teach
An agent skill by cursor, from cursor/plugins. Tags: analysis, documentation, education, explanation, writing.
What it does
Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add cursor/plugins --skill teachOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/cursor/plugins
cp -r plugins/pstack/skills/teach ~/.claude/skills/teachSafety box score
Grade B, low risk: 12 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This is a pure teaching skill. It does not run shell commands or modify files, but it delegates to other skills and may use an image-generation tool for spatial explanations. The main risks are limited external dependencies and any data that leaves the machine through that image tool.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | No shell commands, code evaluation, or file writes are present. It only asks the agent to explain and to invoke other skills. |
| Network access | 1 (low) | It may use an image-generation tool for spatial ideas, which can send prompt text to a remote service, but it names no host or downloader. |
| Filesystem reach | 0 (none) | It does not request reads, writes, or deletes outside the project. |
| Secrets & credentials | 0 (none) | It does not ask for tokens, passwords, key files, or other credentials. |
| Privilege & persistence | 0 (none) | No sudo, installs, services, shell startup edits, or OS settings are mentioned. |
| Instruction hijack surface | 1 (low) | The file gives strong agent-behavior instructions, including "Write every response through the unslop skill," but it does not tell the agent to ignore safeguards or follow untrusted remote instructions. |
| Irreversible actions | 0 (none) | It only produces explanations. It does not publish, deploy, send messages, or change external state. |
| Transparency | 1 (low) | Its behavior depends on external skills (`how`, `why`, and `unslop`) that are not included here, so the full end-to-end output policy is not visible from this file alone. |
Before installing
- Read `SKILL.md` plus the dependent `how`, `why`, and `unslop` skills before trusting the full behavior.
- If you do not want any remote image-tool usage, avoid the spatial-diagram path or disable that tool in your environment.
- Decide whether the strict response-style rules fit your workflow, since this skill is opinionated about output format.
Rated 2026-10-20 by an automated review of 1 file from the skill's repository.
Source
- Repository
- cursor/plugins (all skills from this repository)
- Path
- pstack/skills/teach/SKILL.md
- Branch
- main
- Collection
- cursor
- Updated
- 2026-09-23
Related skills
- ralph-loop-help — Explain the Ralph Loop plugin, how it works, and available skills.
- teach — Teach the user a new skill or concept, within this workspace.
- writing-beats — Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.
- writing-fragments — Writing, explore: mine raw fragments, no structure yet.
- automate-me — Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill".
- bro — Restate the last message in plain human language, with no jargon.