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/text.json
View on GitHub{
"jsonMissing": "JSON object missing",
"jsonIncomplete": "JSON object incomplete",
"schemaInvalid": "invalid schema",
"rangeOutside": "{id}: evidence range outside trace",
"traceMissing": "{id}: evidence trace missing or ambiguous",
"quoteAbsent": "{id}: evidence quote absent from rendering",
"rawPathMissing": "{key}: raw label path missing",
"newAppend": "new page permits append only",
"patchSubstring": "patch target is not an exact substring",
"frontmatterMissing": "page frontmatter missing",
"frontmatterInvalid": "page frontmatter field invalid",
"storedPageInvalid": "stored page invalid",
"pageFilename": "page id differs from filename",
"pageIdInvalid": "invalid page_id",
"lessonRow": "invalid lesson row",
"usageMalformed": "usage: malformed line skipped",
"none": "none",
"unsolved": "unsolved",
"solvedBy": "solved_by {unit}",
"indexLine": "{id} | {summary} | count {count} | last_seen {seen} | {solved} | skills_loaded {skills}",
"patchNeedsRead": "a patch needs {target} to have been read by this harness (Claude Code or Codex) first",
"rejectedRepeat": "byte-identical to a Rejected proposal: {id}",
"missingPurposePage": "a create or patch proposal must name at least one page id in its purpose summary",
"missingExpertise": "a create or patch proposal is missing expertise field {field}",
"growLines": "the change grows SKILL.md by more than {cap} lines",
"growDescription": "the change grows the description by more than {cap} characters",
"growReminders": "the change pushes the reminders block at the end of SKILL.md past {cap} lines",
"nameRename": "a proposal may not remove or rename the frontmatter name",
"targetCount": "the patch target occurs {count} times in the file, not once",
"patchTargetPath": "a patch must target an existing absolute payload path from the catalogue",
"createTargetPath": "a create target must be a fresh lower-kebab skill name",
"createUnitExists": "an installed skill already exists at {path}",
"createNameExists": "a skill named {name} already exists",
"createFrontmatter": "the created SKILL.md frontmatter is invalid: {why}",
"regionMismatch": "the patch region {region} disagrees with the cited page class {cls}",
"reminderDuplicate": "the reminder line is byte-identical to a line already in the region",
"replaceLineMissing": "replace_line names a line that is not in the reminders block at the end of SKILL.md",
"tbdHeading": "## TBD",
"skillImpactHeading": "## Skill impact",
"recheckHeading": "## Re-check",
"tbdProposalLine": "- {id}: {kind} {target} awaiting verdict{evidence}",
"tbdLessonLine": "- {id}: {status} — {reason}{evidence}",
"tbdNewEvidence": " — new evidence: {ids}",
"skillImpactLine": "- {unit} ({id}): loaded_before: {before} loaded_after: {after}",
"recheckProposal": "- {id}: adopted then {status}, awaiting verdict",
"recheckLesson": "- {id}: under_review, awaiting verdict",
"lessonAdopted": "{id}: accepted and adopted into {target}",
"lessonAdoptRefused": "{id}: {reason}",
"lessonNotListed": "{id}: accept refused: {reason}",
"recallHeading": "Lessons from this machine's own sessions",
"recallIndexLine": "{id} · {scope} · {headline} — {advice}",
"recallInstruction": "Read one in full with: sno rem-reflect lesson <lesson_id> --session {session} --agent {agent} --cwd {cwd}",
"notArmed": "daily run not armed since {date}; arm with: sno heartbeat --interval 24h --max-hours 0 --label rem-reflect -- sno rem-reflect run --trigger timer",
"pendingVerdict": "{n} skill proposals and {m} lessons await your verdict: {ids}; present each listed lesson and ask the owner: this project or all your projects; report: {path}",
"lessonField": "{key}: {value}",
"recallMissing": "recall: missing {field}",
"lessonMissing": "lesson: missing {field}",
"lessonRefusedScope": "{id}: refused: {reason}",
"usageAppendFailed": "could not record use to ledger/usage.jsonl: {error}",
"usageMalformedCount": "skipped {n} unparsable usage line(s)",
"ceilingStopped": "run stopped at ceiling: {ceiling}"
}
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 |