Produce publish-ready Chinese and English writing packages across WeChat articles, Medium/Substack essays, research notes, founder memos, op-eds, speeches, data storytelling, statistical graphics, and platform-ready HTML. Use this unified workflow for writing, rewriting, sourcing, lowering AI feel, creating visuals…
INVOKE BEFORE EVERY NON-TRIVIAL TASK — before writing code, before using any tool, before answering. Do not skip. Produces the required Skill + Agent + Model for the task. Routing engine for 2,700+ skills.
End-to-end pipeline: pull a task from Redmine by ID, sanity-check and impact-assess it against the codebase before touching anything, implement it with the Claude CLI, verify the result in a real browser via the Claude Chrome extension (claude-in-chrome), and keep the Redmine ticket in sync throughout (in-progress…
Compress one Claude Code JSONL session with strict active-branch isolation, model-authored semantic summaries by default, recent raw context for rewind, validated compact-style output, transactional backup/replacement for one live .claude/projects file, and an independent byte-preserving Read.pages compatibility…
Audit and fix any website (new, in development, or already live) against the organization's mandatory engineering and web standards, then scaffold or repair the gaps after the user approves. Use this whenever the user wants an SEO, GEO, AEO, accessibility, performance, structured data, schema, sitemap, robots.txt…