zhijunio

Use when creating or revising AGENTS.md for a repository—agent operating context, commands, and conventions. Not README.md, CONTRIBUTING, or full API documentation unless the user asks.

Use when creating or revising README.md for a project—comprehensive human onboarding for developers. Not AGENTS.md, CONTRIBUTING, or full API documentation unless the user asks.

Whole-repo (or named-scope) audit for over-engineering only: ranked cuts to delete, simplify, or replace with stdlib/native. Use for "audit for over-engineering", "what can I delete", "find bloat", "ponytail-audit". One-shot report; does not apply fixes. Not a full Standards health scan or increment quality report.

Use when an approved plan is ready for test-first implementation, or when review findings must be fixed without changing accepted behavior. Not spec/plan revision unless blocked.

Broad-scope Standards scan for improvement candidates. Use when the user wants a repo, module, area, or branch health/improve pass — hotspot-first, four-dimension report, pick a candidate next. Not increment delivery review.

Use when an approved specification needs decomposition into testable vertical slices before implementation. Not clarifying product behavior or writing code unless the user asks.

Two-axis Standards/Spec review of changes since a fixed point. Use when the user wants a branch, PR, or "review since X" quality report. Not whole-repo improve scan.

Use when a software change needs a durable behavior contract, scope, acceptance criteria, and technical constraints before implementation planning. Not implementation, open-ended design interviews, trivial one-line fixes, or fully specified direct edits.

Read-only codebase health audit — MECE pillars architecture (A1–A6), code (C0–C3), security (S1), verification (V1–V2), dependencies (D1), operations (O1). Chat-only P0/P1/P2 roadmap; effort snapshot, standard, or deep; variants simplicity, anti-pattern, branch, direction, cicd, and pillar-scoped review. Use for codebase audit, architecture review, security hygiene, CI/CD review, over-engineering and anti-pattern scan; not article writing, topic learning, implementation edits, or plans/.

Guard long, ambiguous, or stateful AI-agent work from drift. Use for multi-step implementation, compaction at phase boundaries, task contracts, handoff/resume, or work spanning many tool calls, files, or sessions — not single-shot article writing, topic learning, or codebase audit.

Remove AI-writing tells from finished prose only — neutral tone, preserve facts and structure. Optional deep QA (tell-focused L1–L4). Use for 去AI味, humanize, de-AI polish, 润色; not 审校定稿 with author voice-default, publish-ready writing pipeline, blank-page drafts, or chapter reorder.

Fetch a random classical Chinese poem line from the Jinrishici HTTP API and format with standard Chinese attribution punctuation (author, title). Use for daily poem, briefing garnish, 今日诗词.

Log in via Keep Open API and fetch runs into Garmin-compatible running.json (VDOT, training load, period stats, optional per-km segments). Use for Keep run sync, fetch_keep_run, running.json, or exporting Keep running data.

Audit, design, categorize, distribute, and measure agent skills using lessons from Anthropic's Lessons from building Claude Code: How we use skills. Use when reviewing an existing skill, deciding whether a workflow deserves a skill, planning a skill library, turning team knowledge into skills, choosing skill categories, writing trigger descriptions, designing progressive disclosure, or planning skill marketplace and usage measurement.

Fetch URL or PDF as clean Markdown for reading, citation, or archive (读). Modes convert (default), summarize, save, preview. Routes CN platforms, GitHub, PDF, proxy cascade, MCP fallback. Use for 读链接, 抓取正文, 提取文章; not article drafts, topic learning workspace, or codebase audit.

Article and document writing lifecycle (写) — ideate, gather, transcribe, compose, refine with author voice. Long-form, tutorials, scripts, talks, Xiaohongshu. Default voice in voice-default.md. Use for 写文档, 写文章, 选题, 审校定稿, publish-ready; not neutral-only de-AI on finished text, URL ingestion, topic learning, or codebase audit.

Migrate Spring Boot 2.7.x applications to Spring Boot 3.x with a recipe-first OpenRewrite workflow, then complete manual compatibility fixes and verification. Use only when the project is already on Boot 2.7.x; projects on 2.6 or earlier may fail—upgrade to 2.7.x first. Covers pom.xml/build.gradle, javax-to-jakarta, Spring Security config, dependency alignment, Dockerfile Java base image.