remembering-conversations

The remembering-conversations skill provides a structured workflow for agents to query historical conversation data. It mandates searching past interactions before the agent makes assumptions or claims ignorance on topics previously discussed.

8.8K
Installs
4
Use cases
9/10
Quality

Is remembering-conversations safe to install?

Safe to install

Safe to install: our audit of remembering-conversations's source files found 0 shell commands, 0 external URLs, no file writes (none risk). Every command and URL listed appears verbatim in the skill's source. The skill relies on MCP tools for searching and reading memory. It does not execute shell commands or perform network requests directly.

How we audit skills: our security review methodology.

Who is this skill for?

AI agents and developers integrating episodic memory capabilities into their workflows.

What can you do with it?

  • Recalling project decisions, rationale, and patterns from previous work.
  • Retrieving solutions or debugging steps for recurring technical problems.
  • Identifying established workflows or project-specific gotchas.
  • Addressing user queries regarding past discussions or previous implementations.

How good is this skill?

Quality score: 9/10. The documentation is clear and provides specific instructions for tool usage and decision-making logic. It lacks a formal API reference, but directs users to a separate file for that information.

What does the skill file contain?

SKILL.md
# 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 example...

Frequently asked questions

When should an agent use this skill?

The agent should use this skill when a task benefits from prior information, when the agent is stuck, when historical signals appear in user prompts, or before the agent guesses or claims ignorance.

What tools does the skill utilize for memory access?

The skill uses the Task tool with subagent_type 'search-conversations' or direct MCP tools named 'mcp__plugin_episodic-memory_episodic-memory__search' and 'mcp__plugin_episodic-memory_episodic-memory__read'.

Are there scenarios where the agent should avoid searching?

The agent should not search for current codebase structure, information already present in the current conversation, or before understanding the user request.

Data sourced from obra/episodic-memory on GitHub. Install counts from skills.sh. The summary and security audit are derived from the skill's source files: every command and URL listed appears verbatim in the source.

Related skills

browser-act

74.5K

AI agents and developers requiring browser-based automation, web scraping, or interaction with JavaScript-heavy websites

Browser-act provides a command-line interface for AI agents to perform browser automation, including navigation, data extraction, form interaction, and session management.

highautomationbrowserbrowser-act

wind-mcp-skill

27.8K

Financial analysts and users requiring structured financial data, market snapshots, and company research

The wind-mcp-skill provides an interface for AI agents to query financial data from Wind, including A-share, Hong Kong, and US stock market information, fund data, indices, bonds, and financial documents.

highfinancewindwind-information-co-ltd

anti-detect-browser

27.3K

Developers and AI agents requiring isolated browser environments, multi-account management, or automated web interactions that bypass anti-bot detection

The anti-detect-browser SDK provides tools to launch Chromium instances with unique, persistent device fingerprints for multi-account management, web scraping, and AI agent automation. It integrates with Playwright to isolate browser sessions, cookies, and storage, and offers an MCP server mode for AI agent control.

highbrowser-automationanti-detectantibrow

agent-pulse

20.4K

Developers and AI engineers who need to monitor, audit, and optimize local AI-agent performance and costs

Agent Pulse provides a CLI interface to inspect and analyze local AI-agent activity, including session logs, token usage, model costs, and health metrics across multiple platforms like Claude, Aider, and Cursor.

highmonitoringclijane-o-o-o-o