Run a bounded implement-attack-repair loop for a user-specified task. Use when work needs repeated independent criticism: perform the task, dispatch a fresh attacker, verify significant findings, repair them, and stop on a clean attack or the user's round limit.
中文简介正在准备中。当前显示原文说明。
Explain a file, error, design, diff, or concept like a helpful engineering colleague: grounded in evidence, concise, and with useful follow-up threads. Use when the user asks for a clear explanation of the current work or codebase.
中文简介正在准备中。当前显示原文说明。
Turn one user criticism into a principle-level fix: find the violated principle, every similar occurrence, and fix the shared cause. Use only when the user explicitly invokes expand, $expand, /up:expand, or /skill:expand.
中文简介正在准备中。当前显示原文说明。
Use when a task needs an isolated checkout. Verify the worktree location, keep mutable environments and build outputs local, and run only authorized setup and checks.
中文简介正在准备中。当前显示原文说明。
Contract for hands-off mode — the ultrapack workflow variant that minimizes user prompts after Design, takes the safest reversible path, and logs every auto-choice for one end-of-task review. Referenced by the workflow entry point and child skills (udesign, uplan, uexecute, uverify, ureview). Read when the task file's **Mode:** header is `hands-off`.
中文简介正在准备中。当前显示原文说明。
Use when the user explicitly asks to launch and supervise a job. Require an authorized launch, monitoring, recovery, and teardown contract. Detect failures without inventing permission to restart or spend money.
中文简介正在准备中。当前显示原文说明。
Orchestrate the full Ultrapack workflow in Codex and Pi: create or resume a task file, design, plan, execute, verify, review, and validate the observable goal. Use when the user asks to build, fix, or deliver a non-trivial change with the complete workflow.
中文简介正在准备中。当前显示原文说明。
Quickly design and plan, wait for plan approval, then execute sequential phases with focused verification and a manual try. Use when a task needs more than a prompt but does not need the full ultrapack make workflow, or the user asks for a quick plan.
中文简介正在准备中。当前显示原文说明。
Extract durable, non-obvious lessons from the current dialogue and route them to project guidance, memory, documentation, or the active task conclusion. Use when the user asks to reflect on a session or preserve learnings.
中文简介正在准备中。当前显示原文说明。
Break a failed implementation loop by tracing attempts, identifying the real blocker, and proposing a materially different direction before further changes. Use when repeated fixes or investigations are not converging.
中文简介正在准备中。当前显示原文说明。
Produce a compact, zero-context handoff for the current Codex or Pi work and save it to the requested destination, active task conclusion, or a new task summary file. Use when the user asks to preserve progress for a later session.
中文简介正在准备中。当前显示原文说明。
Use when implementing deterministic, reusable code where regressions would warrant a CI red light. Enforces RED-GREEN-REFACTOR. Applicability rule and skip conditions inside.
中文简介正在准备中。当前显示原文说明。
Manually test the latest change with one realistic positive case and one adversarial negative case, capturing evidence before any further fix. Use when the user asks for a quick confidence check or wants to test a recent implementation.
中文简介正在准备中。当前显示原文说明。
Use on any bug, test failure, or unexpected behavior before proposing a fix. Enforces four-phase root-cause investigation — reproduce, pattern-match, hypothesize, fix — with a hard rule against symptom patches.
中文简介正在准备中。当前显示原文说明。
Use before any creative work — features, components, behavior changes. Turns an idea into a validated spec with explicit tradeoffs and unknowns, and splits scope into multiple tasks if it's too large. Output is the `## Context` and `## Design` sections of the task file.
中文简介正在准备中。当前显示原文说明。
Use when writing or editing documentation — project docs, CLAUDE.md, READMEs, SKILL.md, docstrings, inline comments. Auto-triggers on `.md` files and docstring edits. Enforces lead-with-why, kill stale content, lists over tables, no aspirational sentences.
中文简介正在准备中。当前显示原文说明。
Use to implement an approved plan. When the plan declares `### Interface graph`, derives waves by topo-sort over `[blocks]` IF edges only — non-blocking IF edges (the default) put producer and consumer in the same wave, since the IF declaration is sufficient context. Edits inline when only one implementer would fire (single phase or serial fallback). Runs plan-diff check and consistency sweep after each commit. Forbids silent fallbacks and mutation of external spec/design docs. Dispatches the planner skill when deviations invalidate the plan.
中文简介正在准备中。当前显示原文说明。
Use after design to turn a validated spec into a lean implementation plan. Outputs the `## Plan` section of the task file — files, line numbers, class/method names, invariants, test strategy, order. Ends with a scope-creep / simpler-way check.
中文简介正在准备中。当前显示原文说明。
Use after verify passes for the future maintainer's audit — sit in the chair of the person who'll touch this code in 3-6 months and ask "what will bite us later?" at the decision level. Surfaces wrong abstractions, load-bearing-but-unobvious shapes, next-change traps, drift from surrounding code. Raises a Scope flag if the whole change looks like the wrong call. Delegates an independent, critical review and fills the task file's `## Conclusion`.
中文简介正在准备中。当前显示原文说明。
Use after execute to attack the change and demonstrate how it's broken. Default stance — the change is broken, prove and demonstrate it. Builds an attack checklist (happy-path / negative / invariant / interface hypotheses), runs each freshly, smokes the end-to-end, writes a short summary to the task file's Verify section, loops back to execute on any demonstrated break.
中文简介正在准备中。当前显示原文说明。