teaching-skills — Claude Code plugin: teaching workflows and install
teaching-skills is a Claude Code plugin for course design, lesson planning, and assessment. Its router selects from 15 workflows based on the request.
MIT ★ 1,596 updated 2026-10-29
/plugin marketplace add hashgraph-online/awesome-codex-plugins
/plugin install teaching-skills@awesome-codex-pluginsWhat teaching-skills does
teaching-skills routes teaching requests to workflows for course design, lesson planning, assessment, student mentoring, or reflection on teaching. The suite contains 15 workflows. It also covers submission audits and dashboard building.
Claude Code provides /ts-* slash commands, including /ts-course and /ts-rubric. In Codex, ts-* names act as mode aliases rather than registered commands. Installing the Codex edition requires Python 3 and the Codex skill installer script.
What it helps with
- design a university course
- plan a lesson
- assess student work against criteria
- write feedback for a student
- reflect on teaching
Example prompts for the agent
- Design a university course on machine learning.
- Plan a lesson for this course topic.
- Create assessment criteria and feedback for this student submission.
How to install teaching-skills
Plugin marketplace
/plugin marketplace add hashgraph-online/awesome-codex-plugins/plugin install teaching-skills@awesome-codex-pluginsStep by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own
Questions about teaching-skills
How do I install teaching-skills in Claude Code?
Run /plugin marketplace add hashgraph-online/awesome-codex-plugins, then /plugin install teaching-skills@awesome-codex-plugins.
What does teaching-skills do?
It routes requests to 15 workflows for course design, lesson planning, assessment, mentoring, and teaching reflection.
How does teaching-skills work in Codex?
Codex treats ts-* names as mode aliases that the router recognizes, not as registered commands.
Source text
teaching-skills-codex · MIT
# Teaching Skills for Codex
Codex-native packaging of the **Teaching Skills** suite — the full university
teaching lifecycle (design → build → assess → deliver → reflect → improve)
for OpenAI Codex CLI. This is the sibling Codex distribution of
[Teaching Skills for Claude Code](https://github.com/YujxZJCN/teaching-skills).
This repository vendors the suite as a **single Codex skill** that routes to
15 workflows by intent:
```text
skills/teaching-suite/
SKILL.md # router: intent -> workflow, plus ts-* alias emulation
manifest.json # adapter metadata + upstream commit pin
VERSION
agents/openai.yaml
ts/ # vendored content (each upstream SKILL.md -> WORKFLOW.md)
<15 skills>/WORKFLOW.md + agents/ references/ templates/
shared/ scripts/ commands/ MODE_REGISTRY.md
```
> Generated, not hand-edited. The canonical source is the Claude Code repo; this
> package is reproduced by `scripts/build_codex.py` there, with no drift. Do not
> edit files here directly — change the upstream suite and regenerate.
## Which repo do I want?
- **Claude Code** (CLI / VS Code / JetBrains): use
[`YujxZJCN/teaching-skills`](https://github.com/YujxZJCN/teaching-skills) —
native skills, `/plugin` install, `/ts-*` slash commands.
- **Codex CLI**: use this repo — the single-suite Codex skill with `ts-*` aliases.
## Install or update
Install the skill from this repo with the Codex skill installer:
```bash
python3 "$HOME/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py" \
--repo YujxZJCN/teaching-skills-codex \
--ref main \
--path skills/teaching-suite \
--method git
```
To update, remove the installed copy and reinstall:
```bash
rm -rf "$HOME/.codex/skills/teaching-suite"
python3 "$HOME/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py" \
--repo YujxZJCN/teaching-skills-codex \
--ref main \
--path skills/teaching-suite \
--method git
```
On macOS / most Linux, Python 3 is `python3`. If your only `python` is Python 3,
substitute it.
## Use
Ask in natural language ("design a course on machine learning for 90 students"),
or use a Claude-style alias as a mode shortcut: `ts-course`, `ts-exam`,
`ts-rubric`, `ts-feedback`, `ts-cohort`, `ts-dashboard`, and more. The router
(`skills/teaching-suite/SKILL.md`) dispatches to the right workflow and enforces
the suite's non-negotiables (professor checkpoints, no invented context,
evidence-bound person-affecting output, integrity-by-design, no student data in
the passport).
**How this works in Codex.** Codex does not register Claude Code slash commands.
The `ts-*` names are *emulated aliases*: the vendored `ts/commands/*.md` files are
prompt recipes the router reads to pick a workflow and mode — they are not
installed commands. Type `ts-exam ...` (with or without a leading slash) and the
router treats it as a mode shortcut. If anything looks wrong after an upstream
change, recover by reinstalling (the update step above) — the skill is a
regenerated build product, so a clean reinstall always restores a consistent state.
The deterministic validators travel too:
```bash
python3 skills/teaching-suite/ts/scripts/check_passport.py course_passport.yaml
python3 skills/teaching-suite/ts/scripts/build_dashboard.py course_passport.yaml
```
## Versioning
Codex package `0.2.1`. Vendored from
`YujxZJCN/teaching-skills@87cc1aa13784` on 2026-10-03. The package version tracks
the adapter independently of the upstream suite version; see `manifest.json`.
## License
MIT — same as the upstream suite. Architecture inspired by
[academic-research-skills](https://github.com/Imbad0202/academic-research-skills)
and its Codex sibling.
© Jiaxing Yu · MIT · hashgraph-online/awesome-codex-plugins