ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified productivity Safety 4/5

session-recall

Search past session transcripts to recover lost conversation context. MUST use when: (1) the current session is new or has very few messages AND the user's message assumes shared context you don't have (they reference people, events, decisions, or topics not present in your current context), (2) user explicitly refers to a previous conversation ('continue where we left off', 'as we discussed', 'remember when...'), (3) you need to find a specific past discussion by keyword or time range. Key signal: if you find yourself about to reply 'I don't have context' or 'which topic are you referring to' — use this skill FIRST before asking the user to repeat themselves.

Why use this skill?

Use the session-recall skill to search past OpenClaw transcripts. Easily recover lost context, project decisions, and historical data with advanced keyword search.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/hchen13/openclaw-session-recall
Or

What This Skill Does

The session-recall skill acts as a powerful memory retrieval engine for the OpenClaw agent. It allows the agent to index, search, and navigate through historical conversation transcripts stored in JSONL format. Instead of relying solely on the immediate context window of a current session, this skill enables the agent to reach back into past interactions to recover lost information, such as prior decisions, references to specific entities, or ongoing project status. The tool provides granular control through time-based filtering, keyword searching, and pagination, ensuring that the agent can efficiently pinpoint the exact moment a topic was discussed without overwhelming the system.

Installation

To integrate this capability into your agent, use the ClawKit CLI with the following installation command:

clawhub install openclaw/skills/skills/hchen13/openclaw-session-recall

Ensure that your environment has Python 3 installed, as the skill operates via a backend script located in the SKILL_DIR of your configuration.

Use Cases

This skill is essential for maintaining long-term continuity in multi-session workflows. Use it when:

  • Context Resumption: A user says "Continue with the project plan we discussed last Tuesday." The agent uses session-recall to find that specific conversation.
  • Implicit References: A user asks "What was the outcome of that meeting with the finance team?" without defining which meeting. The agent searches past logs to identify the relevant discussion.
  • Search & Recovery: When you need to extract specific data points or facts shared in a previous, long-closed session.

Example Prompts

  1. "As we discussed in our last meeting, what were the three main requirements for the API integration?"
  2. "Can you search our transcripts from the last month for any mention of the 'Project Phoenix' deadline?"
  3. "Remember when we talked about the database migration? I need you to pull up the specific constraints we noted back then."

Tips & Limitations

  • Efficiency: Always narrow your search with --start and --end parameters to minimize processing time.
  • Precision: If a search returns too many results, use more specific keywords or tighter time windows.
  • Limitations: This skill relies on the file structure of your local transcripts. Ensure your AGENT_ID matches your current environment to prevent searching across unrelated datasets. If you find yourself about to apologize for a lack of context, use this skill first to verify if the information exists in your history.

Metadata

Author@hchen13
Stars2387
Views1
Updated2026-03-09
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-hchen13-openclaw-session-recall": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#memory#context#search#history#recall
Safety Score: 4/5

Flags: file-read