claude/skills/session-logs/SKILL.md
Search and analyze your own session logs (older/parent conversations) using jq.
npx skillsauth add kendreaditya/.config session-logsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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 $f)"
done | sort -r
for f in ~/.openclaw/agents/<agentId>/sessions/*.jsonl; do
head -1 "$f" | jq -r '.timestamp' | grep -q "2026-01-06" && echo "$f"
done
jq -r 'select(.message.role == "user") | .message.content[]? | select(.type == "text") | .text' <session>.jsonl
jq -r 'select(.message.role == "assistant") | .message.content[]? | select(.type == "text") | .text' <session>.jsonl | rg -i "keyword"
jq -s '[.[] | .message.usage.cost.total // 0] | add' <session>.jsonl
for f in ~/.openclaw/agents/<agentId>/sessions/*.jsonl; do
date=$(head -1 "$f" | jq -r '.timestamp' | cut -dT -f1)
cost=$(jq -s '[.[] | .message.usage.cost.total // 0] | add' "$f")
echo "$date $cost"
done | awk '{a[$1]+=$2} END {for(d in a) print d, "$"a[d]}' | sort -r
jq -s '{
messages: length,
user: [.[] | select(.message.role == "user")] | length,
assistant: [.[] | select(.message.role == "assistant")] | length,
first: .[0].timestamp,
last: .[-1].timestamp
}' <session>.jsonl
jq -r '.message.content[]? | select(.type == "toolCall") | .name' <session>.jsonl | sort | uniq -c | sort -rn
rg -l "phrase" ~/.openclaw/agents/<agentId>/sessions/*.jsonl
head/tail for samplingsessions.json index maps chat providers (discord, whatsapp, etc.) to session IDs.deleted.<timestamp> suffixjq -r 'select(.type=="message") | .message.content[]? | select(.type=="text") | .text' ~/.openclaw/agents/<agentId>/sessions/<id>.jsonl | rg 'keyword'
development
Search and read content from leetcode.com — problem catalog, daily challenge, full problem statements with hints and starter code, the Discuss forum (interview experiences, comp posts, layoff threads), and company question-list metadata. Read-only, no auth, no API key. Use when the user wants to look up a LeetCode problem by name/number/slug, see today's daily challenge, search Discuss for interview write-ups at a specific company (Google, Waymo, Meta, Amazon, etc.), browse a tag-filtered discuss feed, read a Discuss post + comments, or check what a LeetCode company list covers. Triggers — "lcsearch", "leetcode search", "search leetcode", "leetcode discuss", "leetcode problem", "daily leetcode", "interview discuss", "what's the leetcode for X", URLs containing leetcode.com/problems/, leetcode.com/discuss/, or leetcode.com/company/. Pair with the `interviewcoder` skill (structured leetcode-style writeups from 1point3acres) and `blind` (anonymous workplace chatter) for the same companies.
development
Terminal Spotify playback/search via spogo (preferred) or spotify_player.
development
Search and read posts from interviewcoder.co — a Next.js-fronted aggregator of technical-interview writeups (largely sourced from 1point3acres) tagged by company, position, stage (Phone Screen / OA / Onsite / etc.), period, job type, and structured leetcode-style questions. Use when the user wants real interview questions for a specific company, recent writeups from a hiring loop, leetcode-style problems with tags and difficulty, or to look up a specific interviewcoder.co URL. Read-only, no auth, no API key. Triggers — "interviewcoder", "interviewcoder.co", "interview questions at [company]", "what's been asked at [company] recently", "interview writeup", and URLs containing interviewcoder.co.
tools
Small Yahoo Finance CLI for ticker info + N-year stock returns. Use when the user asks about: stock price, market cap, sector/industry classification, dividend yield, P/E ratio, beta, 52-week range, N-year stock return, company description for a public company. Triggers: 'yfinance', 'yfin', 'stock price', 'market cap of', 'how much has X stock returned', 'sector for ticker', 'industry classification'. Pairs with the levels-fyi skill for cross-checking public/private status (levels gives ticker, yfin returns live data).