← 返回 Skills 市场
264
总下载
0
收藏
1
当前安装
11
版本数
在 OpenClaw 中安装
/install per-agent-compression-universal
功能描述
Automates weekly memory compression per agent in OpenClaw, consolidating daily notes into domain-specific long-term files without manual setup.
安全使用建议
Before installing, review and test the scripts in a safe environment. Key points to check: (1) Metadata mismatch — the registry claims 'no required binaries/env' but install.sh needs openclaw and jq and will require a delivery recipient (DELIVERY_TO) or interactive input. (2) Privacy impact — the installer will register cron jobs that read all agents' workspaces, extract wide-ranging personal/profile information (including 'User Traits'), append it into persistent files, and announce summaries via your configured channels; confirm you want that data consolidated and where announcements will be delivered. (3) Scope control — run the installer on a single agent or staging instance first, back up workspaces, and inspect MSG_FULL/cron messages to ensure no unexpected external recipients are configured. (4) Delivery channels — verify your channel configs (DingTalk/others) to avoid leaking IDs or sending data to unintended recipients. (5) Release scripts — do not run publish/release scripts (publish-github-release.sh, scripts/release.sh) unless you intend to publish and have the appropriate tokens. If you are unsure, classify this skill as 'needs manual review' and ask the maintainer for an explicit list of runtime prerequisites and a dry-run mode that performs no writes or external announcements.
功能分析
Type: OpenClaw Skill
Name: per-agent-compression-universal
Version: 1.4.0
The skill bundle provides a comprehensive system for automating memory consolidation across multi-agent OpenClaw deployments. It functions by discovering agents and registering cron tasks that extract structured information (decisions, preferences, user traits) from daily notes into long-term memory files. While the skill handles sensitive data and utilizes network connectors (DingTalk) for summaries, these actions are transparently documented and user-configurable via the interactive installer (install.sh). The inclusion of a detailed Security SOP (SKILL_RELEASE_SOP.md), automated security scans in the release scripts, and a history of proactive privacy remediations (v1.3.2) indicates a high level of security awareness and no evidence of malicious intent or unauthorized data exfiltration.
能力评估
Purpose & Capability
The skill's purpose (per-agent memory compression) aligns with the actions in SKILL.md and install.sh (agent discovery, reading/moving daily notes, appending to target files, state tracking). However the registry metadata claims no required binaries or env vars while the installer and changelog explicitly require the OpenClaw CLI and jq, and the installer requires a delivery recipient (--to) or DELIVERY_TO env var. The 'zero-config' marketing is therefore misleading.
Instruction Scope
Runtime instructions and the install script instruct the agent to read full daily notes from each agent workspace, extract broad categories including 'User Traits & Self-Profile' and 'personal info', append those into persistent files (USER.md, IDENTITY.md, SOUL.md, MEMORY.md), move originals to processed/, and announce summaries via configured channels. That is coherent with compression but means the skill will systematically process and persist sensitive personal and profile data across multiple agents and deliver summaries externally — users should explicitly consent to this and understand exactly what will be extracted and where it will be delivered.
Install Mechanism
There is no remote download in the provided install flow (install.sh is local), so there is no high-risk network fetch during normal install. However the package includes release/publish scripts that will call external APIs (GitHub via curl) if run. The absence of an install spec in the registry combined with shipped installer/uninstall scripts is a metadata/documentation mismatch that can surprise users.
Credentials
Registry declares no required env vars/credentials, but install.sh expects DELIVERY_TO/DELIVERY_CHANNEL/DELIVERY_ACCOUNT (or interactive input) and will use OpenClaw's channel configuration to deliver summaries (e.g., DingTalk). Other scripts reference GITHUB_TOKEN, gh/clawhub, and assume access to Git credentials/CLIs. The skill will therefore interact with delivery channels and may cause outbound notifications; these credentials/configs are not listed in metadata and the delivery recipient is effectively required by the installer.
Persistence & Privilege
The installer creates persistent scheduled cron jobs (one per discovered agent), writes a per-workspace state file (.compression_state.json) and moves files into memory/processed/. These are expected for a task scheduler but amount to persistent autonomous behavior across all discovered agents. There is no 'always: true' flag, but cron tasks will run autonomously under each agent's context (the script intentionally uses --agent "$agent_id"). Review and limit scope before broad deployment.
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 per-agent-compression-universal - 安装完成后，直接呼叫该 Skill 的名称或使用
/per-agent-compression-universal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
v1.4.0
test
v1.3.4
Critical bug fix: STATE_FILE variable case sensitivity corrected. Tasks now execute successfully.
v1.3.3
v1.3.3: Fixed CLI message truncation by implementing two-step add+edit. All tasks now have full 10-step execution plan (~1700 chars). No functional changes.
v1.3.2
**Per-Agent Memory Compression (Universal) 1.3.2**
- Adds automatic, weekly memory compression for every agent in your OpenClaw deployment—no manual config needed.
- Auto-discovers agents and sets up individual, staggered cron jobs for each.
- Ensures workspace isolation, deduplication, and state persistence for reliable operation.
- Includes summary notifications via DingTalk and domain-specific compression logic.
- Supports agent workspace config with rule files for topic mapping, alert frequency, and user mapping.
- Easy install and uninstall scripts; cron tasks and state files are auto-managed.
v1.3.1
v1.3.1: Security re-release - removed all hardcoded credentials and model references. Same as v1.3.0 but with clean history. No functional changes.
v1.3.0
v1.3.0: Critical security fix - removed hardcoded credentials and model references. Installer now auto-infers model/channel/recipient from user config. All users must upgrade.
v1.2.6
v1.2.6: Unified version numbers across all platforms. Consolidated documentation refinements (bilingual separation, proper CHANGELOG ordering). No functional changes.
v1.2.5
v1.2.5: Fixed README version to 1.2.4, added missing v1.2.4 changelog entry. All docs now consistent. No functional changes.
v1.2.4
v1.2.4: Fixed CHANGELOG ordering (newest first) and separated English/Chinese sections correctly. Added protocol in AGENTS.md for version releases. No functional changes.
v1.2.3
v1.2.3: Documentation update - separated English/Chinese sections for readability. Added 'scroll down for Chinese' notice. No functional changes.
v1.2.2
v1.2.2: Bilingual docs, testing artifacts, production readiness checklist. Fixed CLI command confusion and over-deletion issues. See CHANGELOG.md for full history.
元数据
常见问题
Per Agent Compression Universal 是什么？
Automates weekly memory compression per agent in OpenClaw, consolidating daily notes into domain-specific long-term files without manual setup. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 264 次。
如何安装 Per Agent Compression Universal？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install per-agent-compression-universal」即可一键安装，无需额外配置。
Per Agent Compression Universal 是免费的吗？
是的，Per Agent Compression Universal 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Per Agent Compression Universal 支持哪些平台？
Per Agent Compression Universal 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 Per Agent Compression Universal？
由 Bensk（@bensk2001）开发并维护，当前版本 v1.4.0。
推荐 Skills