E2E Test

What it does

When your agent uses it

• You want to verify new
• Changed endpoints work with actual API calls

Example prompts

• “/e2e-test”

What it can do on your machine

Read from SKILL.md and the folder at commit 63407de. 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:

  • git
  • node
  • pnpm

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

• Network

  No URLs in SKILL.md. Its commands use git and pnpm, 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

E2E Test loads about 893 tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 388 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~48

When it runs · the whole SKILL.md, loaded when a task matches

~893

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

• NoteMentions a .env fileSKILL.md:3

  in Enterprise API using credentials from .env. Use when you want to verify new or changed endpoints work with actual API

• NoteMentions a .env fileSKILL.md:9

  points against the real API. Requires a `.env` file with a valid `TOKEN` (and `ORGANIZATION` for Enterprise accounts).

• NoteMentions a .env fileSKILL.md:13

  !`[ -f .env ] && echo "✓ .env present" || echo "✗ .env missing — copy .env.example and fill in TOKEN"`

• NoteMentions a .env fileSKILL.md:14

  !`[ -f .env ] && grep -v '^#\|^$' .env | sed 's/\(TOKEN=\).*/\1[MASKED]/' || true`

• NoteMentions a .env fileSKILL.md:26

  Read `.env`. If `TOKEN` is empty or the file is missing, stop and tell the user:

• NoteMentions a .env fileSKILL.md:27

  > Create `.env` from `.env.example` and fill in TOKEN. Set ORGANIZATION for Enterprise endpoints.

• NoteMentions a .env fileSKILL.md:72

  Source `.env` and execute:

• NoteMentions a .env fileSKILL.md:74

  export $(grep -v '^#\|^$' .env | xargs) && node e2e-scratch.cjs

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 crowdin/crowdin-api-client-js at commit 63407de, republished under its MIT licence (© crowdin). 388 words, ~893 tokens.

name

e2e-test

description

Run end-to-end tests against the real Crowdin or Crowdin Enterprise API using credentials from .env. Use when you want to verify new or changed endpoints work with actual API calls.

argument-hint

endpoint or resource, e.g. listBranches or sourceFiles

const crowdin = require('./out/index.js').default;

const token = process.env.TOKEN;
const organization = process.env.ORGANIZATION || undefined;
const api = new crowdin({ token, organization });

async function run() {
  // one block per endpoint — print name, call it, print summary or error
}

run().catch(err => {
  const status = err?.response?.status;
  const msg = err?.response?.data?.error?.message ?? err.message;
  console.error(`✗ ${status ? `HTTP ${status}: ` : ''}${msg}`);
  process.exit(1);
});

export $(grep -v '^#\|^$' .env | xargs) && node e2e-scratch.cjs

© crowdin, 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-test of crowdin/crowdin-api-client-js.

Open the folder on GitHubat commit 63407de