Agent skill

E2E Live

by receptron in receptron/mulmoclaude

実 Claude API を叩く総合テスト(全カテゴリ)を実行する。リリース前ではなく、定期的に手動で回して回帰を検出するための skill。yarn dev が起動済みであることが前提。

MITAuto-check passedTesting & QA

Install E2E Live

skills CLI
$ npx skills add receptron/mulmoclaude --skill e2e-live -a claude-code

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

GitHub CLI
$ gh skill install receptron/mulmoclaude e2e-live --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/receptron/mulmoclaude.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/e2e-live .claude/skills/e2e-live && 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/

Facts

Skill name
e2e-live
GitHub stars
368
Token cost
~580 tokens
SKILL.md length
204 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
MIT

At a glance

実 Claude API を叩く総合テスト(全カテゴリ)を実行する。リリース前ではなく、定期的に手動で回して回帰を検出するための skill。yarn dev が起動済みであることが前提。

  • Works in 4 steps: 現在モードで実行 → 結果を確認 → 反対モードに切り替えてもらう → …
  • Tasks that involve End-to-end testing
  • SKILL.md covers 前提, 実行手順(Docker on / off 両モード), デバッグ時(QA が画面で動作を見たい場合) and 失敗時の対応, plus 1 more section
  • Calls yarn, tsx and git; needs ANTHROPIC_API_KEY

What it does

E2E Live is an agent skill from receptron/mulmoclaude. 実 Claude API を叩く総合テスト(全カテゴリ)を実行する。リリース前ではなく、定期的に手動で回して回帰を検出するための skill。yarn dev が起動済みであることが前提。

Its SKILL.md is about 580 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 End-to-end testing and LLM API integration. It works with Anthropic API, Docker and Playwright. The repository describes itself as: Nurture your own AI assistant on your own computer. Local-first and MIT: memories, data and apps stay as plain files in your workspace. Chat summons the right GUI — wiki… The licence is MIT.

When your agent uses it

  • Tasks that involve End-to-end testing
  • Tasks that involve LLM API integration

Example prompts

  • “/e2e-live”

Requirements

  • Node.js
  • Docker
  • A credential in ANTHROPIC_API_KEY

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. 現在モードで実行
  2. 結果を確認
  3. 反対モードに切り替えてもらう
  4. 反対モードで再実行 + 統合サマリ

What it can do on your machine

Read from SKILL.md and the folder at commit 6063082. 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:

    • yarn
    • tsx
    • git
    • claude
    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use yarn, git and npx, 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 these keys or tokens, usually read from environment variables:

    • ANTHROPIC_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

E2E Live loads about 580 tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 204 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~26
When it runs · the whole SKILL.md, loaded when a task matches
~580

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 passed

The automated check found no risky patterns in SKILL.md.

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 receptron/mulmoclaude at commit 6063082, republished under its MIT licence (© receptron). 204 words, ~580 tokens.

Download SKILL.mdSave it as .claude/skills/e2e-live/SKILL.md (or your agent's skills folder).
name
e2e-live
description
実 Claude API を叩く総合テスト(全カテゴリ)を実行する。リリース前ではなく、定期的に手動で回して回帰を検出するための skill。`yarn dev` が起動済みであることが前提。

前提

  • yarn dev を別ターミナルで起動済み(http://localhost:5173 が応答する)
  • yarn dev は server を tsx server/index.ts(--watch なし)で起動するため、 server/*.ts や src/utils/html/previewCsp.ts 等 server に取り込まれるコードを変更した/ git pull で更新した直後は dev を必ず再起動してから走らせる。 stale dev のまま走らせると、 ソース上は修正済の bug が再発したように見えて誤った issue 起票につながる(実例: PR #991 後の webkit L-01 fail → issue #1015、 dev 再起動だけで解消)
  • Claude 認証済み(claude login 済み or ANTHROPIC_API_KEY 設定済み)
  • e2e-live ディレクトリのテストは実 LLM を呼ぶため、API 利用枠を消費する

実行手順(Docker on / off 両モード)

mulmoclaude の Docker サンドボックス挙動はこのテスト群でカバーする品質の重要な軸なので、 両モードで回す こと。 切替は dev サーバ再起動が必要なため Claude では自動化できない — 都度ユーザーに手順を案内する。

Step 1: 現在モードで実行
bash
yarn test:e2e:live
Step 2: 結果を確認
  • 進捗: ターミナル(list reporter)でリアルタイム表示
  • 詳細: playwright-report-live/index.html(失敗時は自動オープン)
  • 動画リプレイ: npx playwright show-trace test-results-live/<spec>/trace.zip
  • 失敗時の動画: test-results-live/<spec>/video.webm
Step 3: 反対モードに切り替えてもらう

ユーザーに 明確に 次の指示を出す:

次は Docker を反対モード で回したいので、 dev サーバを再起動してください:

  • Docker off にする場合: いま起動中の yarn dev を Ctrl+C で停止 → DISABLE_SANDBOX=1 yarn dev
  • Docker on にする場合: いま起動中の yarn dev を Ctrl+C で停止 → yarn dev(こちらが既定)

起動が http://localhost:5173 で ready になったら教えてください。 もう一度 yarn test:e2e:live を回します。

ユーザーの再起動完了通知を待つ。 待ち中に勝手にテストを開始しない(古い dev サーバが残っていると ERR_CONNECTION_REFUSED か誤った結果になる)。

Step 4: 反対モードで再実行 + 統合サマリ

ユーザーから "再起動した" の合図がきたら、 もう一度 yarn test:e2e:live を回す。 両モードの結果(Pass / Fail カウント、 違いがあったシナリオ)を 1 つのサマリにまとめてユーザーに返す。

デバッグ時(QA が画面で動作を見たい場合)

bash
HEADED=1 yarn test:e2e:live

Chromium ウィンドウが開き、slowMo: 200ms で動作が目で追える。

失敗時の対応

各失敗はカテゴリ・シナリオ ID(L-01 〜 L-30)に紐づいている。plans/feat-e2e-live.md の Appendix に内部バグ ID(B-XX)との対応表があるので、回帰したバグを特定できる。

カテゴリ別の skill

特定カテゴリだけ走らせたい場合は以下を使用:

  • /e2e-live-media — 画像 / PDF / 動画
  • /e2e-live-roles — ロール別 sample query(未実装)
  • /e2e-live-session — セッション / 履歴(未実装)
  • /e2e-live-wiki — Wiki / Router(未実装)
  • /e2e-live-ui — UI / 通知 / プラグイン(未実装)
  • /e2e-live-skills — Skill / Tool(未実装)
  • /e2e-live-docker — Docker 環境特有(未実装)

カテゴリ別 skill は playwright-report-live/<category>/index.html に出力するので、 親 /e2e-live の総合レポートは上書きされない。

© receptron, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/e2e-live of receptron/mulmoclaude.

Open the folder on GitHubat commit 6063082

Compare with similar skills

E2E Live 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.

E2E Live compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
E2E Live this skillreceptron/mulmoclaude368—~580Automated safety check: PassMIT
E2E TestingOpenHands/OpenHands90k—~308Automated safety check: PassMIT
E2Esendou-ink/sendou.ink297—~2.1kAutomated safety check: NotesAGPL-3.0
Dev Webtestclassmethod/tsumiki974—~4.2kAutomated safety check: PassMIT
E2Eopenathleteorg/openathlete101—~675Automated safety check: PassAGPL-3.0
Write E2E Testbaserow/baserow6.1k—~1.3kAutomated safety check: NotesCustom licence

Similar skills

  • E2E Testing

    OpenHands/OpenHands

    This skill should be used when the user asks to "add an E2E test", "run live E2E", "run mock-LLM tests", "debug Playwright CI", "test the Docker image", or changes tests/e2e, Playwright configs, E2E…

    90k GitHub stars~308 tokensUpdated today
    Testing & QAAuto-check passed
  • E2E

    sendou-ink/sendou.ink

    Run, debug, and manage Playwright e2e tests. An agent skill from sendou-ink/sendou.ink.

    297 GitHub stars~2.1k tokensUpdated yesterday
    Testing & QAAuto-check: notes
  • Dev Webtest

    classmethod/tsumiki

    This skill should be used when the user asks to "dev-webtest", "Webテスト", "画面の動作確認", "E2Eテスト", "web test", "visual check", "モンキーテスト", "アクセシビリティチェック", "レスポンシブテスト", "フォームテスト".

    974 GitHub stars~4.2k tokensUpdated 2 mo ago
    Testing & QAAuto-check passed
  • E2E

    openathleteorg/openathlete

    Run, debug or extend the OpenAthlete Playwright end-to-end tests, which exercise the production Docker images (API, worker, web, PostgreSQL, Redis) through the API and a real browser on desktop and…

    101 GitHub stars~675 tokensUpdated today
    Testing & QAAuto-check passed
  • Write E2E Test

    baserow/baserow

    Write, update, debug, or run Baserow end-to-end tests in e2e-tests using Playwright, the repo's e2e fixtures, page objects, Docker stack, and just e2e commands.

    6.1k GitHub stars~1.3k tokensUpdated today
    Testing & QAAuto-check: notes
  • Dokan Run Test Suite

    getdokan/dokan

    Execute the Dokan Playwright test suite (E2E + API), locally or via GitHub Actions.

    288 GitHub stars~4.7k tokensUpdated today
    Testing & QAAuto-check: notes

More from receptron/mulmoclaude

All 17 skills in this repo
  • Mc Cooking Coach

    receptron/mulmoclaude

    Personal recipe book — save / read / update / delete cooking recipes as markdown files under data/cooking/recipes/, with a README.md index that lists every recipe.

    368 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Mc Manage Automations

    receptron/mulmoclaude

    Schedule, list, edit, or remove a recurring agent task (cron / interval) in config/scheduler/tasks.json.

    368 GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Mc Manage Skills

    receptron/mulmoclaude

    Save, edit, list, or delete a Claude Code skill in this workspace.

    368 GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Mc Wiki Ingest

    receptron/mulmoclaude

    Ingest a source (workspace file path or pasted text) into the wiki — write a summary page, cross-reference up to 5 related pages with [[links]], and append a log entry.

    368 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Mc Wiki Promote

    receptron/mulmoclaude

    Promote a chat exchange (the assistant's answer + the user's preceding question) into a wiki page — propose a slug + new-or-append target + draft body, show the proposal in the next assistant turn…

    368 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Mc Zenn

    receptron/mulmoclaude

    Turn MulmoClaude work into a Zenn tech article (markdown) inside the workspace.

    368 GitHub stars~2k tokensUpdated today
    Auto-check passed

Questions about E2E Live

What does E2E Live do?

実 Claude API を叩く総合テスト(全カテゴリ)を実行する。リリース前ではなく、定期的に手動で回して回帰を検出するための skill。yarn dev が起動済みであることが前提。. E2E Live is an agent skill from receptron/mulmoclaude.

When should I use E2E Live?

E2E Live fits situations like: tasks that involve End-to-end testing; tasks that involve LLM API integration.

How do I install E2E Live in Claude Code?

Run `npx skills add receptron/mulmoclaude --skill e2e-live -a claude-code`. Or copy the skill folder (.claude/skills/e2e-live in receptron/mulmoclaude) into .claude/skills/e2e-live in your project. Claude Code loads it when a task matches its description.

How do I install E2E Live in Codex?

Run `npx skills add receptron/mulmoclaude --skill e2e-live -a codex`. Or copy the skill folder (.claude/skills/e2e-live in receptron/mulmoclaude) into .agents/skills/e2e-live in your project. Codex loads it when a task matches its description.

Can I use E2E Live 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 receptron/mulmoclaude --skill e2e-live -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/e2e-live, .gemini/skills/e2e-live, .github/skills/e2e-live and .opencode/skills/e2e-live in your project.

What does E2E Live need to run?

Going by SKILL.md and its folder, E2E Live needs the command-line tools its instructions call (yarn, tsx, git, claude and npx) and credentials named ANTHROPIC_API_KEY. Our summary lists: Node.js; Docker; A credential in ANTHROPIC_API_KEY.

Does E2E Live access the network?

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

Is E2E Live safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does E2E Live use?

E2E Live 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 E2E Live use?

About 580 tokens (SKILL.md is roughly 2.3k 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 E2E Live?

Skills that share tags, products or a category with E2E Live: E2E Testing (OpenHands/OpenHands, 90k stars), E2E (sendou-ink/sendou.ink, 297 stars), Dev Webtest (classmethod/tsumiki, 974 stars) and E2E (openathleteorg/openathlete, 101 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains E2E Live?

receptron (a GitHub organization) maintains it in receptron/mulmoclaude, which has 368 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 9, 2026.

Source: receptron/mulmoclaude on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.