Remembering Conversations

Use when user asks 'how should I...' or 'what's the best approach...' after exploring code, OR when you've tried to solve something and are stuck, OR for unf...

Security Scan

The skill is internally consistent: it only instructs the agent to search and read past conversations (episodic memory) and requires no installs, credentials, or unusual system access.

Purpose & Capability

The name/description (remembering past conversations, searching history) aligns with the instructions and the provided MCP tools. There are no unrelated environment variables, binaries, or install steps requested.

Instruction Scope

The SKILL.md explicitly mandates dispatching a 'search-conversations' subagent and reading top results (2–5) to synthesize findings. This is in-scope for a memory/search skill, but it does mean the agent will access the user's stored conversation history (potentially including sensitive information). The MCP-TOOLS.md also documents a 'read' tool that takes absolute local archive paths, confirming the skill will surface local conversation contents.

Install Mechanism

Instruction-only skill with no install spec and no code files. Nothing is written to disk or downloaded by the skill itself.

Credentials

No environment variables, credentials, or config paths are required. The documented file-paths in MCP-TOOLS.md are relevant to the skill's purpose (conversation archive) and not an unrelated privilege escalation.

Persistence & Privilege

always is false and the skill does not request persistent system-wide configuration changes or elevated privileges. It does instruct the agent to use a subagent, which is normal for skills that perform searches.

Assessment

This skill simply tells the agent to search your episodic conversation archive and synthesize results; it does not install software or ask for credentials. Before enabling, consider whether you are comfortable with the agent reading your past conversations (they may contain secrets or private data). If concerned: (1) review or purge sensitive messages from your conversation archive, (2) confirm platform controls around episodic memory access, or (3) avoid enabling the skill. If you want tighter control, ask for a version that restricts date ranges, projects, or explicit user confirmation before each search.

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

Mandatory: Use the Search Agent

YOU MUST dispatch the search-conversations agent for any historical search.

Announce: "Dispatching search agent to find [topic]."

Then 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"

The agent will:

1. Search with the search tool
2. Read top 2-5 results with the show tool
3. Synthesize findings (200-1000 words)
4. Return actionable insights + sources

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

When to Use

You often get value out of consulting your episodic memory once you understand what you're being asked. Search memory in these situations:

After understanding the task:

• User asks "how should I..." or "what's the best approach..."
• You've explored current codebase and need to make architectural decisions
• User asks for implementation approach after describing what they want

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..."

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 Tool Access (Discouraged)

You CAN use MCP tools directly, but DON'T:

• mcp__plugin_episodic-memory_episodic-memory__search
• mcp__plugin_episodic-memory_episodic-memory__show

Using these directly wastes your context window. Always dispatch the agent instead.

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