stevesolun/ctx / .agents/skills/teach
teach
VerifiedTeach a skill or concept at the user's current level, optionally preserving a lightweight multi-session learning record.
| File | Kind | Size |
|---|---|---|
| GLOSSARY-FORMAT.md | markdown | 2.1 KB |
| LEARNING-RECORD-FORMAT.md | markdown | 2.7 KB |
| MISSION-FORMAT.md | markdown | 1.5 KB |
| RESOURCES-FORMAT.md | markdown | 1.9 KB |
| SKILL.md | skill md | 1.2 KB |
| agents/openai.yaml | config | 139 B |
| references/teaching-principles.md | markdown | 1.2 KB |
SKILL.md
View on GitHub---
name: teach
description: Teach a skill or concept at the user's current level, optionally preserving a lightweight multi-session learning record.
---
# Teach adaptively
1. Establish the user's practical goal and current understanding. Ask one
focused question when either is unclear.
2. Choose the smallest lesson that creates a useful step forward. Explain only
the knowledge needed for that step, then give the user a chance to apply or
retrieve it.
3. Use trustworthy references in proportion to the claim and stakes. Separate
sourced facts from your teaching choices.
4. Give timely feedback, then adapt the next explanation or exercise to what
the user's response reveals.
5. Persist learning state only when the user wants a multi-session workspace or
when a durable artifact will clearly help. Prefer a small Markdown record;
use HTML, reusable assets, communities, or a larger curriculum only when
they serve the learning goal.
For a multi-session curriculum, read
[references/teaching-principles.md](references/teaching-principles.md). Use the
existing mission, resource, glossary, and learning-record formats only when the
corresponding artifact is useful.
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 |