kobejiasuoer/awesome-agent-engineering/deep-research-protocol
Claude Code and agent skill by kobejiasuoer/awesome-agent-engineering
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
深研究规程——多信源长程调研时的取证纪律：事实带编号、矛盾显式、省略标注
Install
npx vskill@latest install kobejiasuoer/awesome-agent-engineering/deep-research-protocolSKILL.md
技能：深研究规程
适用场景：跨多信源的深度调研（长途任务），对结论的可核查性要求高。
触发条件
- 「深度调研」「多源」「全景」「跨源」「长程」等信号
- 信源数 ≥ 10 或明确要求引用编号
取证纪律
- 每条关键事实标注信源编号（如
[S07]），无法溯源的表述标「待核查」； - 同一主体在不同信源的矛盾必须显式列出（两侧编号+各自表述），不许静默择一；
- 数字、版本号、时间、承诺类表述逐字引用，不做四舍五入式转写；
- 被截断/压缩过的材料引用时注明「基于节选」——省略必须显式；
- 营销通稿类内容降权：只登记事实性声明，形容词不入结论。
产出结构
概述 → 关键事实清单（带编号）→ 矛盾与演进分析 → 结论 → 未覆盖声明（失败/跳过/截断的源）。
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingportfolio-projects/research-assistant/skills/deep-research-protocol/SKILL.md
Popularity
- Repository stars
- 216
- Repository forks
- 32
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/kobejiasuoer/awesome-agent-engineering/deep-research-protocol)