菜单
Research with parallel agents, independent evidence angles, and cross-validation. Use when the user explicitly asks for parallel or delegated research, or when a high-cost question materially benefits from independent evidence.
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
Use this skill whenever code-review feedback already exists and may affect a code decision or change. This includes PR comments, findings returned by invoke or any external model or review tool, and delegated-review results—even when the user simply says to fix, address, apply, or resolve them. Do not use to perform a new review, diagnose an unrelated bug, implement a new requirement, or merely summarize or explain feedback without deciding about code.
Interview the user to resolve material branches of a decision tree and converge on a shared plan before acting. Use when multiple reasonable choices would materially change scope, cost, reversibility, or outcome, or when the user asks to brainstorm, shape, or grill an idea. Do not use when facts can resolve the ambiguity or a reversible assumption would not materially affect the result.
Draft or review minimal, testable goals. Use only when the user explicitly asks to write, revise, or review a goal.
Create or improve agent skills from concrete behavior and evidence. Use when building or revising SKILL.md, or testing whether a skill earns its context. Do not use for ordinary documentation or one-off prompts.
Diagnose and fix bugs, failures, and performance regressions. Read this skill BEFORE touching any code whenever the user reports a bug, broken behavior, a crash, wrong output, or a regression — even when the cause looks obvious and the user only asked for a fix. Do not use for a simple explanation of a known error when no diagnosis is requested.
Teach with adaptive guidance, retrieval practice, and Socratic questioning. Use when the user wants to study a topic, build durable understanding, practice, or be coached. Do not use for one-off factual answers, quick explanations, or ordinary task guidance.
| name | parallel-research |
| description | Research with parallel agents, independent evidence angles, and cross-validation. Use when the user explicitly asks for parallel or delegated research, or when a high-cost question materially benefits from independent evidence. |
Split a research question only when independent searches are likely to reduce blind spots enough to justify the coordination cost.
Define the question, the decision it informs, required recency, exclusions, and every material, non-overlapping evidence angle. Ask the user only when the scope is materially ambiguous; otherwise state any consequential assumption and proceed.
Assign one researcher per angle, running as many concurrently as subagent slots allow and launching the remainder as slots open until every angle is covered. Every researcher is a leaf: it must not spawn, delegate, or invoke another research workflow.
Each researcher should:
The main thread does not take a research angle. Compare results for agreement, contradiction, and missing coverage. Check numbers, dates, policies, availability, and technical behavior against the strongest primary sources. Downgrade stale, indirect, or single-source claims.
Synthesize the answer around verified findings, unresolved uncertainty, and the decision they support. Cite the underlying sources, never the agents. Save a durable report only when the user asks for one.
