agent-browser-test-from-prd
Execute repository-local browser testcases with agent-browser against a target URL.
Skill by Fairy-Tail-Code
Chalk Labs
Need help deploying agent-browser-test-from-prd?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/fairy-tail-code-agent-browser-test-from-prd
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing, security, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-browser-test-from-prd
What's inside
- Skill name
agent-browser-test-from-prd- Description
- Execute repository-local browser testcases with agent-browser against a target URL. Use when Codex needs to read a specified code repo path, prefer the canonical testcase files `testcase/browser-regression-cases.md` and `testcase/browser-regression-guide.md`, fall back to scanning the repo's fixed `testcase/` directory when needed, load a specified account or auth file, auto-generate an isolated agent-browser session name in the format `abtp-<repo名>-<yyyyMMdd-HHmmss>`, log into the target site in headless mode, wait for Human-In-The-Loop OTP input when verification-code login is used, reuse saved browser state only when the user explicitly asks for reuse, and run the existing regression suite with evidence.
- License
- unknown
- Instructions
- 90 lines in SKILL.md · view on GitHub
Files (9)
- README.md
- SKILL.md
- openai.yaml · agents/
- 01-product.md · example/
- auth.example.json · example/
- image1.png · example/
- image2.png · example/
- auth-file-and-login.md · references/
- execution-and-reporting.md · references/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from Fairy-Tail-Code/Bobby
- 0.489score
claude-code
Fairy-Tail-Code
Delegate coding tasks to Claude Code via the claude_code MCP server.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
backend-delivery
Fairy-Tail-Code
Implement backend code changes in the target repository using workspace and shell MCP tools.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
browser-tester
Fairy-Tail-Code
Validate running applications with Playwright browser automation and focused interaction steps.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
verification-gate
Fairy-Tail-Code
Return structured verification gate results for the current delivery iteration.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
fullstack-analyst
Fairy-Tail-Code
Translate a product PRD into a fullstack implementation brief, design, and delivery plan.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
git-operator
Fairy-Tail-Code
Inspect local git state, review diffs, stage paths, and create local commits.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
runtime-go-toolchain
Fairy-Tail-Code
Prepare a Go toolchain for the current repository when runtime inference selects Go.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
backend-analyst
Fairy-Tail-Code
Translate a backend PRD into an implementation brief, design, and delivery plan.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
repo-surveyor
Fairy-Tail-Code
Inspect a repository and produce an implementation-oriented delivery survey.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
runtime-node-toolchain
Fairy-Tail-Code
Prepare a Node.js runtime for the current repository when runtime inference selects Node.js.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
runtime-python-toolchain
Fairy-Tail-Code
Prepare a Python runtime for the current repository when runtime inference selects Python.
SkillCFreshness: C★ 1Claude Code +9 - 0.485score
memory-manager
Fairy-Tail-Code
持久化记忆系统：在任务执行过程中将重要信息写入 ./memory 目录，并在任务开始时主动读取已有记忆。 触发时机：(1) 任何多步骤任务开始时，主动检查并加载记忆；(2) 任务过程中出现值得保留的信息时（用户偏好、决策原因、遇到的坑、项目结构、关键配置等）立即写入；(3) 任务结束时整理并归档本次新增的记忆。…
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 28, 2026 (6 months ago)
- Last release
- May 9, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/Fairy-Tail-Code/Bobby
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Fairy-Tail-Code
- 0.489score
claude-code
Fairy-Tail-Code
Delegate coding tasks to Claude Code via the claude_code MCP server.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
git-operator
Fairy-Tail-Code
Inspect local git state, review diffs, stage paths, and create local commits.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
browser-tester
Fairy-Tail-Code
Validate running applications with Playwright browser automation and focused interaction steps.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
backend-delivery
Fairy-Tail-Code
Implement backend code changes in the target repository using workspace and shell MCP tools.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
fullstack-analyst
Fairy-Tail-Code
Translate a product PRD into a fullstack implementation brief, design, and delivery plan.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
runtime-go-toolchain
Fairy-Tail-Code
Prepare a Go toolchain for the current repository when runtime inference selects Go.
SkillCFreshness: C★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get agent-browser-test-from-prd running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
agent-browser-test-from-prd skill. Agent Mart. https://agentmart.dev/skills/fairy-tail-code-agent-browser-test-from-prd (last updated 2026-10-24)