop — autonomous iterative development with autoresearch-style gate protocol. Runs FOREVER until verified done.
Use when defending the research design of a Public Administration Review (PAR) manuscript — public-management causal designs (DiD around reforms, survey & field experiments on…
Use when targeting 《财政研究》(Public Finance Research — 财政部主管、中国财政学会主办、不收版面费的财政学权威核心月刊, CNKI 采编系统) or deciding whether a Chinese public-finance manuscript fits this venue.
Git 工作流知识基座。extends netresearch/git-workflow-skill 上游通用 Git 知识，叠加团队 commit 规范、分支策略、Gitea 工作流、镜像同步经验。供 devlab-git-workflow-expert 等下游技能通过 extends 继承。
NL2SQL/Text2SQL 知识基座（供 extends 继承）。聚合两阶段架构、查询类型分类、字段/术语映射、条件与 metric 抽取、多表 JOIN 推理、SQL 正确性与评测的深度知识与踩坑。通常被 devlab-nl2sql-engineering 继承，不直接面向用户触发。
Oracle 知识基座。覆盖 Connection Types、JDBC Driver、Connection Pool、LOB Handling、Character Set、SQL Dialect。供 devlab-oracle-usage 通过 extends 继承。
Python interface to OpenMS for mass spectrometry data analysis. Use for LC-MS/MS proteomics and metabolomics workflows including file handling (mzML, mzXML, mzTab, FASTA — from…
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2 — from majiayu000/claude-skill-registry
Use when the identification argument is the bottleneck for a Quantitative Economics (QE) manuscript — whether causal identification in an empirical design, parameter…
Use early, when judging whether a project fits Quantitative Economics (QE) — a substantive economic question answered with serious quantitative methods (empirical,…
Reproducibility and claim boundaries for QECTOR (manual 19, 22, 27, Appendix D). Covers the chapter 22.3 required-artifact metadata, the safe / unsafe wording rule (manual 22.5),…
Worktree-Question-Research-Design-Structure-Plan-Implement-PR phase discipline with gate enforcement — loaded by orchestrator to govern pipeline phase transitions, artifact…
Use when conducting customer discovery interviews, user research, surveys, focus groups, or observational research requiring rigorous analysis - provides systematic 6-phase…
Automates critical appraisal and quality assessment for research papers by analyzing text against established methodological standards (such as risk of bias tools, quality…
Scan a project to detect configured quality and testing tools across JVM (Gradle/Maven), Android (AGP/Compose/KMP), Node.js/TypeScript, and Python ecosystems.
Activates for quantitative-finance, algorithmic-trading, alpha-factor work, backtests, return prediction, regime detection, portfolio construction, financial machine learning,…
Set up a multi-agent quantitative research and trading team with file-based planning. Use when: (1) user asks to start a new complex quant project with a team, (2) user says "set…
Use when establishing measurement programs, analyzing metrics with statistical process control, setting baselines, or implementing CMMI Level 4 quantitative management - prevents…
World-class systematic trading research - backtesting, alpha generation, factor models, statistical arbitrage. Transform hypotheses into edges.
Gunakan skill ini saat mengimplementasikan fitur baru end-to-end di QuantLab — dari requirements, desain, backend engine, endpoint, frontend component, testing, sampai dokumentasi…
Create hybrid Quarto Markdown (.qmd) lecture scripts for Single Source Publishing (interactive Moodle websites + static PDF textbooks).
Search the FPF knowledge base and display hypothesis details with assurance information
Use when stuck after several failed fixes on the same hypothesis - step back and question whether you're fixing the right layer at all, before trying the next fix.
Scaffold radar/freshness sidecars for research-corpus REFs. Pulls title/authors from the citation sidecar and GRADE from the analysis doc, defaults the refresh cadence from GRADE…
Sweep the official AI lab and big-tech AI blogs on EVERY daily run (not rotated) so no open-weight release, infrastructure or safety announcement is missed.
Aggregate research-corpus radar sidecars into a corpus or per-cluster freshness report — totals, overdue count, per-cluster / per-GRADE / per-trajectory breakdowns, an overdue…
Report which research-corpus radar sidecars are overdue for refresh. Computes staleness (days since last refresh vs the cadence window) for every radar, sorted most-overdue-first.
Research latest library documentation, industry best practices, and technical knowledge to automatically generate project-level skills.
Generate Ralph-compatible prompts for research, analysis, and planning tasks. Creates prompts with systematic research phases, synthesis requirements, and deliverable…
Gene and region-based rare-variant aggregation - burden/collapsing, SKAT, SKAT-O, ACAT-V/ACAT-O, annotation-weighted STAAR - with regenie (--vc-tests), SAIGE-GENE+, and t — from…
Create evidence-first R&D decision packets with an assumption register, three competing paths, a candidate small discriminating experiment, precommitted go/pivot/stop thresholds,…
R&D management expertise for R&D portfolio management, technology roadmapping, research methodology, patent strategy, lab management, academic partnerships, and regulatory…