Research

Navigate between concrete details and abstract principles to find the thinking altitude where problems become solvable. Use when: (1) asked to zoom in on specifics, zoom out to big picture, or move between abstraction levels, (2) stuck in implementation details without seeing the pattern or floating in abstractions without actionable steps, (3) discussion needs grounding in concrete examples or needs elevation to identify transferable patterns, (4) explaining concepts to audiences at different expertise levels who need different altitudes to understand.

Execute implementation plans using strict TDD workflow with quality gates. Fifth phase of research-discussion-specification-plan-implement-review workflow. Use when: (1) Implementing a plan from docs/workflow/planning/{topic}.md, (2) User says 'implement', 'build', or 'code this' after planning, (3) Ad hoc coding that should follow TDD and quality standards, (4) Bug fixes or features benefiting from structured implementation. Writes tests first, implements to pass, commits frequently, stops for user approval between phases.

Automatically use Perplexity search for personalized context enrichment. Use when facing unfamiliar technologies, decision points, learning questions, or preference-dependent choices.

List, search, and reference prior reasoning sessions to build on previous work Use when: (1) asked to reference or build on prior reasoning sessions, (2) At the start of `/reason` or `/reason-session` to check for relevant prior work, (3) When the user mentions something they worked on before, (4) When you need context about past decisions in this repository, (5) Before starting work that might duplicate prior reasoning, (6) When synthesizing insights across multiple reasoning sessions

Use when creating argc commands, uncertain about argc syntax, or learning argc progressively - provides syntax quick reference, common mistakes with fixes, and progressive examples from simple to complex

This skill should be used whenever users need YouTube video scripts written. On first use, collects comprehensive preferences including script type, tone, target audience, style, video length, hook style, use of humor, personality, and storytelling approach. Generates complete, production-ready YouTube scripts tailored to user's specifications for any topic. Maintains database of preferences and past scripts for consistent style.

Apply Chiral Narrative Synthesis (CNS) framework for contradiction detection and multi-source analysis using Tinker API for model training. Use when implementing CNS with Tinker for fine-tuning models on contradiction detection, training on SciFact/FEVER datasets, or building multi-agent debate systems for narrative synthesis.

Extract and structure data from documents about the illegal antiquities trade, including dealers, collectors, artifacts, locations, and relationships. Use when processing news reports, academic articles, legal documents, encyclopedia entries, or research materials pertaining to looted artifacts, antiquities trafficking, provenance research, or cultural heritage crimes. Returns structured JSON with entities (persons, organizations, artifacts, locations) and their relationships.

Master requirements gathering techniques including interviews, workshops, observation, and documentation for effective requirement elicitation.

Research GitHub, GitLab, and Bitbucket repositories using DeepWiki MCP server. Use when exploring unfamiliar codebases, understanding project architecture, or asking questions about how a specific open-source project works. Provides AI-powered repo analysis and RAG-based Q&A about source code. NOT for fetching library API docs (use fetching-library-docs instead) or local files.

Use when you need to research, analyze, and plan technical solutions that are scalable, secure, and maintainable. | Sử dụng khi: nghiên cứu, tìm hiểu, khám phá, học về, tài liệu.

Manifest schema definitions for all LeanOS artifacts. Reference skill forvalidating manifest structure, understanding artifact formats, checkingcross-references. Use when: validating outputs, debugging schema issues,understanding data flow between skills.

Manage cognitive load by explicitly identifying what needs to be held in active focus and externalizing complex state. Use when: (1) explicit request to track multiple elements or manage cognitive load, (2) reasoning involves tracking five or more distinct elements simultaneously, (3) switching between contexts or returning from tangents requires context restoration, (4) responses reference earlier information that wasn't carried forward or reasoning restarts without building on prior context.

MoAI-ADK's foundational principles - TRUST 5, SPEC-First TDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows

Monitor application performance using the RED methodology (Rate, Errors, Duration) with Observe. Use when analyzing service health, investigating errors, tracking latency, or building APM dashboards. Covers when to use metrics vs spans, combining RED signals, and troubleshooting workflows. Cross-references working-with-intervals, aggregating-gauge-metrics, and analyzing-tdigest-metrics skills.

Token-efficient library API documentation fetcher using Context7 MCP with 77% token savings. Fetches code examples, API references, and usage patterns for published libraries (React, Next.js, Prisma, etc). Use when users ask "how do I use X library", need code examples, want API syntax, or are learning a framework's official API. Triggers: "Show me React hooks", "Prisma query syntax", "Next.js routing API". NOT for exploring repo internals/source code (use researching-with-deepwiki) or local files.

Use when GitHub issue lacks scope, has ambiguities, or needs technical definition - researches codebase, identifies gaps, presents options with recommendations, updates issue description (project, gitignored)

Transform specifications into actionable implementation plans with phases, tasks, and acceptance criteria. Fourth phase of research-discussion-specification-plan-implement-review workflow. Use when: (1) User asks to create/write an implementation plan, (2) User asks to plan implementation after specification is complete, (3) Converting specifications from docs/workflow/specification/{topic}.md into implementation plans, (4) User says 'plan this' or 'create a plan' after specification, (5) Need to structure how to build something with phases and concrete steps. Creates plans in docs/workflow/planning/{topic}.md that implementation phase executes via strict TDD.

Conduct research, synthesize information, and create structured summaries

结构化的网络研究方法，帮助进行全面的信息收集和分析