菜单
Classify ECC surfaces as DAILY vs LIBRARY to guide selective agent installation
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Scan installed skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule files.
Audit all installed OpenClaw skills for quality: content overlap, freshness, and uniqueness. Supports Quick Scan (changed only) and Full Stocktake modes.
Cluster MEMORY.md entries by theme and optionally generate SKILL.md drafts.
Export MEMORY.md to a timestamped markdown file for sharing or backup.
Import memory entries from a markdown export file, merging with MEMORY.md without duplicating.
Show current workspace memory: MEMORY.md contents, pending recalls, and index status.
基于 SOC 职业分类
| name | cmd_agent_sort |
| description | Classify ECC surfaces as DAILY vs LIBRARY to guide selective agent installation |
| user-invocable | true |
| origin | openclaw-mas |
| argument-hint | <project-path> |
The first argument is the project path. Before doing anything else:
Classify ECC surfaces with concrete repo evidence to determine which agents are needed daily vs. occasionally.
configure-ecc instead of re-implementing install logic$ARGUMENTS (after the project path)