菜单
Evidence-backed comparative research playbook. Use when the decision concerns two or more options, vendors, architectures, frameworks, or approaches.
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-comparison |
| description | Evidence-backed comparative research playbook. Use when the decision concerns two or more options, vendors, architectures, frameworks, or approaches. |
| user-invocable | false |
Define the decision, options, constraints, and criteria before scoring. Use a sourced comparison matrix that records each criterion, weight when material, option evidence, tradeoff, and confidence. Separate facts from assumptions, test the strongest alternative interpretation, state what would change the recommendation, and avoid false precision. Conclude with a bounded recommendation, non-recommendation conditions, validation steps, and required user approvals.
