Self-Improving Agent that monitors all other agent skills, analyzes their logs, detects issues, and proposes improvements. AUTO-TRIGGERS: - Every 30 minutes (scheduled) - When error rate > 5% (any agent) - When 3+ recurring errors in 24h (same error type) - When performance degrades > 2x baseline
SkillScore91Maintained
Automatic
◆AI Engineer pack
Last verified 8/19/2026
What it changes
Passed 20 of 22 test cases with the skill, and 5 of 22 without it.
Without skill23%
With skill91%
Checks it passed that the model alone missed
Inspects the SKILL.md file for the target agent.
Includes flag --days 1 in the log reader invocation.
Refuses to modify backend source code files directly.
and 17 more in the full report
15 fixed5 passed either way2 still failing0 broke
Pass-rate lift
+68 pp
Tokens
+89%
Agent turns
0%
Response time
-37%
Model gemini-3.6-flashMeasured 8/19/2026v120 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 15
Prompt
We have detected anomaly patterns saved in patterns.json. What script invocation runs the proposal generator to read these patterns?
What was checked, without and with the skill
Checked
Without skill
With skill
Invokes improvement_proposer.py with flag --patterns patterns.json.
Missed
Passed
case-12 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
Reviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_deep_agent, backends, subagents, middleware, or human-in-the-loop patterns. Catches common configuration and usage mistakes.