research
Force an evidence-first research pass before advice or an engineering handoff.
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。
菜单
Force an evidence-first research pass before advice or an engineering handoff.
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
| name | research |
| description | Force an evidence-first research pass before advice or an engineering handoff. |
| disable-model-invocation | true |
| argument-hint | <research question or decision> |
Use this manual workflow when the user explicitly invokes /research. Treat the argument (or current request) as a forced research route and dispatch researcher in the foreground using docs/RESEARCH-CONTRACT.md and docs/RESEARCH-HARNESS.md.
Start with research_state: intake. If Researcher returns RESEARCH_NEEDS_INPUT, relay all three targeted questions to the user and re-dispatch it with research_state: investigation, the answers, and any prior report path. On RESEARCH_EVIDENCE_READY, create the task-scoped Scribe handoff; Researcher sends the full evidence packet directly to Scribe and the lead retains only a compact receipt. Never let research override explicit user requirements or silently add scope.
Screenshot-first visual end-to-end validation policy for browser-rendered UI and webview jobs after verifier approval.
Default engineering workflow. Classify a technical request, route it through the native T1/T2/T3 engineering fleet, and return only independently verified completion to the orchestrator.
Safely operate Claude Code's opt-in advanced capabilities—sessions, worktrees, agent teams, Skills, MCP, plugins, hooks, Channels, schedules, goals, and Agent SDK integrations—when the user explicitly asks for one. Do not use for an ordinary build request.
Routes selective local Codex plan, code, verification, and visual judgment with evidence-backed blocking and strict cost caps.
Shared evidence, accessibility, context, and handoff rules for the local design-agent fleet.
Produces contextual creative theses and bounded visual directions without generic model defaults.