Agent skill

PR Test

by Elite588 in Elite588/AUTOGPT

E2E manual testing of PRs/branches using docker compose, agent-browser, and API calls.

Custom licenceAuto-check: notesTesting & QA

Install PR Test

skills CLI
$ npx skills add Elite588/AUTOGPT --skill pr-test -a claude-code

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

GitHub CLI
$ gh skill install Elite588/AUTOGPT pr-test --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/Elite588/AUTOGPT.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/pr-test .claude/skills/pr-test && 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
pr-test
GitHub stars
103
Token cost
~9.4k tokens
SKILL.md length
2,316 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
Custom licence

At a glance

E2E manual testing of PRs/branches using docker compose, agent-browser, and API calls.

  • Works in 5 steps: Screenshots at Every Step → Screenshots MUST Be Posted to PR → State Verification with Before/After… → …
  • User asks to manually test a PR
  • SKILL.md covers Critical Requirements, State Manipulation for…, Arguments and Step 0: Resolve the target, plus 8 more sections
  • Calls docker, curl and gh; reaches openrouter.ai and github.com; needs CHAT_API_KEY and CLAUDE_CODE_OAUTH_TOKEN

What it does

PR Test is an agent skill from Elite588/AUTOGPT. E2E manual testing of PRs/branches using docker compose, agent-browser, and API calls. TRIGGER when user asks to manually test a PR, test a feature end-to-end, or run integration tests against a running system.

Its SKILL.md is about 9.4k 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, QA and bug reports and Integration testing. It works with Docker. The repository describes itself as: AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters. It is a powerful platform…

When your agent uses it

  • User asks to manually test a PR
  • Test a feature end-to-end
  • Run integration tests against a running system

Example prompts

  • “/pr-test”

Requirements

  • Python 3
  • Node.js
  • Docker
  • A credential in CLAUDE_CODE_OAUTH_TOKEN
  • A credential in CLAUDE_CODE_REFRESH_TOKEN

Workflow steps

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

  1. Screenshots at Every Step
  2. Screenshots MUST Be Posted to PR
  3. State Verification with Before/After Evidence
  4. Negative Test Cases Are Mandatory
  5. Test Report Must Include Full Evidence

What it can do on your machine

Read from SKILL.md and the folder at commit 9e4bc5b. 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:

    • docker
    • curl
    • gh
    • jq
    • git
    • claude
    • bash
    • npm
    • apt-get

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • openrouter.ai
    • github.com
    • raw.githubusercontent.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • CHAT_API_KEY
    • CLAUDE_CODE_OAUTH_TOKEN
    • ANON_KEY
    • CLAUDE_CODE_REFRESH_TOKEN
    • OPEN_ROUTER_API_KEY
    • NEXT_PUBLIC_SUPABASE_ANON_KEY

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

Context cost

PR Test loads about 9.4k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 2,316 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~55
When it runs · the whole SKILL.md, loaded when a task matches
~9.4k

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:185
    ### 3a. Copy .env files from the root worktree
  • NoteMentions a .env fileSKILL.md:187
    rktree (`$REPO_ROOT`) has the canonical `.env` files with all API keys. Copy them to the target worktree:
  • NoteMentions a .env fileSKILL.md:190
    # CRITICAL: .env files are NOT checked into git. They must be copied manually.
  • NoteMentions a .env fileSKILL.md:191
    cp $REPO_ROOT/autogpt_platform/.env $PLATFORM_DIR/.env
  • NoteMentions a .env fileSKILL.md:192
    cp $REPO_ROOT/autogpt_platform/backend/.env $BACKEND_DIR/.env
  • NoteMentions a .env fileSKILL.md:193
    cp $REPO_ROOT/autogpt_platform/frontend/.env $FRONTEND_DIR/.env
  • NoteMentions a .env fileSKILL.md:204
    from your host and auto-update `backend/.env` (works on macOS, Linux, and Windows/WSL):
  • NoteMentions a .env fileSKILL.md:207
    H_TOKEN + CLAUDE_CODE_REFRESH_TOKEN into .env
  • NoteMentions a .env fileSKILL.md:208
    _claude_token.sh --env-file $BACKEND_DIR/.env
  • NoteMentions a .env fileSKILL.md:216
    E_CLAUDE_CODE_SUBSCRIPTION=true` in the `.env` file. On container startup, the backend auto-provisions `~/.claude/.crede

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 2,316 words (~9,360 tokens).

“Test a PR/branch end-to-end by building the full platform, interacting via browser and API, capturing screenshots, and reporting results.”

— opening of SKILL.md by Elite588, Custom licence
name
pr-test
user-invocable
true
argument-hint
[worktree path or PR number] — tests the PR in the given worktree. Optional flags: --fix (auto-fix issues found)
metadata.author
autogpt-team
metadata.version
2.0.0

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/pr-test of Elite588/AUTOGPT.

Open the folder on GitHubat commit 9e4bc5b

Compare with similar skills

PR Test 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.

PR Test compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
PR Test this skillElite588/AUTOGPT103—~9.4kAutomated safety check: NotesCustom licence
Go Redis Client Test Runnerredis/go-redis22k—~786Automated safety check: PassBSD-2-Clause
Testing QAaiskillstore/marketplace4303 repos~1.2kAutomated safety check: PassNone
DeerFlow Smoke Testbytedance/deer-flow83k—~2.5kAutomated safety check: NotesMIT
MongoDB Source Connector E2E Harnessairbytehq/airbyte22k—~1.9kAutomated safety check: PassCustom licence
Senior QAnicepkg/auto-company1923 repos~1.1kAutomated safety check: NotesNone

Similar skills

  • Official

    Explains how to run go-redis tests: the Docker Compose stack, make targets, focusing a single Ginkgo spec, the e2e suite and the version environment variables.

    22k GitHub stars~786 tokensUpdated today
    Testing & QAAuto-check passed
  • Testing QA

    aiskillstore/marketplace

    Comprehensive testing and QA workflow covering unit testing, integration testing, E2E testing, browser automation, and quality assurance.

    430 GitHub starsUsed in 3 repos~1.2k tokens
    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.

    83k GitHub stars~2.5k tokensUpdated today
    Testing & QAAuto-check: notes
  • Official

    Starts a throwaway MongoDB 7.0 replica set and runs the Airbyte spec, check, discover and read commands against source-mongodb-v2 images for local end-to-end testing.

    22k GitHub stars~1.9k tokensUpdated today
    Testing & QAAuto-check passed
  • Senior QA

    nicepkg/auto-company

    Comprehensive QA and testing skill for quality assurance, test automation, and testing strategies for ReactJS, NextJS, NodeJS applications.

    192 GitHub starsUsed in 3 repos~1.1k tokens
    Testing & QAAuto-check: notes
  • Official

    Starts a local PostgreSQL 16 container, loads SQL fixtures and runs the Airbyte spec, check, discover and read commands against a chosen source-postgres image.

    22k GitHub stars~2.5k tokensUpdated today
    Testing & QAAuto-check passed

More from Elite588/AUTOGPT

All 8 skills in this repo
  • Open PR

    Elite588/AUTOGPT

    Open a pull request with proper PR template, test coverage, and review workflow.

    103 GitHub stars~1.3k tokensUpdated 5 mo ago
    Auto-check passed
  • PR Review

    Elite588/AUTOGPT

    Review a PR for correctness, security, code quality, and testing issues.

    103 GitHub stars~768 tokensUpdated 5 mo ago
    Auto-check passed
  • Orchestrate

    Elite588/AUTOGPT

    Meta-agent supervisor that manages a fleet of Claude Code agents running in tmux windows.

    103 GitHub stars~9.2k tokensUpdated 5 mo ago
    Auto-check: warnings
  • Setup Repo

    Elite588/AUTOGPT

    Initialize a worktree-based repo layout for parallel development.

    103 GitHub stars~1.6k tokensUpdated 5 mo ago
    Auto-check: notes
  • Worktree

    Elite588/AUTOGPT

    Set up a new git worktree for parallel development. An agent skill from Elite588/AUTOGPT.

    103 GitHub stars~667 tokensUpdated 5 mo ago
    Auto-check: notes
  • Write Frontend Tests

    Elite588/AUTOGPT

    Analyze the current branch diff against dev, plan integration tests for changed frontend pages/components, and write them.

    103 GitHub stars~1.9k tokensUpdated 5 mo ago
    Auto-check passed

Works with

Categories

Questions about PR Test

What does PR Test do?

E2E manual testing of PRs/branches using docker compose, agent-browser, and API calls. PR Test is an agent skill from Elite588/AUTOGPT. E2E manual testing of PRs/branches using docker compose, agent-browser, and API calls.

When should I use PR Test?

PR Test fits situations like: user asks to manually test a PR; test a feature end-to-end; run integration tests against a running system.

How do I install PR Test in Claude Code?

Run `npx skills add Elite588/AUTOGPT --skill pr-test -a claude-code`. Or copy the skill folder (.claude/skills/pr-test in Elite588/AUTOGPT) into .claude/skills/pr-test in your project. Claude Code loads it when a task matches its description.

How do I install PR Test in Codex?

Run `npx skills add Elite588/AUTOGPT --skill pr-test -a codex`. Or copy the skill folder (.claude/skills/pr-test in Elite588/AUTOGPT) into .agents/skills/pr-test in your project. Codex loads it when a task matches its description.

Can I use PR Test 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 Elite588/AUTOGPT --skill pr-test -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pr-test, .gemini/skills/pr-test, .github/skills/pr-test and .opencode/skills/pr-test in your project.

What does PR Test need to run?

Going by SKILL.md and its folder, PR Test needs the command-line tools its instructions call (docker, curl, gh, jq, git and claude) and credentials named CHAT_API_KEY, CLAUDE_CODE_OAUTH_TOKEN, ANON_KEY and CLAUDE_CODE_REFRESH_TOKEN. Our summary lists: Python 3; Node.js; Docker; A credential in CLAUDE_CODE_OAUTH_TOKEN; A credential in CLAUDE_CODE_REFRESH_TOKEN.

Does PR Test access the network?

SKILL.md names 3 domains. In commands or code: openrouter.ai, github.com and raw.githubusercontent.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is PR Test 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 PR Test use?

PR Test has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does PR Test use?

About 9.4k tokens (SKILL.md is roughly 37k 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 PR Test?

Skills that share tags, products or a category with PR Test: Go Redis Client Test Runner (redis/go-redis, 22k stars), Testing QA (aiskillstore/marketplace, 430 stars), DeerFlow Smoke Test (bytedance/deer-flow, 83k stars) and MongoDB Source Connector E2E Harness (airbytehq/airbyte, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains PR Test?

Elite588 (a GitHub user) maintains it in Elite588/AUTOGPT, which has 103 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on April 16, 2026.

Source: Elite588/AUTOGPT on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.