zero-click

Produce the high-level architecture overview used by downstream product design and engineering.

Independent high-level architecture review gate for discovery.

Capture and structure raw ideas through guided interview or quick note. Produces a structured idea document ready for research or PRD pass. Focuses purely on product intent — no technical decisions.

Entry-point product workflow from raw idea to validated product design artifacts. Stops at reviewed PRD readiness and does not include engineering implementation.

Write the per-feature PRD from the ranked requirements contract using the mandatory PRD template.

Dedicated analyze gate for PRD and UI brief consistency. Runs script extraction first, then semantic review with evidence-backed findings.

Validate whether the captured problem is real, painful, frequent, and worth pursuing before broader discovery work begins.

Stage 3 orchestrator: route dedicated product-design skills to turn an approved roadmap version into reviewed PRDs and interface summaries ready for coding agents.

Transform product requirements into a focused UI/UX design brief with screens, flows, visual direction, and optional image-generation concepts. Bridge between product thinking and implementation.

Stage 3 of idea-to-delivery: gated engineering workflow that receives PRD, roadmap, and architecture inputs, decomposes into stories, and executes with TDD, traceability, and review gates.

Planning and decomposition review skill adapted from ECC planner agent. Covers story-set review (Gate 2) and planning consults for upstream skills. PRD-quality review is NOT in scope — that is owned by `woos-product-prd-review-gate`.

Produce a lean story plan (table) for the Gate 3 execution loop — execution order plus diff scope per story. PRD AC is the spec; tests are the verification. No per-story prose documents.

Resolve multi-agent review conflicts with explicit authority matrix, evidence weighting, and escalation criteria.

Architecture review and design skill adapted from ECC architect agent. Use for design validation, trade-off analysis, and system-level decisions.

Independent code/security review gate for Hermes workflow. Uses woos-code-reviewer and woos-security-reviewer where applicable.

Independent feature design review gate for Hermes workflow. Uses woos-architect review and returns PASS or REQUEST_CHANGES.

审核中文内容中的 AI 写作痕迹。支持"审核"（仅标记）和"改写"两种模式。当用户说"查 AI 痕迹"、"去 AI 味"、"审核 AI 写作"、"这段像不像 AI 写的"时触发。

Use when a user asks whether an AI answer, management argument, technical proposal, investment view, article draft, vendor claim, or elegant-sounding explanation is trustworthy. This skill applies Socratic interrogation to fluent but uncertain reasoning: separate facts from opinions, expose hidden premises, seek strongest counterarguments, test boundaries, surface real costs, and return final judgment ownership to the human instead of letting AI sign the answer.