agent_skills

Stress-test and refine an OpenSpec change through a structured grilling session. Use when the user wants Codex to interrogate, complete, or improve an existing or planned OpenSpec change, maintain a visible problem panorama and progress map, resolve unclear requirements and design decisions one question at a time, and write confirmed decisions back into proposal.md, design.md, specs, and tasks.md.

Agent-first graph-backed knowledge wiki builder with a self-contained CLI. Use for Graphwiki init/build/ingest/update, source indexing, semantic entity and relationship extraction, generated wiki pages, graph JSON/HTML explorer, evidence line ranges, query/explain question answering, synthesis pages, HTML reports, adding confirmed entity types, applying patches, cleanup, validation, tasks, and SQLite cache generation.

Build and expand an insight-ready raw-material layer by discovering page-level sources, deduplicating them with an internal pre-crawl link index, capturing raw Markdown, verifying metadata in place, and keeping ingest/register state aligned. Use for additive source harvesting, raw webpage capture, source registry maintenance, source/ingest tracking, source/raw downloads, and in-place verification rather than final synthesis.

Conduct structured deep research on any topic — security threat analysis, technology trend mapping, ecosystem analysis, market forecasts, or law/policy compliance research. Produces a multi-part report grounded in confirmed sources with no premature design assumptions. Use when asked to "deepresearch", "research deeply", or produce a comprehensive multi-part research report. Auto-detects whether the topic calls for security-focused, tech-trend-focused, or law/policy-focused structure.

Generate a structured, illustrated Q&A HTML document from the current conversation. Scans the conversation for conceptual questions the user asked and Claude's answers, then produces a self-contained HTML file with styled cards and SVG diagrams for technical/architectural topics. If a Q&A HTML file already exists in the current project directory, appends the new Q&As to it instead of creating a new file. Trigger this skill whenever the user asks to "generate Q&A", "create Q&A from conversation", "save Q&A", "document our Q&A", "turn this chat into Q&A", or anything suggesting they want the conversation's questions and answers captured as a document — even if they don't use the exact phrase "Q&A skill".

Use when the user asks to export a local HTML file, web page, or invitation page to a single-page PDF, a no-pagination PDF, a long PDF with auto-calculated height, or a PDF without headers and footers. Trigger on phrases like 单页 PDF, 不分页, 自动计算长度, 长图 PDF, 去掉页眉页脚, export HTML to single-page PDF, or print page to one PDF page.

Create high-quality draw.io diagrams with better layout for architecture diagrams, flowcharts, block diagrams, system maps, data flows, and complex connection-heavy visuals. Use when draw.io routing becomes messy, edges overlap, blocks cross too much, or the user wants cleaner diagram layout than the default drawio skill.

Multi-session AI coding history analysis across Copilot CLI, Claude Code, and VS Code sessions for a project. Collects raw logs, normalizes them into a unified format, and produces an actionable report covering recurring bugs, tool-error patterns, missing tests, refactoring opportunities, process improvements, and documentation gaps. Supports incremental analysis — only new sessions are processed on repeat runs, with persistent storage at ~/.retro/<project>/. Use this skill whenever the user asks to review, analyze, or get a retrospective on AI coding sessions, chat history, agent logs, copilot sessions, what went wrong across sessions, what patterns the AI made, or wants a report on how the AI performed on a project. Also trigger for phrases like "look at my sessions", "analyze my chat history", "what bugs recurred", "review my AI sessions", or "how has the AI been doing".

Analyze SpecStory chat history exports to identify problems, friction points, and areas needing improvement. This skill should be used when the user wants to understand what went wrong in their agent interactions. Use when the user asks to "analyze chat history", "what went wrong", "review agent sessions", or "find problems in conversations".

Analyze Polymarket prediction market data to provide investment insights for Chinese concept stocks (中概股) and A-shares. This skill should be used when the user asks about Polymarket data, prediction markets, A-share (A股) investment advice based on prediction market sentiment, or 中概股 correlations.

Helps users scaffold new projects with production-ready files: README.md, AGENTS.md (agent memory), and CI/CD pipelines (GitLab CI, GitHub Actions, or both). Handles tech stack selection, coding standards ingestion, quality level configuration (demo vs. production), and SDD framework integration (OpenSpec, SpecKit, or GSD). Documentation is generated in Chinese (中文) by default, with support for other languages upon request. Use this skill whenever a user wants to create a new project, initialize a repository, set up CI/CD, choose a spec-driven development workflow, scaffold project files, or asks about project structure and agent memory files. Even if the user only asks about one part (e.g., "set up CI/CD" or "create AGENTS.md"), use this skill — it ensures all files stay consistent with each other.

Act as a Product Manager who gathers requirements and orchestrates Claude Code using OpenSpec protocol. Install proper skills, delegate to Claude Code in background mode, and validate completion while remaining responsive to user messages.

Act as a Product Manager who manages Claude Code as an automated development team. Understand requirements, configure development agents with proper skills, assign tasks using CLI automation mode, validate deliverables, and ensure quality before handover. Use this when users need complex development work managed by automated Claude Code agents.

This skill helps users get started with existing (brownfield) projects by scanning the codebase, documenting structure and purpose, analyzing architecture and technical stack, identifying design flaws, suggesting improvements for testing and CI/CD pipelines, and generating AI agent constitution files (AGENTS.md) with project-specific context, coding principles, and UI/UX guidelines.

This skill provides a systematic approach for investigating and fixing bugs and issues in the codebase. Use this skill when users report bugs, unexpected behavior, test failures, or request fixes for specific issues. The skill guides through issue registration, root cause analysis, impact assessment, minimal code changes, quality validation, and E2E testing.

This skill composes project AGENTS.md constitution files into openspec/config.yaml to inject quality validation gates into OpenSpec workflows. Use this skill when initializing openspec for the first time in a project or when AGENTS.md files are updated. The skill ensures openspec artifacts are validated against project-specific quality criteria from constitutions.

This skill reviews the current chat session and GitHub Copilot instructions to identify user-reported issues that should become new lessons, detect violations of existing instructions, and update instructions accordingly to prevent future mistakes.