name: remembering-conversations description: You MUST invoke this skill before saying "I don't know," guessing, or treating any topic as new, no matter how trivial the question seems. It supplements other memory systems, which only hold partial records. Searching past conversations is the only way to recover what was actually said.

Remembering Conversations

Core principle: Search before reinventing. Searching costs nothing; reinventing or repeating mistakes costs everything.

Mandatory: Search Historical Memory

YOU MUST search historical memory for any historical search.

Announce: "Searching past conversations for [topic]."

Claude Code

Use the Task tool with subagent_type: "search-conversations":

Task tool:
  description: "Search past conversations for [topic]"
  prompt: "Search for [specific query or topic]. Focus on [what you're looking for - e.g., decisions, patterns, gotchas, code examples]."
  subagent_type: "search-conversations"

Codex

If a search-conversations agent is available, dispatch it with the same prompt. If not, use the MCP tools directly:

Search with the episodic-memory search tool
Read the top 2-5 results with the episodic-memory read tool
Synthesize findings in your response
Include source pointers so the user can inspect the original conversations

The search workflow will:

Search with the search tool
Read top 2-5 results with the read tool
Synthesize findings (200-1000 words)
Return actionable insights + sources

Saves 50-100x context vs. loading raw conversations.

When to Use

Use this whenever the current task would benefit from information you may have learned before, even if the user did not explicitly ask you to search.

When past experience may help:

You need to recall decisions, rationale, patterns, solutions, pitfalls, or project context from earlier work
A task resembles something you've solved, debugged, reviewed, released, or planned before
You need to repeat a workflow or process that may have prior gotchas or established steps

When you're stuck:

You've investigated a problem and can't find the solution
Facing a complex problem without obvious solution in current code
Need to follow an unfamiliar workflow or process

When historical signals are present:

User says "last time", "before", "we discussed", "you implemented"
User asks "why did we...", "what was the reason..."
User says "do you remember...", "what do we know about..."

Before answering from uncertainty:

Before guessing from memory or saying "I don't know" about something that may have been learned in a past conversation, search memory unless the current conversation already answers it

Don't search first:

For current codebase structure (use Grep/Read to explore first)
For info in current conversation
Before understanding what you're being asked to do

Direct MCP Tool Access

Use these directly when a search agent is unavailable or the current harness does not support agent dispatch:

mcp__plugin_episodic-memory_episodic-memory__search
mcp__plugin_episodic-memory_episodic-memory__read

When using MCP tools directly, keep context small: search first, then read only the top 2-5 relevant conversations or line ranges.

See MCP-TOOLS.md for complete API reference if needed for advanced usage.

附带文件

MCP-TOOLS.md

# Episodic Memory MCP Tools Reference

The episodic-memory plugin exposes two MCP tools for searching and displaying past Claude Code and Codex conversations.

## search

Search your episodic memory of past Claude Code and Codex conversations using semantic or text search.

**Tool name:** `mcp__plugin_episodic-memory_episodic-memory__search`

### Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `query` | `string` or `string[]` | Yes | Search query. String for single-concept search, array of 2-5 strings for multi-concept AND search |
| `mode` | `"vector"` \| `"text"` \| `"both"` | No | Search mode (default: `"both"`). Only used for single-concept searches |
| `limit` | `number` | No | Maximum results to return, 1-50 (default: 10) |
| `after` | `string` | No | Only return conversations after this date (YYYY-MM-DD) |
| `before` | `string` | No | Only return conversations before this date (YYYY-MM-DD) |
| `response_format` | `"markdown"` \| `"json"` | No | Output format (default: `"markdown"`) |

### Search Modes

- **`vector`** - Semantic similarity search using embeddings
- **`text`** - Exact text matching (case-insensitive)
- **`both`** - Combined semantic + text search (default, recommended)

### Single-Concept Search

```typescript
{
  query: "React Router authentication errors",
  mode: "both",
  limit: 10
}
```

### Multi-Concept Search (AND)

Search for conversations containing ALL concepts:

```typescript
{
  query: ["authentication", "React Router", "error handling"],
  limit: 10
}
```

Note: `mode` is ignored for multi-concept searches (always uses vector similarity).

### Date Filtering

```typescript
{
  query: "refactoring patterns",
  after: "2025-09-01",
  before: "2025-10-01"
}
```

### Response Format

#### Markdown (default)

Human-readable format with:
- Project name and date
- Conversation summary
- Matched exchange snippet
- Similarity score
- File path and line numbers

#### JSON

Machine-readable format:
```json
{
  "results": [...],
  "count": 5,
  "mode": "both"
}
```

## read

Display a full conversation from episodic memory as markdown.

**Tool name:** `mcp__plugin_episodic-memory_episodic-memory__read`

### Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `path` | `string` | Yes | Absolute path to the JSONL conversation file |
| `startLine` | `number` | No | Starting line number (1-indexed, inclusive) |
| `endLine` | `number` | No | Ending line number (1-indexed, inclusive) |

### Usage

**Read entire conversation:**
```typescript
{
  path: "/Users/name/.config/superpowers/conversation-archive/project/uuid.jsonl"
}
```

**Read specific range:**
```typescript
{
  path: "/Users/name/.config/superpowers/conversation-archive/project/uuid.jsonl",
  startLine: 100,
  endLine: 200
}
```

### Response Format

Markdown-formatted conversation with:
- Message roles (user/assistant)
- Content (including tool uses and results)
- Line numbers for reference

## Error Handling

Both tools return errors as text content with `isError: true`:
- Invalid parameters (validation errors)
- File not found
- Date parsing errors
- Search failures

## Performance Notes

- **Search** is fast (< 100ms typically)
- **Read** can be slow for large conversations
  - Use `startLine`/`endLine` to paginate
  - Conversations can be 1000+ lines
- Vector search uses sqlite-vec with cached embeddings
- Text search uses SQLite FTS5 full-text index