一键导入
research-and-synthesis
Fetch and summarize authoritative external sources into actionable guidance using MCP helpers. EXCLUSIVE to researcher agent.
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
Fetch and summarize authoritative external sources into actionable guidance using MCP helpers. EXCLUSIVE to researcher agent.
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。
回顾最近 N 天的 Claude Code 使用记录——扫描原始会话数据,按主题分组汇总"我都做了什么",并从个人操作系统视角输出模式、风险与增删建议。当用户说 /recap、"看看我这几天做了什么"、"回顾一下我最近的会话"、"这两天我用 claude 干了啥"、"活动回顾" 时使用。
Wenn es um /anpassen in diesem Spezialbereich geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten.
Use when wiring up or switching between China-domestic LLM providers (DeepSeek, Doubao/Volc Ark, Qwen/DashScope, MiniMax). Provides OpenAI-compatible adapter pattern, env-var contracts, fallback strategy, cost guardrails, and minimum verifications before declaring integration done.
Consult an independent GPT-5.6 reviewer (Terra by default; Sol on request, for a stronger but costlier review), matched to your current reasoning-effort level. Use before committing to an interpretation or a substantial piece of writing/analysis, when stuck (recurring errors, a non-converging approach, results that do not fit), when considering a change of approach, or when you believe a task is complete and want a check before finalizing. Not a co-implementer — read-only advisory only, does not edit files.
QA the omo Codex Light edition (lazycodex / packages/omo-codex) itself, in strict isolation so ONLY our plugin is exercised, never the user's real ~/.codex. The first-party method drives the real `codex app-server` against an isolated CODEX_HOME plus a LOCAL mock model (no real API call), and proves a plugin hook fired by asserting hook/started + hook/completed notifications. Also: isolated install verification, per-component hook probes, a tmux TUI smoke, and runtime log observation (RUST_LOG / logs SQLite / /debug-config). Ships tested helper scripts each with a --self-test. Use whenever someone changes anything under packages/omo-codex or wants to QA, smoke-test, verify, or debug the Codex plugin, its hooks/components, the installer/config.toml, the app-server flow, or the Codex TUI. Triggers: codex qa, qa codex, codex-qa, test codex plugin, verify codex hook, codex app-server, lazycodex qa, isolated CODEX_HOME, prove codex hook fired, codex tui test.
MANDATORY for every coding agent (Claude Code, Codex, or any other) on every change-set — every applicable source file the agent creates or updates MUST start with the project's copyright/authorship header (file overview + exact author line). Use automatically whenever writing a new file or editing an existing one; do not wait to be asked. Covers JS/TS/TSX/CJS/MJS, Python, shell, and CSS. Includes the audit script to verify repo-wide compliance.
基于 SOC 职业分类
| name | research-and-synthesis |
| description | Fetch and summarize authoritative external sources into actionable guidance using MCP helpers. EXCLUSIVE to researcher agent. |
| allowed-tools | Read, Grep, Glob, Bash, WebFetch, mcp_gemini-bridge, mcp_context7, mcp_web-search-prime, mcp_web-reader, mcp_zread |
Exclusive to: researcher agent
mcp_gemini-bridge_consult_gemini(
query="Research [topic] with pros/cons, security considerations, and code examples",
directory="."
)
# Resolve library first
mcp_context7_resolve-library-id(libraryName="fastapi", query="dependency injection")
# Then query
mcp_context7_query-docs(libraryId="/tiangolo/fastapi", query="Depends pattern")
# Discover relevant content
mcp_web-search-prime_search(query="[topic] best practices 2025")
# Read full articles
mcp_web-reader_read(url="https://discovered-url.com/article")
# Smart content extraction
mcp_zread_read(url="https://docs-page.com")
Research Flow:
## Instructions
1. Understand project stack from `docs/project-overview-pdr.md`
2. Define the research question clearly
3. Use **Gemini-Bridge** for deep analysis and reasoning
4. Use **Context7** for up-to-date library documentation
5. Verify with multiple sources
6. Summarize actionable findings
## Supported Stacks
**PHP/Laravel:**
- Laravel 12, Inertia.js, Pest
**JavaScript/React:**
- React 19, TypeScript, Tailwind, shadcn/ui
**Python:**
- FastAPI, LangChain, LangGraph, pytest, Pydantic
## Source Evaluation
| Criteria | ✅ Good | ❌ Bad |
|----------|---------|--------|
| Recency | < 1 year | > 2 years |
| Authority | Official docs | Random blogs |
| Relevance | Same stack | Different framework |
## Research Process
1. Define the question clearly
2. Fetch 1-3 authoritative sources
3. Verify with multiple sources
4. Summarize actionable findings
## Package Evaluation
| Factor | Check |
|--------|-------|
| Maintenance | Last commit < 6 months |
| Compatibility | Works with Laravel 12 / React 19 |
| Documentation | Clear docs, examples |
| Security | No known vulnerabilities |
## Comparison Matrix
```markdown
| Criteria | Option A | Option B |
|----------|----------|----------|
| Implementation | ⭐⭐⭐ | ⭐⭐ |
| Performance | ⭐⭐ | ⭐⭐⭐ |
| Security | ⭐⭐⭐ | ⭐⭐ |
## Summary
[2-3 sentences]
## Key Findings
- Finding 1
- Finding 2
## Recommendation
[Which option and why]
## References
- [Source](url)