mitodl

35 mods across 2 repositories, 64 stars between them.

uv-python-workflow

25

mitodl/agent-kit

Skill Claude CodeCodex

Use uv as the exclusive Python package and environment manager. Use this skill when installing packages, syncing environments, running scripts, writing Dockerfiles, or doing any Python dependency management — never pip, pip-compile, or virtualenv directly.

not rated 5 changed 16d ago A 52 tokens original BSD-3-Clause

creating-skills

26

mitodl/agent-kit

Skill Claude CodeCodex needs its repo

Create a new Agent Skill for this repository. Use this skill when asked to capture a workflow, convention, or repeated correction as a reusable skill — covers file naming, frontmatter fields, category placement, progressive disclosure, and updating the index.

not rated 5 changed 8d ago A 52 tokens original BSD-3-Clause

mitodl/agent-kit

Skill Claude CodeCodex

Run the full validation sequence before declaring any task done. Use this skill proactively after any code or infrastructure change — run the repository's hooks with prek, then mypy and pulumi preview (where applicable), without waiting to be asked. Never declare success without passing checks.

not rated 5 changed 16d ago A 59 tokens original BSD-3-Clause

add-canary-journey

28

mitodl/agent-kit

Skill Claude CodeCodex

Add a Playwright canary journey to an existing web property, or onboard a whole new property, in src/olconcourse/pipelines/canaries. Use when asked to add or extend an end-to-end canary test, cover a new user journey, add a new target property or environment to the canary fleet, or register a canary pipeline. Covers…

not rated 5 changed 15d ago A 116 tokens original BSD-3-Clause

run-canary-locally

29

mitodl/agent-kit

Skill Claude CodeCodex

Get a passing local run of the Playwright canary specs in src/olconcourse/pipelines/canaries. Use when running, debugging, or reproducing a canary journey outside Concourse — triaging a red canary- build, opening a failed run's trace.zip, iterating on a spec before shipping it, or reproducing a pipeline failure in the…

not rated 5 changed 15d ago C 121 tokens original BSD-3-Clause

mitodl/agent-kit

Skill Claude CodeCodex

Build an evidence-backed, longitudinal profile of how a person, a team, or a repository writes code and communicates, from git history and GitHub activity (commits, PRs, reviews, issues, discussions, code diffs), separating pre-AI baseline behavior from AI-assisted drift. Produces a report plus paste-ready CLAUDE.md /…

not rated 5 yesterday C 167 tokens original BSD-3-Clause

mitodl/agent-kit

Skill Claude CodeCodex

Prove whether a Django/DRF performance change actually made an endpoint faster, by A/B-ing two git refs against one production-shaped local database. Use this skill when asked to benchmark an endpoint, measure or verify a performance fix, answer "is this actually faster", size a speedup before merging, or turn a…

not rated 5 yesterday A 169 tokens original BSD-3-Clause

mitodl/agent-kit

Skill Claude CodeCodex

Use this skill before stating the status of anything outside the conversation: a PR, CI run, review, witan task, branch, deploy, environment, or fix. Triggers on "what's the status of", "is it merged", "did CI pass", "did the review land", "is it deployed", "is it fixed", "is X done", "where are we on", and on any…

not rated 5 yesterday A 132 tokens original BSD-3-Clause

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: