SkillHub

Skills obra episodic-memory

remembering-conversations

Use it when:
A task resembles past work, or you say "last time", "we discussed" or "why did we", and the answer lives in an earlier conversation.
It does:
In Claude Code, hands the search to episodic-memory's search-conversations subagent; elsewhere it calls the search and read tools itself.
You get:
A synthesis of the top 2–5 matching conversations, with pointers to the originals so you can check them.
Runs:
On its own and often: it's told to search before saying "I don't know", guessing, or treating any topic as new.
Skips:
Questions about the current code, which it explores directly, and anything already in the conversation.
Needs:
episodic-memory's MCP server, from its Claude Code, Codex or opencode plugin.

Needs the episodic-memory plugin or package for its search tools. Its description tells the agent to search past conversations before it guesses or says "I don't know", however trivial the question.

TL;DR

episodic-memory makes past agent conversations searchable; this skill tells the agent when and how to use it. It announces "Searching past conversations for [topic]" and, in Claude Code, dispatches the search-conversations subagent with a focused prompt about the decisions, patterns, gotchas or code examples it needs. The subagent searches, reads the top 2–5 results and returns a 200–1,000-word synthesis with sources, which the skill says saves 50–100 times the context of loading raw conversations. In Codex and opencode it uses that agent if present, or calls the search and read MCP tools directly and reads only the most relevant conversations or line ranges. It triggers broadly: on historical cues, when the agent is stuck, when a task resembles earlier work or needs a workflow repeated, and before answering from uncertainty. Unlike memory skills that save notes you pick, it only reads back what earlier conversations actually said.

Summarizes the skill at 7e06519.

npx skills add https://github.com/obra/episodic-memory --skill remembering-conversations

skills.sh pageSource on GitHubAll skills from obra/episodic-memory

Total Downloads
9,200 on skills.sh, Nov 9, 2026
Repo stars
499 obra/episodic-memory
First seen
Jan 20, 2026 on skills.sh
Weekly Downloads
16
-24% over the 8 weeks to Nov 9
Weekly values
Week toInstalls
Sep 2121
Sep 2811
Oct 517
Oct 1210
Oct 197
Oct 265
Nov 24
Nov 916
Category
category:agentscategory:software-engineering

Build agents, orchestrate workers and give agents memory.

Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills.
Type
type:tool

Operates a CLI, API, app or bundled script to get something done.
Effect
effect:none

Adds no side effects of its own. It shapes how the agent thinks, writes or reviews. Guidelines and routers are always effect:none, even when the task they support edits code.
Needs
needs:mcp

Needs an MCP server connected.
Publisher
by:official

A verified publisher on skills.sh, or the company or maintainer behind the product the skill operates.
Topics
memory
Stack
stack:episodic-memory

SKILL.md

From obra/episodic-memory at 7e06519. Checked daily, last changed Nov 6, 2026.

Frontmatter
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:

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

The search workflow will:

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

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

opencode

Use the MCP tools directly unless a local search agent is available:

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