New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Ya Run

by kzahel in kzahel/yepanywhere

Launch and drive Yep Anywhere — an isolated dev server plus real browser interaction — and run the repository's check suite.

MITAuto-check passedTesting & QA

Install Ya Run

skills CLI
$ npx skills add kzahel/yepanywhere --skill ya-run -a claude-code

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

GitHub CLI
$ gh skill install kzahel/yepanywhere ya-run --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/kzahel/yepanywhere.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/ya-run .claude/skills/ya-run && 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
ya-run
GitHub stars
534
Token cost
~957 tokens
SKILL.md length
502 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Launch and drive Yep Anywhere — an isolated dev server plus real browser interaction — and run the repository's check suite.

  • Smoke-test the app rather than only build
  • SKILL.md covers "Run the tests" is not "run…, Launching the app, Driving it and Device and hardware paths
  • Calls pnpm and curl
  • Tasks that involve QA and bug reports

What it does

Ya Run is an agent skill from kzahel/yepanywhere. Launch and drive Yep Anywhere — an isolated dev server plus real browser interaction — and run the repository's check suite. Use when asked to run, start, screenshot, or smoke-test the app rather than only build or typecheck it.

Its SKILL.md is about 960 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 QA and bug reports. It works with pnpm, Vite and Vitest. The repository describes itself as: Self-hosted web UI for Claude and Codex. Push notifications, file uploads, no accounts, no database. Uses your existing CLI session history. The licence is MIT.

When your agent uses it

  • Smoke-test the app rather than only build
  • Tasks that involve QA and bug reports

Example prompts

  • “/ya-run”

What it can do on your machine

Read from SKILL.md and the folder at commit 3d02243. 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:

    • pnpm
    • curl

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

  • Network

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

Ya Run loads about 957 tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 502 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~957

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 kzahel/yepanywhere at commit 3d02243, republished under its MIT licence (© kzahel). 502 words, ~957 tokens.

Download SKILL.mdSave it as .claude/skills/ya-run/SKILL.md (or your agent's skills folder).
name
ya-run
description
Launch and drive Yep Anywhere — an isolated dev server plus real browser interaction — and run the repository's check suite. Use when asked to run, start, screenshot, or smoke-test the app rather than only build or typecheck it.
disable-model-invocation
true

Running Yep Anywhere

This file exists so that any "how do I run this project?" procedure lands on the repository's own verified path instead of a generic recipe. It is a pointer, not a second copy: when it disagrees with the documents it cites, they win.

"Run the tests" is not "run the app"

The check suite is CLAUDE.md § After Editing Code — pnpm lint, pnpm format:check, pnpm typecheck, pnpm test, and pnpm test:e2e for UI changes. A request to run tests, checks, or lint is satisfied by those commands and needs no server and no browser.

Focused runs go through the owning package's runner, e.g. pnpm --filter @yep-anywhere/server exec vitest run test/services/Foo.test.ts; vitest is not a root dependency, so a repo-root pnpm vitest fails.

Launching the app

Start a fresh server from the current worktree on an unused port. Never reuse, reload, or restart an already-running instance: one may be supervising live agent sessions, and a capture taken against a stale process is invalid (AGENTS.md § UI Tweak Visual Verification).

All ports derive from PORT: the app on PORT, the maintenance server on PORT + 1, Vite on PORT + 2 (CLAUDE.md § Port Configuration). YEP_PROFILE gives the instance its own data directory, so it cannot disturb the default one (CLAUDE.md § Data Directory & Profiles).

bash
PORT=4000 YEP_PROFILE=dev \
VITE_DISABLE_ONBOARDING=true \
VITE_DISABLE_CLI_UPDATE_NOTIFICATIONS=true \
pnpm dev

The two VITE_* values suppress the first-run and CLI-update dialogs that would otherwise cover the surface under test. They are Vite startup inputs: setting them on a later screenshot command has no effect.

Readiness, from another shell — the maintenance server on PORT + 1 answers over plain HTTP and is the cheapest liveness probe (CLAUDE.md § Maintenance Server):

bash
curl -sf http://127.0.0.1:4001/status

The app itself is served over HTTPS; the repository's capture command passes --ignore-https-errors for it, and curl needs -k. Whether an API route answers without credentials depends on the profile's stored auth state, so treat a 401 as a configuration fact rather than a failed launch.

Stop the instance when finished; do not leave it listening.

Show full SKILL.md (180 more words)Show less

Driving it

Launching alone proves only that the entrypoint resolves. Exercise the surface the change touches: call the route with curl for server work, and for client work load the affected view in a browser and capture it.

CLAUDE.md § Browser Control (UI Testing) gives the capture command — the repository's installed Playwright dependency, pointed at https://localhost:4000/ with --ignore-https-errors. Do not write a custom browser driver; the dependency is already present.

AGENTS.md § UI Tweak Visual Verification and topics/ui-testing.md own the rest and are binding: which viewport widths to capture, the requirement to read and inspect each image in its own tool call, what to check in each one, where to archive them, and the case where the user has taken visual verification for themselves. Read topics/ui-testing.md before capturing rather than assuming the dimensions — a capture at the wrong size, or one skimmed instead of inspected, does not discharge the requirement.

Device and hardware paths

Emulator testing is required only for device-control changes — /api/devices, deviceBridge, or packages/device-bridge (CLAUDE.md § Device Control Testing). Ordinary client, server, provider, relay, and rendering work does not need it.

© kzahel, 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/ya-run of kzahel/yepanywhere.

Open the folder on GitHubat commit 3d02243

Compare with similar skills

Ya Run 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.

Ya Run compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ya Run this skillkzahel/yepanywhere534—~957Automated safety check: PassMIT
Next QA Loopbreaking-brake/cc-wf-studio5.4k—~2.5kAutomated safety check: PassCustom licence
DeerFlow Smoke Testbytedance/deer-flow84k—~2.5kAutomated safety check: NotesMIT
OpenWork Desktop CDP Driverdifferent-ai/openwork24k—~465Automated safety check: PassCustom licence
Vitestsupabase/supabase111k12 repos~1.1kAutomated safety check: PassApache-2.0
Desktop Dual Repo TestEynzof/Hermes-CN-Desktop1.8k—~1.8kAutomated safety check: PassCustom licence

Similar skills

  • Next QA Loop

    breaking-brake/cc-wf-studio

    Runs one unattended iteration of a QA loop: tend any open QA pull request, then build one queued qa issue as tests or test tooling only and open a PR.

    5.4k GitHub stars~2.5k tokensUpdated 3 days ago
    Testing & QAAuto-check passed

  • DeerFlow Smoke Test

    bytedance/deer-flow

    Walks through an end-to-end smoke test of a DeerFlow deployment: pull the latest code, deploy with Docker or locally, verify services, run health checks and write a report.

    84k GitHub stars~2.5k tokensUpdated today
    Testing & QAAuto-check: notes

  • OpenWork Desktop CDP Driver

    different-ai/openwork

    Drives a running OpenWork desktop window over CDP from the shell to evaluate JS, take screenshots, start sessions and send prompts for hand checks.

    24k GitHub stars~465 tokensUpdated today
    Testing & QAAuto-check passed

  • Vitest

    supabase/supabase

    Official

    Vitest API and config reference (Jest-compatible) — mocking with vi., spies, fake timers, coverage configuration, fixtures, snapshots, and test filtering.

    111k GitHub starsUsed in 12 repos~1.1k tokens
    Testing & QAAuto-check passed

  • Desktop Dual Repo Test

    Eynzof/Hermes-CN-Desktop

    A skill your agent uses when starting or verifying Hermes Agent CN Desktop with the latest Hermes-CN-Desktop and Hermes-CN-Core branches — dev smoke test (pnpm tauri:dev), packaged beta/release…

    1.8k GitHub stars~1.8k tokensUpdated 18 days ago
    Testing & QAAuto-check passed

  • OpenWork Electron Browser Automation

    different-ai/openwork

    Attaches OpenCode browser tools to the OpenWork Electron dev app through CDP to explore its UI, send a composer task and debug, not to give test verdicts.

    24k GitHub stars~780 tokensUpdated today
    Testing & QAAuto-check passed

Works with

Categories

Questions about Ya Run

What does Ya Run do?

Launch and drive Yep Anywhere — an isolated dev server plus real browser interaction — and run the repository's check suite. Ya Run is an agent skill from kzahel/yepanywhere. Launch and drive Yep Anywhere — an isolated dev server plus real browser interaction — and run the repository's check suite.

When should I use Ya Run?

Ya Run fits situations like: smoke-test the app rather than only build; tasks that involve QA and bug reports.

How do I install Ya Run in Claude Code?

Run `npx skills add kzahel/yepanywhere --skill ya-run -a claude-code`. Or copy the skill folder (.claude/skills/ya-run in kzahel/yepanywhere) into .claude/skills/ya-run in your project. Claude Code loads it when a task matches its description.

How do I install Ya Run in Codex?

Run `npx skills add kzahel/yepanywhere --skill ya-run -a codex`. Or copy the skill folder (.claude/skills/ya-run in kzahel/yepanywhere) into .agents/skills/ya-run in your project. Codex loads it when a task matches its description.

Can I use Ya Run 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 kzahel/yepanywhere --skill ya-run -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ya-run, .gemini/skills/ya-run, .github/skills/ya-run and .opencode/skills/ya-run in your project.

What does Ya Run need to run?

Going by SKILL.md and its folder, Ya Run needs the command-line tools its instructions call (pnpm and curl).

Does Ya Run access the network?

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

Is Ya Run 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 Ya Run use?

Ya Run 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 Ya Run use?

About 957 tokens (SKILL.md is roughly 3.8k 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 Ya Run?

Skills that share tags, products or a category with Ya Run: Next QA Loop (breaking-brake/cc-wf-studio, 5.4k stars), DeerFlow Smoke Test (bytedance/deer-flow, 84k stars), OpenWork Desktop CDP Driver (different-ai/openwork, 24k stars) and Vitest (supabase/supabase, 111k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ya Run?

kzahel (a GitHub user) maintains it in kzahel/yepanywhere, which has 534 GitHub stars. The repository was last updated on October 9, 2026.

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