Install any skill in seconds. Free to start, no credit card required.
Get Started Free →trpc-group/session-logs
Search and analyze your own session logs (older/parent conversations) using jq.
Passed 15 of 18 test cases with the skill, and 7 of 18 without it.
and 11 more in the full report
11 fixed8 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
What are the three allowed string values for the message.role property within an OpenClaw session transcript message line?
| Checked | Without skill | With skill |
|---|---|---|
| identifies 'user' as a valid message.role value | Passed | Passed |
| identifies 'assistant' as a valid message.role value | Passed | Passed |
| identifies 'toolResult' as a valid message.role value | Missed | Passed |
The instructions your model reads when the skill loads.
Search your complete conversation history stored in session JSONL files. Use this when a user references older/parent conversations or asks what was said before.
Use this skill when the user asks about prior chats, parent conversations, or historical context that isn't in memory files.
Session logs live at: ~/.openclaw/agents/<agentId>/sessions/ (use the agent=<id> value from the system prompt Runtime line).
sessions.json - Index mapping session keys to session IDs<session-id>.jsonl - Full conversation transcript per sessionEach .jsonl file contains messages with:
type: "session" (metadata) or "message"timestamp: ISO timestampmessage.role: "user", "assistant", or "toolResult"message.content[]: Text, thinking, or tool calls (filter type=="text" for human-readable content)message.usage.cost.total: Cost per responsefor f in ~/.openclaw/agents/<agentId>/sessions/*.jsonl; do
date=$(head -1 "$f" | jq -r '.timestamp' | cut -dT -f1)
size=$(ls -lh "$f" | awk '{print $5}')
echo "$date $size $(basename $f)"
done | sort -r
test cases passed, vs 7 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.