haxudev

clarifying-intent

Turn a vague or broad request into a written, approved brief before any planning or execution happens. Use when the ask is ambiguous, wide-ranging, or expensive to get wrong — 帮我看看 / 调研一下 / 做个方案 / 搞一下 / 优化下 / 分析一下. Asks one question per turn with concrete options, a recommendation, and the consequence of each choice, inside a strict budget so the user is never interrogated. Uses what is already installed on the machine to make questions concrete instead of abstract. Produces .superclarity/<task>/brief.md covering scope, non-goals, constraints, success criteria and assumptions. Do NOT use when the user already gave a complete brief, for one-step reversible tasks, or for plain factual questions.

drafting-plans

Turn an approved brief into a step plan where every step is independently verifiable and bound to a concrete local provider with a stated fallback. Use after intent is agreed and capabilities are surveyed, for multi-step or long-running work — 写个计划 / 制定计划 / 拆解一下 / 排一下步骤 / 分几步做. Sizes step granularity by risk rather than uniformly, makes dependencies explicit, and routes work through installed specialist skills instead of improvising. Produces .superclarity/<task>/plan.md, which the user approves before any execution begins. Do NOT use before the brief is approved, for single-step tasks, or as a place to reopen scope decisions already settled in the brief.

running-plans

Execute an approved plan step by step with checkpoints, an append-only journal, and provider fallback when a tool fails or is missing. Use when a plan exists and the user says to start — 开始 / 执行 / 跑吧 / 继续 / 动手. Verifies each step against its own criterion instead of assuming success, stops and asks rather than silently rerouting when reality diverges, and refuses to retry a failing action more than twice without diagnosing it. Handles long-running work by reporting and yielding rather than waiting in silence. Appends to .superclarity/<task>/journal.md. Do NOT use without an approved plan, and do NOT use to expand scope beyond it.

superclarity

Entry point and router for a clarify-plan-execute workflow built for long-horizon work tasks. Load this first for any multi-step task, when the user asks for an approach or a plan (规划 / 计划 / 做个方案 / 拆解一下 / 怎么做), or when resuming interrupted work (继续 / 接着做 / 上次做到哪了). Detects which phase applies, loads a domain profile when one fits, owns the .superclarity/ state convention, and reconstructs state after a session ends or context is compacted. Routes to clarifying-intent, surveying-capabilities, drafting-plans, running-plans, and verifying-outcomes, which are phases of this one workflow rather than independent tools. Do NOT use for single-step requests, plain factual questions, or coding-specific methodology.

surveying-capabilities

Survey what the local machine can actually do and bind each abstract capability a task needs to a concrete provider — an installed skill, an MCP tool, a CLI, or a subagent — before any plan is written. Use before planning multi-step work, when you need to know what tooling exists (有什么工具 / 本机能力 / 装了哪些技能 / 能不能做), or when a step fails because something is missing. Introspects your own context first at zero cost, then probes only what the task requires. Produces .superclarity/environment.md and .superclarity/<task>/capabilities.md, including an explicit list of capability gaps. Do NOT use for trivial single-step tasks, and do NOT use to enumerate the whole machine when the provider is already confirmed.

verifying-outcomes

Gather evidence before claiming that work is finished, delivered, correct, or fixed. Use immediately before reporting completion — 完成了吗 / 好了没 / 交付 / 验收 / 检查一下 / 确认下. Requires a named artifact or a direct observation behind every claim, checks each plan step against its own stated criterion, and forces coverage gaps to be disclosed together with their cause and their effect on the conclusion. Enforces the rule that "we did not observe X" must never be reported as "X does not exist". Produces .superclarity/<task>/report.md. Do NOT use it to redo work that failed — fix the step first, then verify. Never skip it because the task looked simple or because the tools returned without errors.