Teach a skill or concept at the user's current level, optionally preserving a lightweight multi-session learning record.
Scanned 9/5/2026
Install to Claude Code
Skills Directorynpx -y skills add stevesolun/ctx --skill teach --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Teach?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/stevesolun-teach)More formats (shields.io, HTML) on the badges page.
---
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.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
