session-review

name	Session Review
description	Analyze agent sessions for tool failures, retry patterns, knowledge gaps, context limits, and config drift. Use when: Running periodic session reviews (cron), investigating agent reliability issues, looking for recurring failure patterns, or identifying workspace improvements from real usage. This is the primary skill for Robert's review cron job. Don't use when: You're making changes to fix issues (use workspace-improvement for that). Don't use for live debugging of a current issue (use the appropriate troubleshooting skill). Don't use for code review of PRs (use code-review). Outputs: Session analysis report with categorized findings (tool failures, retries, knowledge gaps, config drift), severity ratings, and proposed fixes. Written to /tmp/outputs/session-review.md for handoff.
requires	[]

Session Review

Routing

Use This Skill When

• Running a periodic session review (daily cron)
• Investigating why an agent struggled with a task
• Looking for recurring failure patterns across agents
• Identifying stale docs or missing skills from real usage
• Someone asks "what went wrong in recent sessions?"

Don't Use This Skill When

• You already have findings and need to open PRs → use workspace-improvement
• An issue is happening right now and needs live debugging → route to the appropriate agent
• Reviewing a PR's code quality → use code-review (leon)
• Looking at cluster health, not agent sessions → use cluster-health (dyson)

Gathering Sessions

Use the built-in sessions_list and sessions_history tools (OpenClaw tool calls, NOT bash commands).