Project Retrospective
PassAudited by ClawScan on May 10, 2026.
Overview
This instruction-only skill is transparent about creating project retrospectives, but users should review any generated skills or memory before saving because they persist for future use.
This skill appears safe to install as an instruction-only retrospective helper. Before letting it save output, review the generated SKILL.md and memory file to ensure they do not contain secrets, private project details, or instructions that should not persist.
Findings (2)
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.
Project details may be retained and reused in future tasks.
The skill stores project lessons in persistent memory for later reuse. This is the stated purpose, but saved retrospectives could include sensitive, incorrect, or overly project-specific details if not reviewed.
提取踩坑经验 → 记录到memory ... 文件位置：`/root/.openclaw/workspace/memory/YYYY-MM-DD-<project-name>-pitfalls.md`
Review the generated memory entry before saving, and remove secrets, private data, or instructions that should not influence future sessions.
A generated skill may be reused later and could affect how the agent handles similar projects.
The skill can create a new persistent skill document that may shape future agent behavior. This is clearly disclosed and includes confirmation steps, so it is a notice rather than a concern.
提取标准化最优路径 → 生成skill ... 文件位置：`/root/.openclaw/workspace/skills/<project-name>/SKILL.md`
Approve generated skills only after checking that their instructions are accurate, scoped, and free of sensitive project information.