yusifeng

Use when the user wants a reusable rolling execution pattern (README + TODO-INDEX) like plans/web-reference-react-refactor, and wants to run delivery in small validated loops.

Use when changing web CSS/UI styling so requirements, state ownership, and acceptance checks are locked before edits to prevent rework churn.

Use after task analysis when a non-trivial Formax repository task needs a structured `docs/todolist.md` with [x]/[ ] items, definitions-before-UI ordering, explicit non-goals, tests, and loop-ready execution slices.

Use when a Formax repository task is non-trivial and you should analyze goals, non-goals, boundaries, data/type/interface impact, contract impact, test strategy, and whether an xhigh subagent is actually needed before writing a todo or code.

Use after receiving WebGPT or another LLM review on a Formax todo and before sending the todo back for another pass. Produce a concise handoff response that says what we adopted, what we reject or question, and what the reviewer should specifically re-evaluate in `docs/todolist.md`.

Use for all frontend and web UI tasks by default to apply a business-agnostic desktop web visual style system with medium-strength guardrails; if an existing design system is present, follow it first and use this skill only as a style harmonizer.

Use when changing REPL clear/reset/resume/surface behavior (onClearTerminal, transcriptSeq remount, Ink Static paths, Ctrl+O/Ctrl+E transitions). Enforces single-owner reset transaction and prevents black-screen/flicker/duplicate-row regressions.

Use when code has gone through repeated rework and may contain redundant logic, style drift, or tangled structure. Trigger when user asks for "返工收敛", "cleanup-pass", or requests a focused cleanup pass that reduces churn without changing behavior.

Use after receiving WebGPT or other LLM feedback on an agent-infra roadmap/todo and before sending the todo back for another review. Produce a concise handoff response that says what we adopted, what we reject or question, and what WebGPT should specifically re-evaluate in the todo.

Use when preparing a Formax code handoff: selecting files, generating repomix bundles, and writing a high-quality prompt for WebGPT or another coding agent with clear constraints and validation scope.

Use when implementing or reviewing changes in this repository and you need a strict, repeatable local development loop: align with repo docs, execute one mainline task at a time, run pnpm-based targeted verification, run codex review for code changes, and prepare clean commits/PR context.

Use after task analysis when a non-trivial repository task needs a structured docs/todolist.md with [x]/[ ] items, data/type/interface-first ordering, explicit non-goals, tests, and loop-ready execution slices.

Use when a repository task is non-trivial and you should analyze goals, non-goals, boundaries, data/type/interface impact, test strategy, and whether an xhigh subagent is actually needed before writing a todo or code.