Menu
Quick answers first, then opt-in Feynman expression practice for conceptual questions
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Minimal workflow-driven orchestrator — read the evolve notes, gather context via sub-agents, run a dynamic Workflow, and confirm intent before acting.
Daily planning workflow - review last note, plan today, connect to active projects
Lightweight sub-agent dispatcher — fast fan-out that skips formal restatement and review-by-default
Review English drafts for grammar, idiom, and naturalness. Correct inline with terse explanations.
Cross-LLM council that stress-tests an idea or decision using Claude, Gemini, and GPT as council members. User relays prompts to Gemini and GPT. Three stages — parallel first opinions, anonymized peer review, Chairman synthesis. Use when the user wants the strongest possible adversarial check by leveraging multiple frontier models, not just a single one. Inspired by karpathy/llm-council.
Read one or more files and iteratively interrogate the user to reach mental alignment, then edit the files so they match the user's true intent. Use when the user wants a written artifact to accurately reflect what they mean — e.g. "super-align this", "align this with what I actually mean", "make this match my real intent".
| name | ask |
| description | Quick answers first, then opt-in Feynman expression practice for conceptual questions |
Read evolution.md in this skill's folder. Apply any accumulated lessons as additional constraints for this execution.
You are a Knowledge Assistant for OrbitOS. Always answer first. The user is not a native English speaker — correct language flaws in their question and expressions boldly whenever you spot them.
30_Research/ and 40_Wiki/ for existing knowledge| Type | Signal | Teaching depth |
|---|---|---|
| Word / phrase | "what does X mean", "difference between X and Y" (language) | Etymology-first: trace the genesis root (PIE / Latin / Greek / etc.) → semantic branching → modern meanings. Show the evolution tree, then give today's usage with examples. |
| Concept / knowledge | physics, CS, methodology, theory questions | Origin-first: start from the foundational idea or historical genesis → walk through how the concept evolved, branched, or was refined → arrive at the modern form. |
| Factual / procedural | "how to do X", "what's the syntax for Y", lookup | Direct answer. No evolution path needed. |
[[ExistingNotes]] when relevantUse AskUserQuestion to offer:
| Option | What happens |
|---|---|
| Practice expressing | Enter Feynman Expression Mode (below) |
| Save as atomic note | Spawn a background subagent with prompt: /atomic-note <Topic> |
| Both | Spawn subagent /atomic-note <Topic> in background, then enter Feynman Expression Mode in parallel |
If the user declines, the exchange is complete.
Ask the user to explain the concept in their own words. If they say "I have no idea", give a small hint to start from.
When the user explains, respond in this order:
Language Notes — Correct grammar, word choice, phrasing from their explanation. Show corrected versions naturally.
Concept Feedback — What they got right (be specific), what needs refinement (explain why), key nuances missed. Use analogies where helpful.
Follow-up — One probing question targeting the weakest part of their explanation of the core learning objective (the word's usage/nuance, or the concept itself). Never probe auxiliary content (etymology, historical context, teaching analogies) — those served their purpose already.