技能详情（站内镜像，无评论）
作者：@amor71 @amor71
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.0
统计：⭐ 0 · 507 · 1 current installs · 1 all-time installs
⭐ 0
安装量（当前） 1
🛡 VirusTotal ：可疑 · OpenClaw ：良性
Package：amor71/session-history
安全扫描（ClawHub）
- VirusTotal ：可疑
- OpenClaw ：良性
OpenClaw 评估
The skill's code and instructions match its stated purpose: it searches local OpenClaw session JSONL files and returns matches; nothing here tries to reach out to the network or request unrelated credentials.
目的
Name/description (search/browse past session history) align with the included script and SKILL.md, which explicitly read session JSONL files under ~/.openclaw/agents/*/sessions/. No unrelated binaries, env vars, or external services are requested.
说明范围
SKILL.md and the script instruct the agent to read local transcript files and use a 'sessions_history' tool when available. This is within the skill's stated scope, but the behavior involves reading potentially sensitive local conversation transcripts; SKILL.md advises summarizing rather than dumping raw transcripts, while the script prints excerpts and file paths. The instructions also reference external agent tools (sessions_history, read, m…
安装机制
No install spec; instruction-only plus a local Python script bundled with the skill. The script uses only Python standard library modules and does not download or execute remote code.
证书
The skill requests no environment variables, credentials, or config paths. It accesses the user's home directory (~/.openclaw) which is appropriate for its purpose of searching local session files.
持久
always:false and no code attempts to modify other skills or system-wide settings. The skill has no elevated persistence or privileged installation steps.
综合结论
This skill legitimately reads your local OpenClaw session transcripts (~/.openclaw/agents/*/sessions/*.jsonl) and prints matching excerpts and file paths. Before installing, confirm you are comfortable granting the agent access to your local transcript files (they may contain sensitive data). Note the SKILL.md recommends summarizing results rather than pasting full transcripts — follow that guidance. Also verify your agent environment provides…
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「Session History」。简介：Search and browse past conversation history across all sessions. Use when recal…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/amor71/session-history/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: session-history
description: 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.
---
# Session History
Search through past OpenClaw session transcripts (JSONL files in `~/.openclaw/agents/*/sessions/`).
## Quick Reference
```bash
# Search for conversations about a topic
python3 scripts/search_sessions.py "gclid pipeline error"
# List recent sessions
python3 scripts/search_sessions.py --list --days 3
# Search specific agent's history
python3 scripts/search_sessions.py "flight monitor" --agent main
# Wider time range
python3 scripts/search_sessions.py "quantum encryption" --days 30 --max-results 5
```
## Workflow
1. Run `search_sessions.py` with the user's query terms to find relevant sessions
2. Use `sessions_history` tool with the `sessionKey` to pull full context from a match
3. If `sessions_history` doesn't work (old/closed sessions), read the JSONL file directly with `read`
4. Summarize what was found — don't dump raw transcripts
## When to Use
- User says "remember when we discussed X?" or "we talked about Y last week"
- Resuming a thread that isn't captured in memory files
- Finding a decision, code snippet, or error from a past session
- Cross-referencing what was said vs what's in MEMORY.md
## Tips
- Also check `memory_search` first — it indexes session transcripts too
- Combine both: `memory_search` for semantic matching, `search_sessions.py` for keyword/exact matching
- The script searches user AND assistant messages
- JSONL path format: `~/.openclaw/agents/{agent_id}/sessions/{session_uuid}.jsonl`