User describes a research question — what they're trying to predict or explain, what variables are involved, and what the study design looks like — and wants a recommended…
Interactive feature brainstorming through guided discovery, web research, and codebase analysis. Helps users who have a vague idea ("I want to improve X", "what if we added…
Skill for statistical power analysis and sample size calculation
Statistical power analysis and sample size determination
Create visually rich PowerPoint (.pptx) presentations from academic papers, research notes, or any content the user wants in slide format.
Skill for building standardized research protocols
This skill covers publication-quality tables and figures for academic research papers. Use when formatting regression results, summary statistics, Monte Carlo output, or research…
PyMOL molecular visualization skill for structure rendering and analysis
Qiskit Nature skill for quantum chemistry and materials science applications
Quantum kernel computation skill for quantum machine learning
Research Literature agent for healthcare workflows.
Quantum resource estimation skill for algorithm feasibility analysis
This skill should be used for RESEARCH.md artifact reviewer — validates that all findings cite evidence, confidence levels are justified, pitfalls are actionable, and…
Robust statistical methods resistant to outliers
Skill for generating publication-quality scientific figures
Use this skill to dispatch any task across multiple LLM models in parallel and consolidate their outputs into a single artifact.
This skill should be used for SB-orchestrated research workflow: explore → MultAI (landscape | tech-selection | competitive) → brainstorm → hand off to silver:feature or…
Compare N candidate outputs (drafts, designs, code variants, research reports, ...) on a stated rubric and pick the best, with cited justification.
Full state vector simulation skill for exact quantum circuit evaluation
Skill for formatting statistical results according to reporting standards
Skill for selecting appropriate statistical tests for analyses
This skill covers academic journal submission, referee responses, and revision management. Use when the user is preparing a manuscript for submission, formatting for a specific…
Ambiguity-exhaustive, research-grounded planning. BEFORE proposing any plan it (1) enumerates EVERY ambiguity as a structured clarifying question and (2) grounds every option in…
Maximum-information PARALLEL web research. Fans out MANY searches at once (one per independent sub-question × source-category) with a bounded worker pool, extracts the best hits,…
Design and analyze surveys for product validation and user research
将一条已生成的 digest/research 归档到指定 topic，并更新 topic 的 sources/timeline（M2/M3 辅助能力）。
Use this skill when the user wants to turn a rough idea, product problem, engineering thread, or research track into the right planning surface: direct bounded work, a lightweight…
Variational quantum classifier training skill with gradient optimization
Recommend the cheapest experiment that discriminates between two or more candidate paths.
Fix integer type definitions for specified platform. Researches correct primitive type mappings and applies fixes to platform-specific int headers.
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets.
Universal planning for technical and non-technical projects. Domains: software implementation, business, personal, creative, academic, events.
Technical research methodology with YAGNI/KISS/DRY principles. Phases: scope definition, information gathering, analysis, synthesis, recommendation.
Structured reflective problem-solving methodology. Process: decompose, analyze, hypothesize, verify, revise.
[00] META. Orchestrate skills into dynamic chains for complex tasks. Analyzes the task, discovers available skills, builds an optimal chain, explains why each skill is ne — from…
Use when starting a new research campaign, entering a new Claude Code session on a research repo, or when unsure which methodology principle applies.
Build neuro-symbolic LLM applications with Synalinks framework. Use when working with DataModel, Program, Generator, Module, training LLM pipelines, in-context learning — from…
Run this repo’s Units+Checkpoints research pipelines end-to-end (survey/综述/review/调研/教程/系统综述/审稿), with workspaces + checkpoints.
Designs graphics for thumbnails, social media, banners, and presentations. Applies design principles (CRAP, Gestalt, visual hierarchy) with research-backed techniques.
Creates diagrams and animations for STEM education using Matplotlib and Manim. Use for physics diagrams (FBD, vectors), math plots (functions, geometry), flowcharts, or 3 — from…
Creates diagrams and animations for STEM education using Matplotlib and Manim. Use for physics diagrams (FBD, vectors), math plots (functions, geometry), flowcharts, or 3 — from…
Designs graphics for thumbnails, social media, banners, and presentations. Applies design principles (CRAP, Gestalt, visual hierarchy) with research-backed techniques.
[02] META. Create new skills when existing ones don't cover the task. Analyze unique requirements, build framework (Frame → Research → Plan → Execute), integrate risks, and…
Deep web research, competitor scanning, technology evaluation, and implementation planning. Decomposes work into vertical slices, identifies parallel workstreams, tracks — from…
Chat with web AI agents (ChatGPT, Gemini, Claude, Grok, Perplexity, NotebookLM) via browser automation.
Fierce autonomous internal co-founder. Bounded web research for evidence-backed improvements. Structured idea formulation with self-critique filter that rejects ideas not — from…
End-to-end AI website generation pipeline. Single Claude Code prompt builds complete Vite+React+Tailwind sites from business data.
1c-mcp-toolkit — MCP доступ к данным и метаданным 1С:Предприятие. ИСПОЛЬЗУЙ когда нужно выполнить запрос к базе 1С, получить метаданные конфигурации, выполнить код 1С, прочитать…
Generate a 24-hour PR activity report grouped by module with Chinese summaries. Use when the user asks for PR statistics, daily report, PR summary, or mentions "PR 统计", "每日报告",…
Classical end-to-end empirical analysis workflow in the traditional Stata ecosystem — native Stata + reghdfe + ivreg2 + csdid + did_imputation + eventstudyinteract + sdid +…
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, o — from…
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, o — from…
Executive coaching skill that helps you plan your 2026 using research-backed process goals. Guides you through discovery questions, creates outcome goals, converts them to daily…
Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal l — from…
[21] UNDERSTAND. Deep research workflow for this project using 150% scope (100% core + 50% boundary), evidence-based reasoning, and structured investigation notes.
[22] UNDERSTAND. Deep research from all sources — internal (code, git, logs) AND external (web, docs, best practices).
This pipeline performs genome-wide segmentation of CpG methylation profiles to identify Unmethylated Regions (UMRs), Low-Methylated Regions (LMRs), and Partially Methylated…
Prepares meeting materials by gathering context from Notion, enriching with Claude research, and creating both an internal pre-read and external agenda saved to Notion.
Classical end-to-end empirical analysis workflow in the modern tidyverse + econometrics R ecosystem — dplyr + tidyr + haven + fixest + sandwich + lmtest + clubSandwich + AER +…
Three.js 3D building system with spatial indexing, structural physics, and multiplayer networking. Use when creating survival games, sandbox builders, or any game with…