自我复盘
PassAudited by ClawScan on May 10, 2026.
Overview
This appears to be a local self-reflection note-taking skill with no credential or network use shown, but it can persist local memories and optionally set up a daily scheduled task.
Before installing, decide whether you want the agent to keep ongoing local reflection notes. Review files under ~/.openclaw/workspace/reflections and ~/.openclaw/workspace/memory, avoid storing secrets there, and enable the launchd schedule only if you want daily background automation.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The agent may create or update reflection files after normal work, which could be useful but may also be unexpected if the user wanted no persistent notes.
The skill instructs the agent to perform additional recording steps in several situations, not only when the user explicitly asks for a reflection.
以下情况必须触发记录： 1. 完成复杂任务后 2. 用户指出错误或问题时 3. 发现反复犯同一个错误 4. 学到新的有效方法/工具/认知 5. 用户提出新的功能需求 6. 每天对话结束时
Use this skill only if you want proactive local reflection records, and review the generated files periodically.
Stored lessons, mistakes, and snippets can shape future behavior and may contain sensitive task details if the agent records them.
The skill creates persistent reflection content that may be read or reused by future agents.
主动在每次完成任务、犯错、学到新知后，将内容写入 reflections/。
Keep reflections local, review them for sensitive information, and delete or edit entries that should not persist.
Recent command errors or log context may be surfaced to the agent/user for reflection; local logs can sometimes include sensitive paths or command output.
The reminder helper inspects local OpenClaw log lines to detect command failures.
log_file = f"/tmp/openclaw/openclaw-{today}.log"
...
with open(log_file, encoding="utf-8", errors="ignore") as f:
lines = f.readlines()Avoid recording secrets in command output, and review reminder text before copying it into long-term reflection files.
If enabled, the skill can run daily in the background to create reflection/memory files.
The helper can create and load a user-level launchd scheduled task for recurring daily execution.
PLIST_FILE = os.path.expanduser("~/Library/LaunchAgents/com.openclaw.daily-reflect.plist")
...
result = os.system(f"launchctl load '{PLIST_FILE}' 2>/dev/null")Run the scheduling setup only if you want daily automation; use the provided --remove option or remove the LaunchAgent if you no longer want it.