Agent skill

Learn Dogfood

by debs-obrien in debs-obrien/playwright-movies-app

Dogfood the learn/ course like a new user: docs site walk, fresh clone setup, then Practice and shell steps from each module.

MITAuto-check: notesTesting & QA

Install Learn Dogfood

skills CLI

$ npx skills add debs-obrien/playwright-movies-app --skill learn-dogfood -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install debs-obrien/playwright-movies-app learn-dogfood --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/debs-obrien/playwright-movies-app.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/learn-dogfood .claude/skills/learn-dogfood && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "learn-dogfood" agent skill from https://github.com/debs-obrien/playwright-movies-app/tree/main/.agents/skills/learn-dogfood into .claude/skills/learn-dogfood/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learn-dogfood", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/debs-obrien/playwright-movies-app/tree/main/.agents/skills/learn-dogfood

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add debs-obrien/playwright-movies-app --skill learn-dogfood -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install debs-obrien/playwright-movies-app learn-dogfood --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/debs-obrien/playwright-movies-app.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/learn-dogfood .agents/skills/learn-dogfood && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "learn-dogfood" agent skill from https://github.com/debs-obrien/playwright-movies-app/tree/main/.agents/skills/learn-dogfood into .agents/skills/learn-dogfood/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learn-dogfood", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add debs-obrien/playwright-movies-app --skill learn-dogfood -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install debs-obrien/playwright-movies-app learn-dogfood --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/debs-obrien/playwright-movies-app.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/learn-dogfood .cursor/skills/learn-dogfood && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "learn-dogfood" agent skill from https://github.com/debs-obrien/playwright-movies-app/tree/main/.agents/skills/learn-dogfood into .cursor/skills/learn-dogfood/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learn-dogfood", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/debs-obrien/playwright-movies-app.git --path .agents/skills/learn-dogfood

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add debs-obrien/playwright-movies-app --skill learn-dogfood -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install debs-obrien/playwright-movies-app learn-dogfood --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/debs-obrien/playwright-movies-app.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/learn-dogfood .gemini/skills/learn-dogfood && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "learn-dogfood" agent skill from https://github.com/debs-obrien/playwright-movies-app/tree/main/.agents/skills/learn-dogfood into .gemini/skills/learn-dogfood/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learn-dogfood", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install debs-obrien/playwright-movies-app learn-dogfood

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add debs-obrien/playwright-movies-app --skill learn-dogfood -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/debs-obrien/playwright-movies-app.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/learn-dogfood .github/skills/learn-dogfood && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "learn-dogfood" agent skill from https://github.com/debs-obrien/playwright-movies-app/tree/main/.agents/skills/learn-dogfood into .github/skills/learn-dogfood/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learn-dogfood", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add debs-obrien/playwright-movies-app --skill learn-dogfood -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install debs-obrien/playwright-movies-app learn-dogfood --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/debs-obrien/playwright-movies-app.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/learn-dogfood .opencode/skills/learn-dogfood && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "learn-dogfood" agent skill from https://github.com/debs-obrien/playwright-movies-app/tree/main/.agents/skills/learn-dogfood into .opencode/skills/learn-dogfood/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learn-dogfood", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: learn-dogfood
GitHub stars: 103
Token cost: ~1k tokens
SKILL.md length: 452 words
Files: 1
Skills in repo: 3
Repo updated: Oct 1, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Dogfood the learn/ course like a new user: docs site walk, fresh clone setup, then Practice and shell steps from each module.

Works in 4 steps: Course home loads; beginner /… → 00 → each in-scope module via in-page… → CTAs: live Movies demo, clone/GitHub,… → …
The user says dogfood learn
SKILL.md covers Sources of truth, Scope, Procedure and Report format
Calls npx, npm and git

What it does

Learn Dogfood is an agent skill from debs-obrien/playwright-movies-app. Dogfood the learn/ course like a new user: docs site walk, fresh clone setup, then Practice and shell steps from each module. Use when the user says dogfood learn, validate the course, learner journey, or re-check learn/ after curriculum changes. Maintainer QA — not learn-lab-coach.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Static sites and blogs and Browser testing. It works with Playwright. The repository describes itself as: Playwright tests for a Movie App. The licence is MIT.

When your agent uses it

The user says dogfood learn
Validate the course
Learner journey
Re-check learn/ after curriculum changes

Example prompts

“/learn-dogfood”

Requirements

Node.js

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

Course home loads; beginner / intermediate / AI-first links work.
00 → each in-scope module via in-page Next / agenda links.
CTAs: live Movies demo, clone/GitHub, /docs/TESTING, /docs/AI-TESTING, /AGENTS.
Note 404s, broken anchors, and copy that contradicts learn/00-start-here.md.

What it can do on your machine

Read from SKILL.md and the folder at commit e628ea9. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- npx
- npm
- git
- playwright
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npx, npm and git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Learn Dogfood loads about 1k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 452 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~74
When it runs · the whole SKILL.md, loaded when a task matches: ~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NoteMentions a .env fileSKILL.md:67
```
cp .env.example .env
```

NoteMentions a .env fileSKILL.md:110

- **setup** — clone, install, browsers, `.env`

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from debs-obrien/playwright-movies-app at commit e628ea9, republished under its MIT licence (© debs-obrien). 452 words, ~1,032 tokens.

Download SKILL.mdSave it as .claude/skills/learn-dogfood/SKILL.md (or your agent's skills folder).

name: learn-dogfood
description: Dogfood the learn/ course like a new user: docs site walk, fresh clone setup, then Practice and shell steps from each module. Use when the user says dogfood learn, validate the course, learner journey, or re-check learn/ after curriculum changes. Maintainer QA — not learn-lab-coach.

Learn dogfood

Maintainer QA for the VitePress course under learn/. Simulate a new learner and report blockers. Do not coach a human one step at a time — that is learn-lab-coach.

Sources of truth

Module pages: learn/*.md and learn/index.md
Setup copy: learn/00-start-here.md, root README.md
House style: AGENTS.md, docs/TESTING.md, docs/AI-TESTING.md
Skills for labs: movies-playwright, playwright-cli, playwright-trace

Do not invent commands, files, or APIs missing from those sources.

Scope

Ask once if unclear. Defaults:

Scope	Modules
beginner (default)	00 → 04, then foundations smoke, then 05 → 11 if time
ai-first	00 setup, `AGENTS.md`, 07, 09
module N	00 setup (if needed) + that module only
docs-only	Layer A only

Continue on failure unless the user says stop-on-fail. Fix nothing unless asked — report only.

Procedure

Layer A — Docs site

From the repo under test (workspace or temp clone):

bash

npm run docs:dev

Open http://127.0.0.1:5173/course (VitePress default). Prefer npx playwright cli; browser MCP is fine for click-through.

Check:

Course home loads; beginner / intermediate / AI-first links work.
00 → each in-scope module via in-page Next / agenda links.
CTAs: live Movies demo, clone/GitHub, /docs/TESTING, /docs/AI-TESTING, /AGENTS.
Note 404s, broken anchors, and copy that contradicts learn/00-start-here.md.

Layer B — Fresh learner setup

Prefer a clean temp clone so dirty WIP does not hide broken instructions:

bash

git clone https://github.com/debs-obrien/playwright-movies-app.git /tmp/movies-learn-dogfood
cd /tmp/movies-learn-dogfood
npm install
npx playwright install chromium
cp .env.example .env

Run the block from learn/00-start-here.md verbatim when it differs. Record any step that fails on a clean tree.

If the user asks to dogfood uncommitted learn/ edits, use the workspace (or a worktree of the current branch) for Layers A–C instead of main on GitHub.

Show full SKILL.md (204 more words)Show less

Layer C — Module practice

For each in-scope module, read learn/<module>.md and execute only:

Shell/code blocks a learner is told to run (Start the app, run test, CLI explore, …).
Sections titled Practice on a clone, Practice:, or Done when.
Linked exercises when the module points to them (03, 07, 09).
After 01–04 (beginner path): foundations smoke from learn/index.md:

bash

npx playwright test tests/logged-out/movie-list.spec.ts --project=chromium
npx playwright test tests/logged-out/auth.spec.ts --project=chromium
npx playwright test tests/logged-out/search.spec.ts --project=chromium

Rules:

Ports 3000 / 4000 for the app; docs on 5173. Use npm run dev when the module says so; otherwise let Playwright webServer start the app during tests.
Writing or healing tests → movies-playwright. Explore → playwright-cli. Failures → evidence via UI Mode Errors or playwright-trace before locator changes.
Module 09: Path A (playwright cli) by default; Path B only if scoped. Thin prompts live under .github/prompts/.
Never treat Codegen or an IDE Testing UI as the course path.
Skim-only “Read first” external links (playwright.dev) unless the user wants link checks.

Report format

End with a compact table (and open with a one-line verdict):

Module	Step	Result	Bucket
00	`npm install`	pass / fail + short reason	docs / setup / lab

Buckets:

docs — site nav, broken links, misleading copy
setup — clone, install, browsers, .env
lab — practice commands, tests, CLI explore, prompts

Do not commit fixes unless the user asks.

Files

Just SKILL.md in .agents/skills/learn-dogfood of debs-obrien/playwright-movies-app.

Open the folder on GitHubat commit e628ea9

Compare with similar skills

Learn Dogfood next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Learn Dogfood compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Learn Dogfood this skilldebs-obrien/playwright-movies-app	103	—	~1k	Automated safety check: Notes	MIT	10 days ago
Localframekoolamusic/claudefiles	130	—	~2.1k	Automated safety check: Pass	MIT	yesterday
PR Screenshotsbradygaster/squad	3.3k	—	~1.1k	Automated safety check: Pass	MIT	yesterday
Web Application Testinganthropics/skills	180k	51 repos	~966	Automated safety check: Pass	Apache-2.0	yesterday
Chrome Tracelayoutit/polycss	767	—	~2k	Automated safety check: Pass	MIT	1 mo ago
Handsontable Visual Testinghandsontable/handsontable	22k	—	~2.3k	Automated safety check: Pass	Custom licence	yesterday

Similar skills

Localframe
koolamusic/claudefiles
Record silent product demos on this machine: a paced Playwright browser walkthrough of a web app or docs site, or a scripted asciinema terminal session against an API, rendered to mp4 with numbered…
130 GitHub stars~2.1k tokensUpdated yesterday
Testing & QAAuto-check passed
PR Screenshots
bradygaster/squad
Capture Playwright screenshots and embed them in GitHub PR descriptions
3.3k GitHub stars~1.1k tokensUpdated yesterday
Testing & QAAuto-check passed
Web Application Testing
anthropics/skills
Official
Tests local web applications with Python Playwright scripts, checking frontend behavior, capturing screenshots and reading browser console logs.
180k GitHub starsUsed in 51 repos~966 tokens
Testing & QAAuto-check passed
Chrome Trace
layoutit/polycss
Capture and analyze Chrome/Chromium performance traces with Playwright around a concrete browser interaction.
767 GitHub stars~2k tokensUpdated 1 mo ago
Testing & QAAuto-check passed
Handsontable Visual Testing
handsontable/handsontable
Guide to Playwright visual regression tests in Handsontable: when a screenshot is justified, the tablePage fixture, naming, reg-suit comparison and demo routes.
22k GitHub stars~2.3k tokensUpdated yesterday
Testing & QAAuto-check passed
UI Review
jvm-skills/jvm-skills
Verify UI/UX by running Playwright tests and reviewing screenshots.
139 GitHub stars~545 tokensUpdated 1 mo ago
Testing & QAAuto-check passed

Questions about Learn Dogfood

What does Learn Dogfood do?

Dogfood the learn/ course like a new user: docs site walk, fresh clone setup, then Practice and shell steps from each module. Learn Dogfood is an agent skill from debs-obrien/playwright-movies-app. Dogfood the learn/ course like a new user: docs site walk, fresh clone setup, then Practice and shell steps from each module.

When should I use Learn Dogfood?

Learn Dogfood fits situations like: the user says dogfood learn; validate the course; learner journey; re-check learn/ after curriculum changes.

How do I install Learn Dogfood in Claude Code?

Run `npx skills add debs-obrien/playwright-movies-app --skill learn-dogfood -a claude-code`. Or copy the skill folder (.agents/skills/learn-dogfood in debs-obrien/playwright-movies-app) into .claude/skills/learn-dogfood in your project. Claude Code loads it when a task matches its description.

How do I install Learn Dogfood in Codex?

Run `npx skills add debs-obrien/playwright-movies-app --skill learn-dogfood -a codex`. Or copy the skill folder (.agents/skills/learn-dogfood in debs-obrien/playwright-movies-app) into .agents/skills/learn-dogfood in your project. Codex loads it when a task matches its description.

Can I use Learn Dogfood in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add debs-obrien/playwright-movies-app --skill learn-dogfood -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/learn-dogfood, .gemini/skills/learn-dogfood, .github/skills/learn-dogfood and .opencode/skills/learn-dogfood in your project.

What does Learn Dogfood need to run?

Going by SKILL.md and its folder, Learn Dogfood needs the command-line tools its instructions call (npx, npm, git and playwright). Our summary lists: Node.js.

Does Learn Dogfood access the network?

SKILL.md contains no URLs. Its commands use npx, npm and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Learn Dogfood safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Learn Dogfood use?

Learn Dogfood is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Learn Dogfood use?

About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Learn Dogfood?

Skills that share tags, products or a category with Learn Dogfood: Localframe (koolamusic/claudefiles, 130 stars), PR Screenshots (bradygaster/squad, 3.3k stars), Web Application Testing (anthropics/skills, 180k stars) and Chrome Trace (layoutit/polycss, 767 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Learn Dogfood?

debs-obrien (a GitHub user) maintains it in debs-obrien/playwright-movies-app, which has 103 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 1, 2026.

Source: debs-obrien/playwright-movies-app on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Learn Dogfood

Install Learn Dogfood

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Learn dogfood

Sources of truth

Scope

Procedure

Layer A — Docs site

Layer B — Fresh learner setup

Layer C — Module practice

Report format

Files

Compare with similar skills

Similar skills

Localframe

PR Screenshots

Web Application Testing

Chrome Trace

Handsontable Visual Testing

UI Review

More from debs-obrien/playwright-movies-app

Learn Lab Coach

Movies Playwright

Questions about Learn Dogfood

Install Learn Dogfood

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Learn dogfood

Sources of truth

Scope

Procedure

Layer A — Docs site

Layer B — Fresh learner setup

Layer C — Module practice

Report format

Files

Compare with similar skills

Similar skills

More from debs-obrien/playwright-movies-app

Related

Questions about Learn Dogfood