phj128

Auto-loop execution workflow with quality gates. Use when starting any non-trivial implementation task. Provides automatic task decomposition, code implementation, testing (L1-L4), and iterative quality gates until completion. Invoke with /autoworker.

Record progress to subtask: Phase completion (from autoworker:code) or test results (from autoworker:test). Auto-detects upstream type from conversation context. Ends by calling autoworker:dispatch.

Implement ONE pending Phase from subtask plan. Only write code, do not mark checkboxes or run tests. Called by autoworker:dispatch. Ends by calling autoworker:checkpoint.

Structured deep discussion for Plan Mode. Runs inside EnterPlanMode to ensure thorough questioning before writing a plan. Covers motivation, assumptions, design, acceptance criteria. Call this immediately after entering Plan Mode for any non-trivial task.

Read subtask.md checkbox state and route to next skill. The ONLY routing point in the execution loop. Called after autoworker:checkpoint, autoworker:gate-check, autoworker:subtask-update, autoworker:subtask-plan, or when resuming after context loss. When lost, call autoworker:dispatch.

Final quality gate before reporting task completion (Gate 3). Fills confidence assessment, runs supplementary verification for <95% items, completes self-check checklist. Writes PASS/FAIL result to subtask.md, then calls autoworker:dispatch for routing.

Create subtask document (first half): user confirmation, goals, assumptions. Auto-runs assumption verification experiments and fills in results. Call after Gate 1.1 (user confirmation) is done, before writing any code.

Complete subtask verification plan: upstream traceability table + L1-L4 test plan + self-check. Call after autoworker:subtask-init. Makes subtask ready for code implementation.

Memory management for personal info, preferences, and notes. Activate when user says: 记住, 我的XXX是, 别忘了, remember, 笔记, 日记, OR when user corrects personal info, shares preferences, or asks to note something down.

Personal secretary for managing schedules, tasks, goals, notes, and reports via Feishu Bitable. Activate when user mentions: schedules, tasks, goals, reminders, notes, reports, weather, location, OR any time/date references (明天、下周、X点、几号), plans, events, deadlines, appointments, OR phrases like "要去做X", "得做X", "有个X", "打算X". IMPORTANT: All reminders MUST use planner_schedule, NEVER use cron for reminders.

Trigger automated literature surveys on research topics. When the user says "调研 XXX", "survey XXX", "帮我调研一下 XXX", or asks for a literature review on a topic, first check existing surveys with list_surveys, then confirm with user, then trigger_survey. Also supports follow-up investigations on existing surveys with followup_survey.

搜索淘宝商品、查看详情、加入/移除购物车

在小红书发布图文帖子（宣传推广用），管理已发布笔记