Skip to content

borghei/Claude-Skills / engineering/self-improving-agent

self-improving-agent

Verified

Curates agent memory and turns repeated lessons into reviewed rules: memory health checks, pattern extraction, feedback and regression analysis. Use when managing auto-memory or building agents that learn from their own sessions.

assets/sample_feedback.jsonl

View on GitHub
{"timestamp": "2026-03-01T10:00:00Z", "task_type": "code-review", "outcome": "SUCCESS", "corrections": 1, "turns": 4, "tools_used": ["Read"], "tool_errors": 0, "feedback": ""}
{"timestamp": "2026-03-02T10:00:00Z", "task_type": "bugfix", "outcome": "SUCCESS", "corrections": 0, "turns": 5, "tools_used": ["Read", "Edit"], "tool_errors": 0, "feedback": ""}
{"timestamp": "2026-03-03T10:00:00Z", "task_type": "refactor", "outcome": "SUCCESS", "corrections": 1, "turns": 6, "tools_used": ["Read", "Edit", "Bash"], "tool_errors": 0, "feedback": ""}
{"timestamp": "2026-03-04T10:00:00Z", "task_type": "code-review", "outcome": "FAILURE", "corrections": 0, "turns": 4, "tools_used": ["Read"], "tool_errors": 2, "feedback": "used npm instead of pnpm"}
{"timestamp": "2026-03-05T10:00:00Z", "task_type": "bugfix", "outcome": "SUCCESS", "corrections": 1, "turns": 5, "tools_used": ["Read", "Edit"], "tool_errors": 0, "feedback": ""}
{"timestamp": "2026-03-06T10:00:00Z", "task_type": "refactor", "outcome": "SUCCESS", "corrections": 0, "turns": 6, "tools_used": ["Read", "Edit", "Bash"], "tool_errors": 0, "feedback": ""}
{"timestamp": "2026-03-07T10:00:00Z", "task_type": "code-review", "outcome": "SUCCESS", "corrections": 1, "turns": 4, "tools_used": ["Read"], "tool_errors": 0, "feedback": ""}
{"timestamp": "2026-03-08T10:00:00Z", "task_type": "bugfix", "outcome": "FAILURE", "corrections": 0, "turns": 5, "tools_used": ["Read", "Edit"], "tool_errors": 2, "feedback": "used npm instead of pnpm"}
{"timestamp": "2026-03-09T10:00:00Z", "task_type": "refactor", "outcome": "SUCCESS", "corrections": 1, "turns": 6, "tools_used": ["Read", "Edit", "Bash"], "tool_errors": 0, "feedback": ""}
{"timestamp": "2026-03-10T10:00:00Z", "task_type": "code-review", "outcome": "SUCCESS", "corrections": 0, "turns": 4, "tools_used": ["Read"], "tool_errors": 0, "feedback": ""}
{"timestamp": "2026-03-11T10:00:00Z", "task_type": "bugfix", "outcome": "SUCCESS", "corrections": 1, "turns": 5, "tools_used": ["Read", "Edit"], "tool_errors": 0, "feedback": ""}
{"timestamp": "2026-03-12T10:00:00Z", "task_type": "refactor", "outcome": "FAILURE", "corrections": 0, "turns": 6, "tools_used": ["Read", "Edit", "Bash"], "tool_errors": 2, "feedback": "used npm instead of pnpm"}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall