claude-everything-Workflow

Stress-test a plan, design, decision, or idea through a one-question-at-a-time interview. Use when the user invokes /grill, says grill me, asks to be challenged, 拷问, 压力测试, or wants a plan stress-tested; also use when progress is blocked by an unresolved user-owned decision whose alternatives materially change the outcome after high-risk classification is ruled out. Do not use merely because work is complex, high-risk, new, or spans multiple files.

Use when the user explicitly requests Brainstorming, a design spec, Spec Gate, or the full Superpowers workflow; also use automatically for costly-to-reverse high-risk work involving architecture or service boundaries, public-contract compatibility, authentication or authorization, persistent data/schema migration, or irreversible external side effects. Do not use for ordinary behavior changes or merely because work is new, complex, or spans multiple files.

Chinese workflow for surfacing systematic fact, evidence, context, and blind-spot gaps before, during, and after agentic work. Use when the user explicitly asks for a blind-spot scan, unknown unknowns, prototypes, reference mapping, implementation notes, explainers, or quizzes; when phrases like "I'll know it when I see it" or "teach me this domain" expose unstated assumptions; or when safe progress is blocked by evidence gaps that require multiple low-cost probes. Do not use merely because work is complex, high-risk, long-running, or spans multiple files.

Use when starting or routing a non-trivial task in this workflow harness, when the user references Superpowers, or when deciding which skill, command, rule, or agent should govern the work. Establishes skill invocation discipline: check relevant process skills before acting, follow user/project instructions first, and verify before completion.

Use when you have a spec or requirements for a multi-step task, before touching code

用于功能验收、回归验证、确认修复是否生效，以及需要用真实界面、视频或日志证据判断用户流程是否正常的任务。适用于“验收一下”“测一下”“确认修复”“给我可复核证据”等请求。

为 subagent、代码探索、RAG 式检索和大仓库上下文收集设计迭代检索闭环。用于初始上下文不明确、一次性读全仓会污染上下文、子代理不知道该读哪些文件、或搜索结果需要逐轮收敛时。

Use when executing an approved implementation plan with mostly independent tasks in the current session, when the user has explicitly approved SDD-style task execution or commit-per-task workflow. Uses task briefs, implementer report files, review diff packages, and a .superpowers/sdd progress ledger.

Use after an approved implementation plan exists and the user wants execution. Runs the plan task-by-task with checkpoints, optional project-agent loop, tests, reviews, and final verification without expanding scope.

Use before claiming work is complete, fixed, passing, ready for PR, or moving to the next task. Requires fresh verification evidence from this turn, with exact commands, results, skipped checks, and remaining risk.

基于直觉的学习系统。用于配置或审查 Hook 观察、project/global instinct、置信度、项目推广、迁移和演化为 skills/commands/agents 的流程。

Use before implementing substantial plans when work should be isolated from the current checkout, especially multi-step features, risky refactors, parallel agent work, or when the current worktree has unrelated user changes.

新功能、bug 修复、重构或行为变化需要测试先行时使用。强调先写失败测试、确认失败原因、最小实现和保持测试绿色。

Use when encountering any bug, failing test, flaky behavior, or unexpected result before proposing fixes. Keeps debugging lightweight but root-cause driven.