菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
| name | flowguard |
| description | 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. |
Lifecycle guard for work that can drift, lose context, or compound errors. Routes first, verifies live state, runs bounded loops, leaves resumable handoff.
Does not replace the user's chosen workflow (writing, learning, audit, etc.) — only wraps execution discipline.
| Route | Use when |
|---|---|
execute_direct | Goal, constraints, done-when clear; small scope |
plan_first | Many files/sessions, migrations, risky sequencing |
clarify_first | Missing goal, files, constraints, or destructive permission |
Wrong assumption → large rewrite, prod risk, or data loss → clarify_first.
AGENTS.md for editable paths./path/to/flowguard/scripts/workflow_state_snapshot.sh /path/to/target/repo
State compact preflight (references/state-contract.md § Preflight). High-risk kickoff → expand with references/task-contract.yaml.
| Phase | Read |
|---|---|
| Context compaction | references/strategic-compact.md |
| Prioritize findings / regression | references/scoring-matrix.md, references/review-template.md |
| Implement loop | references/execution-loop.md |
| Handoff / resume | references/state-contract.md |
bash -n flowguard/scripts/workflow_state_snapshot.sh
scripts/workflow_state_snapshot.sh — read-only repo snapshotreferences/state-contract.md — preflight, checkpoint, handoff, resumereferences/strategic-compact.md — boundary compactionreferences/execution-loop.md — loop, verification, multi-agentreferences/task-contract.yaml — high-risk kickoff checklistreferences/scoring-matrix.md — finding priorityreferences/review-template.md — regression template基于 SOC 职业分类
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/.
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.
