Agent skill

Live Crowdin CLI Validation

by crowdin in crowdin/crowdin-cli

Validates CLI commands against live environments with safe setup and cleanup.

MITAuto-check passed

Install Live Crowdin CLI Validation

skills CLI
$ npx skills add crowdin/crowdin-cli --skill live-crowdin-cli-validation -a claude-code

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

GitHub CLI
$ gh skill install crowdin/crowdin-cli live-crowdin-cli-validation --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/crowdin/crowdin-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/live-crowdin-cli-validation .claude/skills/live-crowdin-cli-validation && 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
live-crowdin-cli-validation
GitHub stars
320
Token cost
~1k tokens
SKILL.md length
473 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Validates CLI commands against live environments with safe setup and cleanup.

  • Works in 5 steps: Run live API commands with unrestricted… → Use --no-progress for deterministic logs. → Use timestamped disposable… → …
  • Running bun run dev ..
  • SKILL.md covers Non-negotiable rules, Preflight (required before…, Universal validation pattern and Command-shape adapters, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Live Crowdin CLI Validation is an agent skill from crowdin/crowdin-cli. Validates CLI commands against live environments with safe setup and cleanup. Use when running bun run dev ... or equivalent against real services, validating subcommands in parallel, or diagnosing inconsistent results where some commands pass and others fail.

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.

The repository describes itself as: A command-line client for the Crowdin API. The licence is MIT.

When your agent uses it

  • Running bun run dev ..

Example prompts

  • “Use the live-crowdin-cli-validation skill to validate CLI commands against live environments with safe setup and cleanup”
  • “/live-crowdin-cli-validation”

Workflow steps

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

  1. Run live API commands with unrestricted permissions from the first external call
  2. Use --no-progress for deterministic logs.
  3. Use timestamped disposable identifiers/names for created entities.
  4. Capture exit code and key output for every command.
  5. Clean up created artifacts when feasible.

What it can do on your machine

Read from SKILL.md and the folder at commit 22a296c. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Live Crowdin CLI Validation loads about 1k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 473 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
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 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 crowdin/crowdin-cli at commit 22a296c, republished under its MIT licence (© crowdin). 473 words, ~1,041 tokens.

Download SKILL.mdSave it as .claude/skills/live-crowdin-cli-validation/SKILL.md (or your agent's skills folder).
name
live-crowdin-cli-validation
description
Validates CLI commands against live environments with safe setup and cleanup. Use when running `bun run dev ...` or equivalent against real services, validating subcommands in parallel, or diagnosing inconsistent results where some commands pass and others fail.

Live CLI Command Validation

Use this workflow for live validation of any CLI command that touches real external services.

Non-negotiable rules

  1. Run live API commands with unrestricted permissions from the first external call:
    • required_permissions: ["all"] for shell/subagent shell commands.
  2. Use --no-progress for deterministic logs.
  3. Use timestamped disposable identifiers/names for created entities.
  4. Capture exit code and key output for every command.
  5. Clean up created artifacts when feasible.

Preflight (required before subcommand validation)

Run these checks in order:

  1. <cli-entrypoint> <command> --help
  2. Read environment state required by the command (for example list resources, show config, auth probe).
  3. Determine command prerequisites:
    • required ids/paths/branches/resources
    • mutating vs read-only behavior
    • cleanup strategy for disposable data

If preflight fails with 403, do not conclude command regression until permissions/auth context is corrected and preflight is retried.

Universal validation pattern

For each command/subcommand under test:

  1. Happy path run
    • Execute one valid invocation with complete required arguments.
  2. Validation error run
    • Execute one intentionally invalid invocation to verify local validation behavior.
  3. If mutating
    • Create disposable fixture first.
    • Execute target mutation.
    • Verify post-state if possible.
    • Cleanup fixture.
  4. Output capture
    • record exact command
    • record exit code
    • record key output/error lines

Avoid unsupported flags not present in help output.

Command-shape adapters

Use one of these adapters depending on command shape:

Read-only commands (list, show, status)
  • success run (normal mode)
  • success run (verbose/diagnostic mode)
  • classify API/auth/environment failures separately from CLI parsing failures
Create commands (add, create, upload)
  • discover valid dependency inputs first (resource path/id/branch)
  • run successful create with timestamped payload
  • run one invalid-input case
  • store created id for downstream tests and cleanup
Update commands (edit, update)
  • create or discover target id
  • run successful update changing at least one field
  • run no-op/invalid update to confirm validation
  • cleanup if target was disposable
Show full SKILL.md (177 more words)Show less
Delete commands (delete, remove)
  • create or discover deletable target id
  • run successful delete
  • run invalid-id case (for example non-numeric where applicable)
  • confirm failure classification is validation, not transport

Parallel subagent policy

When validating multiple subcommands in parallel:

  1. Spawn one subagent per subcommand.
  2. Ensure each subagent performs its own preflight with unrestricted permissions.
  3. Require each report to include:
    • exact commands
    • exit codes
    • created/updated/deleted ids (if applicable)
    • cleanup status
    • failure class (validation/API/auth/lock/other)

Transient lock/conflict handling

If backend returns lock/conflict style responses (for example concurrent edit conflicts), retry with bounded attempts:

  • max retries: 3
  • backoff: 2s, 4s, 8s
  • keep same fixture context in logs

Do not classify lock conflicts as command regressions unless retries are exhausted.

Result classification

Classify outcomes explicitly:

  • CLI validation error expected: local input validation works (non-zero expected).
  • Live API success: command succeeds against live service.
  • Auth/permission context issue: 403 or similar due to execution context mismatch.
  • Transient external lock: safe retry scenario.
  • Environment mismatch: wrong target resource/config/fixture path.

Only classify as command regression when behavior is reproducible after correct preflight and permission context.

© 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 .agents/skills/live-crowdin-cli-validation of crowdin/crowdin-cli.

Open the folder on GitHubat commit 22a296c

Compare with similar skills

Live Crowdin CLI Validation 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.

Live Crowdin CLI Validation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Live Crowdin CLI Validation this skillcrowdin/crowdin-cli320—~1kAutomated safety check: PassMIT
Flox Environmentsaffaan-m/ECC275k2 repos~3.5kAutomated safety check: NotesMIT
Form Validationthedaviddias/Front-End-Checklist74k—~633Automated safety check: PassMIT
Platform Environment Validateforcedotcom/sf-skills1.1k—~2.6kAutomated safety check: NotesApache-2.0
Validateagenticnotetaking/arscontexta3.5k—~3kAutomated safety check: PassMIT
Remote Environmentsasgeirtj/system_prompts_leaks69k—~1.4kAutomated safety check: PassCC0-1.0

Similar skills

  • Flox Environments

    affaan-m/ECC

    Create reproducible, cross-platform (macOS/Linux) development environments with Flox, a declarative Nix-based environment manager.

    275k GitHub starsUsed in 2 repos~3.5k tokens
    DatabasesAuto-check: notes
  • Form Validation

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing templates, rendered HTML, or shared components related to Validate forms accessibly.

    74k GitHub stars~633 tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Platform Environment Validate

    forcedotcom/sf-skills

    Validate and configure the local Salesforce development environment.

    1.1k GitHub stars~2.6k tokensUpdated yesterday
    Sales & SupportAuto-check: notes
  • Validate

    agenticnotetaking/arscontexta

    Schema validation for notes. An agent skill from agenticnotetaking/arscontexta.

    3.5k GitHub stars~3k tokensUpdated 7 mo ago
    Frontend & DesignAuto-check passed
  • Remote Environments

    asgeirtj/system_prompts_leaks

    Discover available task environments and create or continue tasks when the user names an environment or computer, or refers to files or apps specifically on their computer.

    69k GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Official

    Validate and publish a canvas source project safely: the source-project shape, declared capabilities, reading the current version pointer, iterating on validation diagnostics, guarded publishing…

    40k GitHub stars~3.2k tokensUpdated today
    Auto-check passed

More from crowdin/crowdin-cli

  • Add E2E Test Suite

    crowdin/crowdin-cli

    Adds a new end-to-end (e2e) test suite for the Crowdin CLI under tests/e2e/suites/, exercising real CLI commands against a freshly-created Crowdin project.

    320 GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Crowdin API Client

    crowdin/crowdin-cli

    A skill your agent uses when implementing, refactoring, or reviewing @crowdin/crowdin-api-client usage in any JavaScript or TypeScript project, especially for endpoint selection, request/response…

    320 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Render Command Output

    crowdin/crowdin-cli

    A skill your agent uses when adding or changing what a CLI command prints - creating or editing views (views.ts), list/item/grid/table rendering, deciding what --output plain, json, or toon emit…

    320 GitHub stars~1.6k tokensUpdated today
    Auto-check passed

Questions about Live Crowdin CLI Validation

What does Live Crowdin CLI Validation do?

Validates CLI commands against live environments with safe setup and cleanup. Live Crowdin CLI Validation is an agent skill from crowdin/crowdin-cli. Validates CLI commands against live environments with safe setup and cleanup.

When should I use Live Crowdin CLI Validation?

Live Crowdin CLI Validation fits situations like: running bun run dev ..

How do I install Live Crowdin CLI Validation in Claude Code?

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

How do I install Live Crowdin CLI Validation in Codex?

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

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

What does Live Crowdin CLI Validation need to run?

SKILL.md names no scripts, command-line tools or credentials: Live Crowdin CLI Validation is instructions for the agent only.

Does Live Crowdin CLI Validation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Live Crowdin CLI Validation 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 Live Crowdin CLI Validation use?

Live Crowdin CLI Validation 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 Live Crowdin CLI Validation use?

About 1k tokens (SKILL.md is roughly 4.2k 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 Live Crowdin CLI Validation?

Skills that share tags, products or a category with Live Crowdin CLI Validation: Flox Environments (affaan-m/ECC, 275k stars), Form Validation (thedaviddias/Front-End-Checklist, 74k stars), Platform Environment Validate (forcedotcom/sf-skills, 1.1k stars) and Validate (agenticnotetaking/arscontexta, 3.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Live Crowdin CLI Validation?

crowdin (a GitHub organization) maintains it in crowdin/crowdin-cli, which has 320 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 7, 2026.

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