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/evidence.ts
View on GitHubimport { message } from './text.ts';
import type { Trace } from './harvest.ts';
import { loadRenderBudgets, renderTrace } from './render.ts';
export interface Evidence { trace_id: string; line_start: number; line_end: number; quote: string }
export function sameSession(a: Trace, b: Trace): boolean {
return a.session_id === b.session_id && a.user_id === b.user_id && a.agent_id === b.agent_id;
}
export function traceKey(trace: Trace): string { return `${trace.user_id}/${trace.agent_id}/${trace.trace_id}`; }
export function validateRange(trace: Trace, start: number, end: number): void {
const lines = new Set(trace.records.map(record => record.line_number));
if (!Number.isInteger(start) || !Number.isInteger(end) || start > end || !lines.has(start) || !lines.has(end)) {
throw new Error(message('rangeOutside', { id: trace.trace_id }));
}
}
export function validateEvidence(evidence: readonly Evidence[], traces: readonly Trace[]): void {
for (const item of evidence) {
const matches = traces.filter(trace => trace.trace_id === item.trace_id);
if (matches.length !== 1) throw new Error(message('traceMissing', { id: item.trace_id }));
const trace = matches[0];
validateRange(trace, item.line_start, item.line_end);
const text = renderTrace(trace, loadRenderBudgets()).records
.filter(record => record.line_number >= item.line_start && record.line_number <= item.line_end)
.map(record => record.text).join('');
if (!item.quote || !text.includes(item.quote)) throw new Error(message('quoteAbsent', { id: item.trace_id }));
}
}
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 |