sno-ai/sno-station-skills / skills/R-recursive-self-improvement/rem-reflect/skill
rem-reflect
UnverifiedSelf Learning from this machine's Claude Code, Codex, Hermes, OpenClaw and Cursor sessions. Decide skill changes and lessons with accept/reject/tbd; recall lessons at session start.
scripts/selftest/fixtures/hermes-session-export.jsonl
View on GitHub{"id": "20261009_044642_0bb1b0", "source": "cli", "model": "sno-test-model-c", "started_at": 1791521229.6024117, "ended_at": 1791521346.6403663, "billing_provider": "anthropic", "cwd": "", "messages": [{"role": "user", "content": "Reply with exactly ONE", "tool_calls": null, "tool_call_id": null, "tool_name": null, "timestamp": 1791521229.5079296}, {"role": "assistant", "content": "ONE", "tool_calls": null, "tool_call_id": null, "tool_name": null, "timestamp": 1791521233.65688}, {"role": "user", "content": "Reply with exactly TWO", "tool_calls": null, "tool_call_id": null, "tool_name": null, "timestamp": 1791521285.9169464}, {"role": "assistant", "content": "Your request was not processed. Send it again if you still want me to carry it out.", "tool_calls": null, "tool_call_id": null, "tool_name": null, "timestamp": 1791521345.2359753}, {"role": "user", "content": "received signal 1", "tool_calls": null, "tool_call_id": null, "tool_name": null, "timestamp": 1791521345.6673546}]}
{"id": "20261009_044111_b24ca7", "source": "oneshot", "model": "sno-test-model-a", "started_at": 1791520873.3666987, "ended_at": 1791520884.0923603, "billing_provider": "openai-codex", "cwd": "", "messages": [{"role": "user", "content": "Reply with exactly ISO-19219", "tool_calls": null, "tool_call_id": null, "tool_name": null, "timestamp": 1791520873.348268}, {"role": "assistant", "content": "ISO-19219", "tool_calls": null, "tool_call_id": null, "tool_name": null, "timestamp": 1791520884.0793355}]}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Unverified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |