Research

Use when the user explicitly asks for vibe brainstorming, creative implementation ideas, implicit expected behavior, or convention checks, and when an implementation task is creative or convention-dependent. Do not use for obvious mechanical edits.

Conduct enterprise-grade research with multi-source synthesis, citation tracking, and verification. Use when user needs comprehensive analysis requiring 10+ sources, verified claims, or comparison of approaches. Triggers include "deep research", "comprehensive analysis", "research report", "compare X vs Y", or "analyze trends". Do NOT use for simple lookups, debugging, or questions answerable with 1-2 searches.

Draft, rewrite, or review reader-facing prose so it is specific, useful, and recognizably the author's without inventing facts or performing humanness. Use for essays, articles, newsletters, documentation, talks, launch copy, and other important prose that feels generic, hollow, or AI-shaped. Supports co-write, rewrite, review, and lint modes.

Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invokes ("interview me", "grill me", "are we sure?", "stress-test my thinking"), or when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists.

Guidance for cell-free protein synthesis (CFPS) optimization. Use when: (1) Planning CFPS experiments, (2) Troubleshooting low yield or aggregation, (3) Optimizing DNA template design for CFPS, (4) Expressing difficult proteins (disulfide-rich, toxic, membrane).

Railway debugging and issue resolution. Use when deployments fail, builds error, services crash, performance degrades, or networking issues occur.

Analyze skill effectiveness through usage feedback, metrics analysis, and outcome assessment. Task-based operations for feedback collection, effectiveness measurement, trend analysis, and insight extraction. Use when analyzing skill effectiveness, measuring ROI, understanding usage patterns, or evaluating toolkit impact based on real usage data.

Recommends movies and TV shows to watch on streaming services. Gives 3-5 curated picks based on genre, mood, format, and streaming platform. Use when the user asks what to watch, wants streaming recommendations, or needs help picking a movie or show.

Run post-bootstrap or post-migration governance audit.

EXPERIMENTAL: Three-layer parallel meta-cognition analysis. Triggers on: /meta-parallel, 三层分析, parallel analysis, 并行元认知

Deep research and analysis tool. Generates comprehensive HTML reports on any topic, domain, paper, or technology. Use when user asks to research, analyze, investigate, deep-dive, or generate a report on any subject. Supports academic papers (arXiv), technologies, trends, comparisons, and general topics.

Structured web research with multi-source validation. Output reports with complete citation links. Focus on key results, verify information quality.

Detect and fix AI writing patterns including overused phrases (testament to, pivotal, landscape, delve), structural tells (rule of three, em dash overuse, negative parallelisms, copula avoidance), promotional language, and vague attributions. Use when user asks to "make text sound human", "remove AI tells", "humanize writing", mentions patterns like "too many dashes" or "sounds like ChatGPT", or requests natural/conversational tone. Triggers: AI-generated, humanize, writing style, natural wr...

Use this skill when planning user research, conducting usability tests, creating journey maps, or designing A/B experiments. Triggers on user interviews, usability testing, user journey maps, A/B test design, survey design, persona creation, card sorting, tree testing, and any task requiring user experience research methodology or analysis.

Use this skill when applying Jobs-to-be-Done, building opportunity solution trees, mapping assumptions, or validating product ideas. Triggers on product discovery, JTBD, jobs-to-be-done, opportunity solution trees, assumption mapping, experiment design, prototype testing, and any task requiring product discovery methodology.

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.

Use this skill when conducting customer research - designing surveys, writing interview guides, performing NPS deep-dive analysis, interpreting behavioral analytics (funnels, cohorts, retention), or building data-driven user personas. Triggers on "create a survey", "interview script", "NPS analysis", "user persona", "behavioral analytics", "customer segmentation", "voice of customer", "churn analysis", "jobs to be done", or "research plan".

Find app screenshots and UI references quickly. Downloads results locally and groups them by pattern. Use when the user wants to see examples of a specific screen, UI element, or flow without a full research report. Trigger on: "show me examples of", "how do other apps do", "design inspiration for", "UI reference for", "what does X's app look like", "find screenshots of", "show me how", "references for".

Deep design research combining Lazyweb's screenshot database with web research. Produces a structured research report with downloaded reference screenshots. Use when the user needs competitive analysis, best practices research, or wants to understand how the best apps handle a specific design problem. Trigger on: "best practices for", "how should I design", "what do top apps do", "competitive analysis for", "design research on", "what works well for", "research how others do".

CRUX — Calibrated Reasoning under eXtreme uncertainty. 8 modes from quick assess to full adversarial analysis with subagents. /crux [mode] <question>. CIA SATs + superforecasting + Kahneman + Munger + Hegelian dialectic. Find the linchpin. Commit to the number.

Compare and selectively merge Brain directories across any two agent instances. Supports diff (see what's unique where), pull (import from another brain), and learn (bidirectional exchange).

Create lightweight user personas and usage scenarios from problem framing or raw research. Use when a user needs to clarify who they're building for beyond a basic target user description. Outputs practical personas and scenarios that inform feature priorities and UX decisions—not marketing fluff.

Surface, prioritize, and track risky assumptions before investing significant effort. Use when starting a new project, before major feature work, when feeling uncertain about direction, when the user says "I think users want...", "we assume...", "probably...", or before any build decision that hasn't been validated with real users.

Run a GitNexus production-readiness pull request review using a coordinated reviewer swarm.