菜单
Craft structured, domain-aware research prompts to leverage deep research agents for solving coding challenges. V2 with domain boundary awareness.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Brief pre-work alignment for any stage. Use before planning, coding, editing, reviewing, or delegating when the user asks you to understand the thesis, vibe, intent, current position, or direction of a request or existing thing. Returns 2–4 bold-labelled one-sentence observations and one short synthesis, then stops.
The single front door to the SDD pipeline (docs/plans/): research → plan → workshop → ADR → phase tasks → implement → progress → review → ship. Use when the user wants to plan, research, explore, specify or architect (now one atomic 'plan' step → one document: business spec + implementation plan), clarify, workshop, write an ADR, break a phase into tasks, implement or build a phase (optionally with a live review companion), update progress, code-review, or ship a plan (push + PR + watch checks) — or types /the-flow (or a legacy /plan-N command), or asks to start, resume, or adopt a plan flow. Guided mode (no args) coaches from durable on-disk state; direct jump runs one stage: /the-flow <id> <verb> [flags] — 1a explore, 1b plan (spec + plan in one doc; incl. clarify), 2c workshop, 3a adr, 5 tasks, 6 implement (--companion for live review), 6a progress, 7 review, 8 ship, 8c reconcile. Ids and verbs resolve alone; printed commands carry both.
Adaptive, high-signal post-action validation for whatever was just produced — unified plan, tasks, code change, workshop, legacy spec, or any artifact. Proves the claims that matter, reports only findings likely to change action, and adds independent critics only when risk or uncertainty earns them. Thesis- and consumer-aware; read-only through adjudication; compact verdict.
Pre-task token discipline. Use before any task when every read, tool call, line of reasoning, and output token must materially advance the stated goal or thesis, without weakening correctness or safety.
FlowSpace-first codebase research agent for parallel subagent exploration with structured output for parent orchestrator synthesis. Domain-aware v2.
Establish or refresh the project constitution and align the supporting norms documents before any planning phases begin. Re-entrant command that preserves user customizations during updates. Domain-aware v2.
| name | deepresearch-v2 |
| description | Craft structured, domain-aware research prompts to leverage deep research agents for solving coding challenges. V2 with domain boundary awareness. |
Please deep think / ultrathink as this is a complex task.
Craft a structured research prompt to leverage a deep research agent for solving coding challenges. Domain-aware: surfaces boundary concerns and cross-domain impacts when relevant.
Before crafting the prompt, check for domain context:
docs/domains/registry.md exists → scan registered domainsdocs/domains/domain-map.md exists → note domain relationships and contract edgesdocs/domains/<slug>/domain.md (concepts, contracts, composition)If no domain system is present, skip this step and proceed normally.
Please create a structured prompt with the following sections:
_platform domain or the feature domain?Please ensure the prompt is detailed, clear, and actionable, facilitating precise and valuable insights from our deep research agent.