菜单
Research source-quality and evidence-audit playbook. Use for deep, current/volatile, comparative, high-stakes, or disputed research.
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
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.
| name | research-source-audit |
| description | Research source-quality and evidence-audit playbook. Use for deep, current/volatile, comparative, high-stakes, or disputed research. |
| user-invocable | false |
Before external research, inspect relevant docs/research/ reports and state whether their evidence is sufficient, stale, conflicting, or incomplete. Prefer supplied/local evidence first, then primary/official sources, peer-reviewed work, authoritative company/government/regulatory data, and reputable secondary analysis. For every material claim, record a ledger entry with source/path or URL, type, authority/relevance, publication date when known, access date, supported claims, and limitations.
Seek independent and contrary evidence. State freshness requirements, sampling gaps, conflicts of interest, jurisdiction limits, and contradictions. Do not collapse uncertainty into a confident recommendation.
