session-history
Search and browse past conversation history across all sessions. Use when recalling prior work, finding old discussions, resuming dropped threads, or when the user references something from a previous conversation that isn't in memory files. Also use when asked to "remember" something discussed before, find "that conversation about X", or continue work from a past session.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/amor71/session-historyWhat This Skill Does
The session-history skill is an essential utility for OpenClaw agents, providing a comprehensive interface to search, browse, and retrieve data from past conversation transcripts stored locally. In environments where context retention is critical, this skill acts as a bridge to historical interactions that may no longer be active in the immediate short-term memory buffer. By scanning the ~/.openclaw/agents/*/sessions/ directory, the skill allows the agent to perform keyword-based searches across JSONL-formatted transcripts, enabling accurate retrieval of past decisions, code snippets, or project requirements that were previously discussed.
Installation
To integrate this functionality into your environment, use the OpenClaw repository manager. Execute the following command in your terminal:
clawhub install openclaw/skills/skills/amor71/session-history
Once installed, ensure the agent has read permissions for the ~/.openclaw/agents/ directory to allow the scripts to index and parse your historical data correctly.
Use Cases
This skill is designed for scenarios where context continuity is paramount. Common use cases include:
- Resuming interrupted tasks: If you previously worked on a complex refactoring project but switched to a different task, this skill helps locate the exact point where work was paused.
- Verification: When the user asks, "What was the outcome of our discussion regarding the API limits last Tuesday?", the skill retrieves the specific decision made.
- Error debugging: Searching for past instances of a specific error stack trace to see how it was resolved in a prior, perhaps unrelated, session.
- Cross-referencing: Validating current project progress against historical requirements or constraints that are not explicitly documented in the static MEMORY.md files.
Example Prompts
- "Search through our previous sessions to find the code snippet we wrote for the PostgreSQL connection handler last month."
- "I remember we talked about the gclid pipeline error a few days ago. Can you find that conversation and summarize the fix we decided on?"
- "List all recent conversations from the last 5 days related to the quantum encryption project."
Tips & Limitations
- Prioritize memory: Always check
memory_searchfirst, as it offers semantic understanding of your history. Usesession-historywhen you need exact keyword matching or specific transcript files. - Summary focus: When the tool returns a match, prioritize synthesizing a concise summary for the user rather than outputting raw JSONL data, which can overwhelm the chat interface.
- Performance: For very large history datasets, utilize the
--max-resultsflag to avoid excessive I/O and processing time. - Formatting: Note that the tool interacts directly with JSONL files; if a file is corrupted, the script may skip it or require manual intervention to clean the transcript.
Metadata
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 skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-amor71-session-history": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read