searching-messages
Search past messages to recall context. Use when you need to remember previous discussions, find specific topics mentioned before, pull up context from earlier in the conversation history, or find which agent discussed a 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
Searching Messages
This skill helps you search through past conversations to recall context that may have fallen out of your context window.
When to Use This Skill
- User asks "do you remember when we discussed X?"
- You need context from an earlier conversation
- User references something from the past that you don't have in context
- You want to verify what was said before about a topic
- You need to find which agent discussed a specific topic (use with
finding-agentsskill)
Script Usage
The scripts are located in the scripts/ subdirectory of this skill. Use the Skill Directory path shown above when loading this skill.
npx tsx <SKILL_DIR>/scripts/search-messages.ts --query <text> [options]
Replace <SKILL_DIR> with the actual path from the # Skill Directory: line at the top of this loaded skill.
Options
| Option | Description |
|---|---|
--query <text> |
Search query (required) |
--mode <mode> |
Search mode: vector, fts, hybrid (default: hybrid) |
--start-date <date> |
Filter messages after this date (ISO format) |
--end-date <date> |
Filter messages before this date (ISO format) |
--limit <n> |
Max results (default: 10) |
--all-agents |
Search all agents, not just current agent |
--agent-id <id> |
Explicit agent ID (for manual testing) |
Search Modes
- hybrid (default): Combines vector similarity + full-text search with RRF scoring
- vector: Semantic similarity search (good for conceptual matches)
- fts: Full-text search (good for exact phrases)
Companion Script: get-messages.ts
Use this to expand around a found needle by message ID cursor:
npx tsx <SKILL_DIR>/scripts/get-messages.ts [options]
| Option | Description |
|---|---|
--after <message-id> |
Get messages after this ID (cursor) |
--before <message-id> |
Get messages before this ID (cursor) |
--order <asc|desc> |
Sort order (default: desc = newest first) |
--limit <n> |
Max results (default: 20) |
--agent-id <id> |
Explicit agent ID |
Search Strategies
Strategy 1: Needle + Expand (Recommended)
Use when you need full conversation context around a specific topic:
-
Find the needle - Search with keywords to discover relevant messages:
npx tsx <SKILL_DIR>/scripts/search-messages.ts --query "flicker inline approval" --limit 5 -
Note the message_id - Find the most relevant result and copy its
message_id -
Expand before - Get messages leading up to the needle:
npx tsx <SKILL_DIR>/scripts/get-messages.ts --before "message-xyz" --limit 10 -
Expand after - Get messages following the needle (use
--order ascfor chronological):npx tsx <SKILL_DIR>/scripts/get-messages.ts --after "message-xyz" --order asc --limit 10
Strategy 2: Date-Bounded Search
Use when you know approximately when something was discussed:
npx tsx <SKILL_DIR>/scripts/search-messages.ts --query "topic" --start-date "2025-12-31T00:00:00Z" --end-date "2025-12-31T23:59:59Z" --limit 15
Results are sorted by relevance within the date window.
Strategy 3: Broad Discovery
Use when you're not sure what you're looking for:
npx tsx <SKILL_DIR>/scripts/search-messages.ts --query "vague topic" --mode vector --limit 10
Vector mode finds semantically similar messages even without exact keyword matches.
Strategy 4: Find Which Agent Discussed Something
Use with --all-agents to search across all agents and identify which one discussed a topic:
npx tsx <SKILL_DIR>/scripts/search-messages.ts --query "authentication refactor" --all-agents --limit 10
Results include agent_id for each message. Use this to:
- Find the agent that worked on a specific feature
- Identify the right agent to ask follow-up questions
- Cross-reference with the
finding-agentsskill to get agent details
Tip: Load both searching-messages and finding-agents skills together when you need to find and identify agents by topic.
Search Output
Returns search results with:
-
message_id- Use this for cursor-based expansion -
message_type-user_message,assistant_message,reasoning_message -
contentorreasoning- The actual message text -
created_at- When the message was sent (ISO format) -
agent_id- Which agent the message belongs to
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
- 2026-02-02
- 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!