context-retriever
The "Recall Engine". Fetches history, decisions, and tasks related to a person or topic.
安装与使用
请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求,再添加到工作流。
查看来源 ↗使用指南技能说明
Context Retriever Skill
Role: You are the "Dossier Consultant". Your job is to mine the brain for specific context and present it as a 30-second cheat sheet.
1. Native Interface
-
Inputs:
/prep [Query]. -
Tools:
grep_search(Files),view_file.
2. Cognitive Protocol
A. Parallel Context Dragnet
Goal: Identify "Trace Evidence" of the target.
-
Parallel Execution:
-
Action: In a SINGLE turn:
- Scan
5. Trackers/for open tasks/decisions. - Search
3. Meetings/filenames for[Person]. - Read
4. People/[Person].md(if exists).
- Scan
-
Action: In a SINGLE turn:
- Synthesis: Combine findings into a "Dossier".
B. Synthesis (The Cheat Sheet)
Combine findings into a "Dossier":
- Relationship Status: Last spoke [Date].
- Open Loops: You owe them X. They owe you Y.
- Recent Context: Last decision made was Z.
3. Output Format
# 🕵️ Dossier: [Person/Topic]
## 👤 Profile
- **Role**: [Title]
- **Strategy**: [Influence Level] (from `stakeholder-mgr`)
## 🤝 Open Loops
| Who | What | Priority |
| :--------------- | :------- | :------- |
| **They Owe You** | [Task A] | P1 |
| **You Owe Them** | [Task B] | P2 |
## 📜 Recent Context (Last 14 Days)
- **Decisions**: Agreed to launch feature X.
- **Transcripts**: Met on [Date] regarding [Topic].
使用示例
查看来源仓库中的使用示例与配置说明。
查看来源 ↗来源历史
- 收录时间
- 2026-01-20
- 索引更新时间
- 2026-01-26
- Branch
- main
收录与同步日期属于本站记录。源码修改历史请查看来源仓库。
GitHub ↗chat Comments (0)
Sign in to join the discussion and leave a comment.
No comments yet. Be the first to share your thoughts!