sno-ai/sno-station-skills / skills/R-recursive-self-improvement/rem-reflect/skill
rem-reflect
VerifiedSelf 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.
references/local-writer.schema.json
View on GitHub{
"type": "object",
"properties": {
"lesson": { "oneOf": [{ "type": "null" }, { "$ref": "#/$defs/lesson" }] }
},
"required": ["lesson"],
"additionalProperties": false,
"$defs": {
"lesson": {
"type": "object",
"properties": {
"summary": { "type": "string", "minLength": 1 },
"class": { "enum": ["SKILL_DEFECT", "EXECUTION_LAPSE"] },
"situation": {
"type": "object",
"properties": {
"task_type": { "type": "string", "minLength": 1 },
"trigger": { "type": "string", "minLength": 1 },
"tools": { "type": "array", "items": { "type": "string" } }
},
"required": ["task_type", "trigger", "tools"],
"additionalProperties": false
},
"advice": { "type": "string", "minLength": 1 },
"expected_result": { "type": "string", "minLength": 1, "pattern": "\\S" },
"success_criteria": { "type": "string", "minLength": 1, "pattern": "\\S" },
"memory_fact_ids": { "type": "array", "items": { "type": "string", "minLength": 1 } },
"because": { "type": "string", "minLength": 1 },
"polarity": { "enum": ["from_failure", "from_success"] },
"evidence": {
"type": "array",
"minItems": 1,
"items": {
"type": "object",
"properties": {
"line_start": { "type": "integer", "minimum": 1 },
"line_end": { "type": "integer", "minimum": 1 },
"quote": { "type": "string", "minLength": 1 }
},
"required": ["line_start", "line_end", "quote"],
"additionalProperties": false
}
},
"skill_target": { "oneOf": [{ "type": "string" }, { "type": "null" }] },
"reminder_line": { "oneOf": [{ "type": "string" }, { "type": "null" }] },
"verdict_line": { "type": "integer", "minimum": 1, "description": "the line of the external verdict (from the External verdicts list in the prompt) this lesson rests on: a passed test for from_success, a failed test, check or build near the evidence for from_failure" }
},
"required": ["summary", "class", "situation", "advice", "expected_result", "success_criteria", "memory_fact_ids", "because", "polarity", "evidence", "skill_target", "reminder_line", "verdict_line"],
"additionalProperties": false
}
}
}
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 | Verified | 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 |