← Back to Skills Marketplace
axelhu

Session Recover

by AxelHu · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
126
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install session-recover
Description
短期记忆恢复技能。用于快速回顾当前 session 或上一个 session 的完整内容。适用于:想知道"这次 session 聊了什么"、session 被意外重置后需要恢复上下文、或想提取对话精华。
Usage Guidance
This skill reads local OpenClaw session archive files and prints extracted messages. The included parser is local and contains no network or credential-siphoning code, but be aware: (1) it will output conversation content you may consider sensitive—only run it if you trust the skill source and the runtime environment; (2) the SKILL.md uses shell commands and hard-coded agent paths (e.g., ~/.openclaw/agents/main/sessions and session_status/sessions_list) — confirm those commands and paths exist in your environment; (3) the parser accepts any file path you provide, so do not point it at unrelated sensitive files. If you have doubts, inspect parse_session.py locally before running or run it in a restricted environment. If you want higher assurance, request the publisher/source or a cryptographic release channel for the skill.
Capability Assessment
Purpose & Capability
Name and description match the included artifacts: SKILL.md documents locating and parsing local OpenClaw session JSONL files and the repo includes a dedicated parse_session.py that implements that parsing. No unrelated binaries, env vars, or service credentials are requested.
Instruction Scope
Runtime instructions tell the agent to list and read local session archive files (under ~/.openclaw/agents/.../sessions), call sessions_list, and run the included Python parser. Those actions are necessary for restoring session content. The instructions do rely on local commands (session_status, sessions_list) and specific paths (agents/main/sessions), which is expected but means the skill assumes a particular agent layout.
Install Mechanism
No install spec is provided (instruction-only plus a small script). Nothing is downloaded or written to disk by an installer, reducing risk.
Credentials
The skill declares no required environment variables, credentials, or config paths beyond reading local session archive files. That is proportionate to the stated purpose.
Persistence & Privilege
always is false and the skill does not request persistent platform privileges or modify other skills. It is user-invocable and can run when invoked, which is appropriate.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install session-recover
  3. After installation, invoke the skill by name or use /session-recover
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
session-recover v1.0.0 - Initial release of the session-recover skill for short-term memory retrieval. - Enables users to quickly review the content of the current or previous session, including after unexpected resets. - Supports summarizing session highlights, extracting key points, and listing unfinished tasks. - Provides command-line steps for locating, parsing, and extracting information from session JSONL files. - Includes a standardized output format for session recall reports.
Metadata
Slug session-recover
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Session Recover?

短期记忆恢复技能。用于快速回顾当前 session 或上一个 session 的完整内容。适用于:想知道"这次 session 聊了什么"、session 被意外重置后需要恢复上下文、或想提取对话精华。 It is an AI Agent Skill for Claude Code / OpenClaw, with 126 downloads so far.

How do I install Session Recover?

Run "/install session-recover" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Session Recover free?

Yes, Session Recover is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Session Recover support?

Session Recover is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Session Recover?

It is built and maintained by AxelHu (@axelhu); the current version is v1.0.0.

💬 Comments