論文

Analyze ML model architecture from papers and code. Use when understanding model structure for implementation.

Prepare research outputs for publication with compliance to venue rules, evidence integrity, and confidence ceilings.

[CLAUDE CODE ONLY] Leverage Gemini CLI for AI peer review, second opinions on architecture and design decisions, cross-validation of implementations, security analysis, alternative approaches, and holistic codebase analysis. Requires terminal access to execute Gemini CLI commands. Use when making high-stakes decisions, reviewing complex architecture, analyzing large codebases (1M token context window), or when explicitly requested for a second AI perspective. Must be explicitly invoked using skill syntax.

Synthesize multiple sources into coherent narratives with explicit evidence tracking and confidence ceilings.

Systematic technology and market reconnaissance for extracting actionable intelligence from repositories, papers, and competitive landscapes.

Use when writing or reviewing NIH, NSF, or foundation grant proposals. Invoke when user mentions specific aims, R01, R21, K-series, significance, innovation, approach section, grant writing, proposal review, research strategy, or needs help with fundable hypothesis, reviewer-friendly structure, or compliance with grant guidelines.

Query Obsidian vault using local HTTP API. Use when user asks about tasks, goals, experiments, journals, people, or any vault data.

Systematic debugging methodology with root cause analysis. Phases: investigate, hypothesize, validate, verify. Capabilities: backward call stack tracing, multi-layer validation, verification protocols, symptom analysis, regression prevention. Actions: debug, investigate, trace, analyze, validate, verify bugs. Keywords: debugging, root cause, bug fix, stack trace, error investigation, test failure, exception handling, breakpoint, logging, reproduce, isolate, regression, call stack, symptom vs cause, hypothesis testing, validation, verification protocol. Use when: encountering bugs, analyzing test failures, tracing unexpected behavior, investigating performance issues, preventing regressions, validating fixes before completion claims.

기술 프로젝트를 공식 문서로 정리하거나 투자자료가 필요할 때 사용. AI, SaaS, 블록체인 등 한국어 기술 백서를 작성합니다. (user)

Orchestrates multi-model LLM consensus through a three-phase deliberation protocol. Use when you need collaborative AI review, multi-model problem-solving, code review from multiple perspectives, or consensus-based decision making. Coordinates OpenAI Codex, Google Gemini, and Claude CLIs for opinion collection, peer review, and chairman synthesis.

Property-based testing with Hypothesis for discovering edge cases and validating invariants.Use when implementing comprehensive test coverage, testing complex logic with many inputs,or validating mathematical properties and invariants across input domains.Triggered by: hypothesis, property-based testing, @given, strategies, generative testing.

Property-based testing with fast-check (TypeScript/JavaScript) and Hypothesis (Python).Generate test cases automatically, find edge cases, and test mathematical properties.Use when user mentions property-based testing, fast-check, Hypothesis, generatingtest data, QuickCheck-style testing, or finding edge cases automatically.

UX research and design toolkit for Senior UX Designer/Researcher including data-driven persona generation, journey mapping, usability testing frameworks, and research synthesis. Use for user research, persona creation, journey mapping, and design validation.

Comprehensive toolkit for product managers including RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, and go-to-market strategies. Use for feature prioritization, user research synthesis, requirement documentation, and product strategy development.

Multi-agent coordination and synthesis patterns. Use when orchestrating multiple specialized agents, implementing fan-out/fan-in workflows, or synthesizing outputs from parallel agents.

Daily report creation skill. Summarizes GitHub activities, creates a draft, and posts as an Issue. Use when: - Asked to "create daily report" or "write daily report" - Asked to "summarize today's activities" - Requested to create a daily report or journal

ChatGPT-style deep research strategy with problem decomposition, multi-query generation (3-5 variations per sub-question), evidence synthesis with source ranking, numbered citations, and iterative refinement. Use for complex architecture decisions, multi-domain synthesis, strategic comparisons, technology selection. Keywords: architecture, integration, best practices, strategy, recommendations, comparison.

Multi-model AI council for actionable project advice. Leverages Gemini 3 Flash and GPT-5.2 skills in parallel, then synthesizes through an Opus Judge for stage-appropriate, non-overkill recommendations. Use when seeking architectural guidance, code review synthesis, or implementation planning.

Structure and present research findings with source authority assessment, cross-referencing, and confidence calibration. Use when synthesizing multi-source research, presenting findings, comparing options, or when report, findings, synthesis, sources, or --report are mentioned. Micro-skill loaded by research-and-report, codebase-analysis, and other investigation skills.

Systematic problem investigation through hypothesis formation, evidence gathering, and elimination methodology. Use when diagnosing failures, investigating incidents, finding root causes, or when root-cause, diagnosis, investigate, or --rca are mentioned. Micro-skill loaded by debugging-and-diagnosis, codebase-analysis, and other investigation skills.