Research & Search

majiayu000 Bundle

Orchestrates parallel research subagents to gather context for a ticket. Use after ticket-intake completes and ticket.json exists.

majiayu000 Bundle

Search for research papers and academic content using Exa advanced search. Full filter support including date ranges and text filtering.

majiayu000 Bundle

Use this skill when researching potential clients, leads, or business contacts before outreach or meetings. Gathers information from LinkedIn, company websites, news, and social media to build prospect profiles. Invoke for lead research, pre-meeting prep, or competitive intelligence.

majiayu000 Bundle

Research Neovim APIs, plugin patterns, and Lua development. Invoke for lua-language research tasks.

majiayu000 Bundle

Research Python/Z3 patterns and APIs for semantic theory development. Invoke for Python-language research tasks.

majiayu000 Bundle

Procedural terrain generation algorithms and techniques for Three.js/R3F. Research-based skill with patterns from THREE.Terrain, Nathan Pointer's landscape rendering, and academic papers.

majiayu000 Bundle

Create detailed user personas based on research and data. Develop realistic representations of target users to guide product decisions and ensure user-centered design.

majiayu000 Bundle

Download, transcribe, and summarize videos from X and other platforms

majiayu000 Bundle

Transform raw ideas and brain dumps into polished YouTube scripts through a structured checkpoint workflow. Use when the user wants to write a YouTube script, improve video retention, craft hooks, structure educational or entertainment content, or turn source material (transcripts, notes, research) into a compelling video script. Guides through research, hook writing, story structure, body content, and editing phases.

majiayu000 Bundle

Use for workflow guidance on HOW to research effectively. Covers analyzing tickets, memories, comments, generating proposals, and identifying patterns.

majiayu000 Bundle

General UX/UI refactor patterns for dense information products, including layout compression, view-mode clarity, selection-to-results flow, research workspace design (non-chat), and enforcing a no-emoji UI policy. Use when restructuring existing UIs for clarity while preserving all features.

majiayu000 Bundle

[Implementation] No research. Only scout, plan & implement [trust me bro]

majiayu000 Bundle

Create per-subsection evidence packs (NO PROSE): claim candidates, concrete comparisons, evaluation protocol, limitations, plus citation-backed evidence snippets with provenance. **Trigger**: evidence draft, evidence pack, claim candidates, concrete comparisons, evidence snippets, provenance, 证据草稿, 证据包, 可引用事实. **Use when**: `outline/subsection_briefs.jsonl` exists and you want evidence-first section drafting where every paragraph can be backed by traceable citations/snippets. **Skip if**: `outline/evidence_drafts.jsonl` already exists and is refined (no placeholders; >=4 comparisons per subsection; `blocking_missing` empty). **Network**: none (richer evidence improves with abstracts/fulltext). **Guardrail**: NO PROSE; do not invent facts; only use citation keys that exist in `citations/ref.bib`.

majiayu000 Bundle

Standard Operating Procedure for /plan phase. Covers research depth, code reuse detection, design pattern selection, and architecture planning.

majiayu000 Bundle

Interviews a researcher, in rounds, until a research idea, design, or draft has no silently assumed decision left — every question numbered, each with a plain-language "why this matters" and a recommended answer, facts fetched by the assistant rather than asked, and every settled decision written to a file. Three stages, idea (a topic or hunch → a falsifiable question and a contribution claim), design (a question → estimand, identification, sample and power, measurement, pre-registration, analysis plan, venue), and defend (a finished design or draft → the objections a reviewer would raise, before the reviewer does). Use when the user says "grill me", "grill this", "stress-test my idea/design/plan", "interview me about this project", "poke holes in this", "what am I assuming", or brings a research idea that is not yet a design. Suitable for BA, MA, and PhD students as well as grant designs; it never answers the research question for the researcher. Adapted for research from Matt Pocock's grill-me. For a softwa

majiayu000 Bundle

Mines academic papers, research blogs, and curator newsletters for stealable methods and frameworks. Use when scanning research for applicable techniques across AI/ML/SWE.

majiayu000 Bundle

Research and synthesize information about {{TOPIC}}. Use when {{TRIGGER_CONTEXTS}}. Produces {{OUTPUT_FORMAT}} with citations.

majiayu000 Bundle

Read and summarize constitution principles for the AI-Native Robotics Textbook project. Use when checking project rules, validating compliance, or understanding constraints.

majiayu000 Bundle

Use this skill when optimizing for AI-powered search engines and generative search results - Google AI Overviews, ChatGPT Search (SearchGPT), Perplexity, Microsoft Copilot Search, and other LLM-powered answer engines. Covers Generative Engine Optimization (GEO), citation signals for AI search, entity authority, LLMs.txt specification, and LLM-friendliness patterns based on Princeton GEO research. Triggers on visibility in AI search, getting cited by LLMs, or adapting SEO for the AI search era.

majiayu000 Bundle

想法群聊室 — 反方角色。被 idea-team 主编排器调用，或用户单独说"反方意见"、"挑这个想法的刺"、"为什么会失败"、"找漏洞 / 反例"、"devil's advocate"时触发。**专门挑漏洞、找隐藏假设、给反例——不安慰、不"也许可以这样"、不全盘否定**。Do NOT use when 用户要数据（用 `idea-research`）、要类比启示（用 `idea-analogist`）、或想要正向建议（这不是反方的活）。

majiayu000 Bundle

Validate and enforce standard YAML frontmatter on research documents with JD-aware path resolution. Use when creating, editing, or validating research files, when user mentions "research metadata", "research frontmatter", "research staleness", "validate research", "RD-rules", or "research docs validation".

majiayu000 Bundle

Shows you how to use Cowork's parallel workers to run multiple tasks at the same time instead of one after another — dramatically cutting the time on batch work. For processing large batches of files or research tasks, when running multiple independent analyses simultaneously, or during a performance optimization session. Use when the user says "speed up", "parallel workers", "batch task", "process multiple files", "why is cowork so slow", "faster", "do several things at once", or "can cowork multitask".

majiayu000 Bundle

Self-improving lead research expert for autonomous eCommerce brand intelligence gathering.

majiayu000 Bundle

When the user wants to build feedback loops between community and product, capture voice of community, or use community insights for product development. Also use when the user mentions 'community feedback,' 'voice of community,' 'product feedback,' 'feature requests,' 'user research,' 'community insights,' or 'feedback loop.' For community health metrics, see community-metrics.

majiayu000 Bundle

Create/Updates detailed user personas and prioritized user stories based on target users and market research. Use when user asks to create personas, define user stories, or start Stage 2 after market research or init-ideas.

majiayu000 Bundle

Bulk convert legacy user research profiles to UTC (User Truth Canvas) format. Use when migrating existing research from grimoires/pub/research/users/ to laboratory.

majiayu000 Bundle

Diagnostic-first user research for support conversations and feedback analysis. Reaches Level 3 (user goal) before investigating or fixing. Applies The Mom Test methodology to extract product insights from bug reports and feature requests.

majiayu000 Bundle

10 pre-dev workflow skills + 3 research agents organized into Small Track (4 gates, <2 days) and Large Track (9 gates, 2+ days) for systematic feature planning with research-first approach.

majiayu000 Bundle

Parse ctest and sanitizer output, summarize failures, identify root causes, and track test coverage for Orpheus SDK builds.

majiayu000 Bundle

Generate project-specific workflow commands (research, plan, implement, qa) by asking questions about the project and creating customized commands

majiayu000 Bundle

Write scientific manuscripts. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), abstracts, for research papers and journal submissions.

majiayu000 Bundle

Search academic literature and generate research hypotheses

majiayu000 Bundle

Produce an experiment blueprint from a research hypothesis

majiayu000 Bundle

Structure vague opportunities and unclear briefs into actionable one-page problem statements. Use when asked to clarify a vague brief, frame an undefined problem, make sense of an unclear opportunity, or when the user says 'we need to figure out what to do about X' or 'I've been asked to look into Y'. Produces a structured problem brief with reframed questions, scoped boundaries, and a minimum viable research plan.

majiayu000 Bundle

Use when factual claims in a science blog essay need verification with source URLs, or when proactive research enrichment would strengthen an argument.

majiayu000 Bundle

Build a research definition and execute the study based on a Linear issue.