← 返回 Skills 市场
Session Memory & Summarization
作者
Thomas Alcala Schneider
· GitHub ↗
· v0.2.0
· MIT-0
181
总下载
0
收藏
0
当前安装
6
版本数
在 OpenClaw 中安装
/install session-context
功能描述
Automatically loads recent conversation memory into new sessions and generates AI summaries during compaction to maintain continuity across conversations. Pr...
安全使用建议
This skill appears to do what it says (load summaries and the last N raw messages), but it stores the last 10 verbatim turns in workspace/memory as plaintext — that can include secrets or PII. Before installing: (1) decide whether storing verbatim messages on disk is acceptable for your environment; (2) consider reducing MAX_RECENT_MESSAGES or MAX_CONTENT_PER_MSG, or adding encryption/access controls to the memory/ directory; (3) verify which GitHub repo you should trust (docs reference more than one URL) and review source history; (4) test in an isolated workspace first to confirm no unexpected network activity and to see how long sensitive data persists; (5) if you need stricter guarantees, ask the maintainer to add optional encryption, retention policies, or replace verbatim storage with redaction.
能力评估
Purpose & Capability
Name/description (session continuity + summarization) match the included handlers: session:compact:before creates summaries and appends a recent_messages JSON block; session:start loads summaries and that recent block. No unrelated credentials, binaries, or outside services are requested.
Instruction Scope
Handlers only read/write files under workspace/memory and access the hook context (messages, session, config). This matches SKILL.md. Note: the skill intentionally persists the last N raw message turns verbatim to disk (default 10), which is expected for exact resumption but expands the attack surface for sensitive data leakage.
Install Mechanism
No install spec (instruction-only skill). Handlers are plain JS executed by OpenClaw; nothing downloads arbitrary code or external archives. Minor documentation inconsistency: SKILL.md/README suggest different git clone URLs (thomasmarcel vs animo66), which is a provenance/documentation mismatch but not an installation-time code-install risk in itself.
Credentials
The skill requests no environment variables, no credentials, and no config paths beyond the workspace. It does reference a platform global agent (global.__OPENCLAW_AGENT__) to call agent.generateSummary(), which is reasonable for summarization and falls back to a local summarizer if not present.
Persistence & Privilege
always is false and the skill does not request elevated platform privileges. However it intentionally persists verbatim conversation chunks to the workspace/memory directory (plaintext JSON in daily .md files). That persistence is core functionality but is a material privacy/retention concern and should be considered a privileged data storage behavior.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install session-context - 安装完成后，直接呼叫该 Skill 的名称或使用
/session-context触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.2.0
v0.2.0: Preserve last 10 raw messages verbatim for exact conversation resumption. Two-layer continuity: AI summary + raw interactions. Loads today + yesterday on session start. Configurable MAX_RECENT_MESSAGES and MAX_SUMMARY_CHARS.
v1.1.0
v1.1.0: Preserve last 10 raw messages verbatim for exact conversation resumption. Two-layer continuity: AI summary + raw interactions. Loads today + yesterday on session start. Configurable MAX_RECENT_MESSAGES and MAX_SUMMARY_CHARS.
v0.1.3
- Renamed skill from session-memory to session-context for clarity and consistency.
- Updated documentation: revised install instructions, repository URLs, and usage guidance for the new skill name.
- Removed obsolete script, example, and reference files for a leaner codebase and easier maintenance.
v0.1.2
- Added AGENTS.md file for documentation or configuration.
- Removed handler.js and handler.ts from hooks/openclaw, streamlining the codebase.
v0.1.1
session-context v0.1.1
- Documentation updates made in README.md and metadata for clarity.
- No functional or code changes; behavior remains the same.
v0.1.0
- Introduces session continuity by loading recent conversation memory at session start.
- Automatically generates and saves AI-powered conversation summaries during compaction to maintain context across sessions.
- No manual steps required; integrates with OpenClaw hooks for seamless automation.
- Customizable thresholds for when to summarize and how much memory to load.
- Requires OpenClaw version 0.29.0 or newer.
元数据
常见问题
Session Memory & Summarization 是什么？
Automatically loads recent conversation memory into new sessions and generates AI summaries during compaction to maintain continuity across conversations. Pr... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 181 次。
如何安装 Session Memory & Summarization？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install session-context」即可一键安装，无需额外配置。
Session Memory & Summarization 是免费的吗？
是的，Session Memory & Summarization 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Session Memory & Summarization 支持哪些平台？
Session Memory & Summarization 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Session Memory & Summarization？
由 Thomas Alcala Schneider（@thomasmarcel）开发并维护，当前版本 v0.2.0。
推荐 Skills