mymx2/dyc
m2-plugins/plugins/dyc — eight core engineering workflow skills for AI agents: think, check, hunt, ui, read, write, learn, and health, with additional skills for extended capabilities.
Reviews code diffs, PRs, issue queues, release readiness, commits, pushes, publishing, project audits, domain conformance (test coverage, security, performance, observability), and document or prose audits against the writing rulebook. Use when users ask for code review, issue or PR triage, release gates, publishing follow-through, project audits, security/performance/readiness review, or doc proofreading. Not for debugging root causes or writing new prose.
Drives a real Chrome browser through the chrome-devtools-mcp MCP server or its CLI for page automation, network and console analysis, emulation, and extension testing. Use when a task needs operating a live browser: navigating, snapshotting the accessibility tree, interacting by element uid, capturing screenshots, traces, or heap snapshots, or fixing the MCP server setup itself. Not for diagnosing application logic root causes (use hunt) or judging visual quality (use ui).
插件与技能的全生命周期管理：基于 Agent Plugins Spec 创建标准插件、通过 extensions + init 模式适配多厂商（Claude Code / Qoder / Codex），以及发现、安装、编写、校验技能。Use when users ask to create a plugin, scaffold multi-vendor plugin, write plugin.json, generate init.ts, find/install skills, or author/validate SKILL.md. Not for runtime debugging of deployed skills (route to hunt) or reviewing plugin code quality (route to check).
Runs a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask to audit Claude, Codex, Pi, agent instructions, MCP or hooks, verifier coverage, or AI-maintainability drift. Not for debugging application code or reviewing PRs.
Finds root cause before applying fixes for errors, crashes, regressions, failing tests, and defects proven against a known-good reference (prior version, build, or "good" screenshot). Use when users report errors, crashes, broken behavior, failing tests, or a used-to-work state that now fails. Not for code review (route to check) or a first-impression visual complaint with no working baseline (route to ui).
Runs a six-phase research workflow that turns unfamiliar domains, source bundles, or collected material into publish-ready output. Use when users ask to research, study, deep-dive, compile sources, synthesize unfamiliar material, or turn a source bundle into a coherent reference. Not for quick lookups or single-file reads.
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.
Generates a DeepWiki-style repository analysis report from repository structure, config, and dependencies, producing a single REPOWIKI.md with Mermaid diagrams and source-file references. Use when the user asks for a repository report, project documentation, codebase analysis, or wiki generation. Not for answering one-off questions about a repo, code review, or refactoring.
Turns rough ideas into approved, decision-complete plans with validated structure before coding. Use when users ask for planning, architecture, design direction, feasibility, value judgment, or whether a feature is worth doing before implementation, or triaging a bundle of mixed requests/feedback into accept/reject buckets. Not for bug fixes or small edits.
Produces distinctive, production-grade UI for pages, components, visual interfaces, typography, screenshot-driven polish, and DESIGN.md token contracts (lint, diff, export via the @google/design.md CLI). Use when users ask for UI, page, component, frontend, typography, design-system files, or a first-impression complaint that a screen looks unclear, ugly, or inconsistent. Not for backend logic or closing a delta against a known-good previous version (route to hunt).
Rewrites and polishes prose in Chinese or English, removes AI-like wording, and authors technical documentation with the writing rulebook. Use when users ask to rewrite or polish supplied prose, remove AI-like wording, draft release notes or launch/social copy, localize copy, or write or revise technical docs and coding standards. Not for code comments, commit messages, or auditing docs against the rulebook (use check — check flags rule violations, write applies the wording fixes).