doctor-triage
Perform breadth-first hypothesis surfacing and prioritization across all ownership zones, without commitment. This is not diagnosis and not investigation.
Perform breadth-first hypothesis surfacing and prioritization across all ownership zones, without commitment. This is not diagnosis and not investigation.
Query Chrome browsing history with natural language. Filter by date range, article type, keywords, and specific sites.
Community superstitions - unverified observations from pattern development. Use when encountering undocumented edge cases or framework quirks not in official docs. Verified knowledge should be upstreamed to labs docs.
Self-driven skill selection system that uses internal curiosity asking (self-questioning) to analyze user requests, infer context from available information, and automatically recommend the most appropriate skills. Use when (1) User requests are ambiguous or unclear, (2) Multiple skills could potentially match a request, (3) User needs help discovering available skills, (4) Understanding user context is needed before recommending skills, or (5) User asks "what skills are available" or "which skill should I use".
Classify problems into Cynefin Framework domains (Clear, Complicated, Complex, Chaotic, Confusion) and recommend appropriate response strategies. Use when unsure how to approach a problem, facing analysis paralysis, or needing to choose between expert analysis and experimentation.
Expert in generating executive briefing notes (1-2 pages, decision-focused) for infrastructure acquisition projects including issue framing, background context, financial analysis, recommendation development, risk assessment, and action planning. Use when preparing board submissions, executive decision memos, or approval requests for property acquisitions. Key terms include briefing note, executive summary, decision memo, board approval, acquisition recommendation, risk assessment, action items
The master skill for generating technical specifications. Identifies project technology and delegates deep analysis to specialized sub-skills.
Create a concise plan. Use when a user explicitly asks for a plan related to a coding task.
Comprehensive feature artifact analysis for loading and understanding complete feature context. Use when needing to: (1) Load all feature documentation before implementation, (2) Build mental model of feature requirements and architecture, (3) Prepare context for downstream operations like checklist generation or task execution, (4) Analyze feature completeness and artifact availability. Triggers on: analyze feature, load feature context, prepare feature, check feature prerequisites, understand feature scope.
Refining issues with technical context and structured details. Use when expanding a brief bug, feature, or refactor description into a detailed issue suitable for developers and AI agents.
Transform vague ideas into implementation-ready specifications through structured interviewing. Use when user describes a new feature/product idea, has a problem to solve, needs to document requirements, or says things like "帮我梳理需求", "interview me about this", "细化这个想法", "spec out this project". Produces two artifacts - intent.md (technical spec for code agents) and overview.md (human-friendly summary for team).
Builds incident/PCN evidence packs with timelines, appeal drafts, corrective actions, and follow-up monitoring. USE WHEN handling PCNs or incidents needing documentation.
Generate a session briefing from development memory (events.jsonl, sessions.jsonl). Shows recent timeline, open questions, and suggested focus areas.
Resources for conversational interviews to create learner profiles. Used by project-interviewer agent during /init.
Domain-specific configuration profiles for learning resource creation. Defines search strategies, special fields, terminology policies, and content structures for different academic domains: technology, history, science, arts, and general. Use when researcher or writer agents need domain-adapted behavior.
Create publication-quality scientific diagrams using AI with smart iterative refinement. Uses AI quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Research-driven critique and enhancement of Amelia architecture or ideas docs. Use with GPT-5.2 when given a design/architecture doc to analyze concepts, find sources, and propose improvements plus OSS candidates.
Explore complex, multi-faceted topics requiring deep understanding through a three-round iterative strategy with parallel subagents.
Manage learned patterns - list, view, archive, boost or penalize confidence. Use when you want to see what patterns Claude has learned, review pattern effectiveness, or manage the pattern library.
Use when saving or retrieving important patterns, decisions, and learnings across sessions. Triggers on keywords like "remember", "save pattern", "recall", "memory", "persist", "knowledge base", "learnings".
Teach Claude a new pattern, preference, or convention explicitly. Use when you want to save a correction, preference, or coding pattern for future sessions. Triggers on keywords like "remember this", "always do", "never do", "learn this pattern", "/learn".
Multi-agent debate orchestration for Architecture Decision Records. Automatically triggers on ADR create/edit/delete. Coordinates architect, critic, independent-thinker, security, analyst, and high-level-advisor agents in structured debate rounds until consensus.