Agent skill

Testing Pd Hunter Frontend

by FuZoe in FuZoe/PD-Hunter

Test the PD-Hunter Next.js frontend end-to-end. An agent skill from FuZoe/PD-Hunter.

MITAuto-check passedFrontend & Design

Install Testing Pd Hunter Frontend

skills CLI
$ npx skills add FuZoe/PD-Hunter --skill testing-pd-hunter-frontend -a claude-code

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

GitHub CLI
$ gh skill install FuZoe/PD-Hunter testing-pd-hunter-frontend --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/FuZoe/PD-Hunter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/testing-pd-hunter-frontend .claude/skills/testing-pd-hunter-frontend && 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
testing-pd-hunter-frontend
GitHub stars
123
Token cost
~681 tokens
SKILL.md length
240 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Test the PD-Hunter Next.js frontend end-to-end. An agent skill from FuZoe/PD-Hunter.

  • Verifying UI changes
  • SKILL.md covers Prerequisites, Setup, Serving for Testing and Key Test Scenarios, plus 3 more sections
  • Calls npm and npx

What it does

Testing Pd Hunter Frontend is an agent skill from FuZoe/PD-Hunter. Test the PD-Hunter Next.js frontend end-to-end. Use when verifying UI changes, routing, or data display.

Its SKILL.md is about 680 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 Frontend & Design. It works with Next.js. The repository describes itself as: AI-powered bounty intelligence dashboard for Github repositories. The licence is MIT.

When your agent uses it

  • Verifying UI changes

Example prompts

  • “/testing-pd-hunter-frontend”

Requirements

  • Python 3
  • Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit 014b5ae. 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:

    • npm
    • npx

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

  • Network

    No URLs in SKILL.md. Its commands use npm and npx, 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

Testing Pd Hunter Frontend loads about 681 tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 240 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~681

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 FuZoe/PD-Hunter at commit 014b5ae, republished under its MIT licence (© FuZoe). 240 words, ~681 tokens.

Download SKILL.mdSave it as .claude/skills/testing-pd-hunter-frontend/SKILL.md (or your agent's skills folder).
name
testing-pd-hunter-frontend
description
Test the PD-Hunter Next.js frontend end-to-end. Use when verifying UI changes, routing, or data display.

Testing PD-Hunter Frontend

Prerequisites

  • Node.js 18+ installed
  • enriched_bounties.json present at repo root (used by api-server.ts as fallback)

Setup

bash
cd frontend
npm install
npm run build   # generates static export in out/

Serving for Testing

Use static build, NOT dev server for testing routes with output: "export". The dev server has strict generateStaticParams enforcement that may differ from production behavior.

bash
npm install -g serve
serve frontend/out -l 3002 --no-clipboard
# WITHOUT -s flag (SPA mode breaks static routing)

Clean URLs work automatically with serve (e.g., /bounty/commaai-flash--42 maps to commaai-flash--42.html).

Do NOT use serve -s — it enables SPA fallback that serves index.html for all routes, breaking static page routing.

Do NOT use Python http.server — it doesn't handle clean URLs (requires .html extension).

Key Test Scenarios

Bounty Detail Routes
  • Bounty detail pages use composite slug format: /bounty/{owner}-{repo}--{number}
  • The bountySlug() function in frontend/src/lib/utils.ts generates slugs
  • Collision data (as of May 2026): #42 (flash/website), #30 (agnos-builder/website)
Backward Compatibility
  • Unique bare numbers (e.g., /bounty/2281) resolve directly to the bounty
  • Colliding bare numbers (e.g., /bounty/42) show a disambiguation page (BountyDisambiguation.tsx)
  • Non-existent numbers return 404
Data Loading
  • Homepage loads data client-side from ./data/enriched_bounties.json
  • Bounty detail pages are statically generated (SSG) — data is baked into HTML at build time
  • Data endpoint: /data/enriched_bounties.json

Verification Commands

bash
# Lint and typecheck
cd frontend && npm run lint && npx tsc --noEmit

# Check build generates expected page count
npm run build 2>&1 | grep "Generating static pages"

# Verify no duplicate static paths
ls frontend/out/bounty/ | sort | uniq -d  # should be empty

# Verify collision files exist separately
ls frontend/out/bounty/ | grep -E '(flash--42|website--42)'

Common Issues

  • Dev server (npm run dev) might fail with "missing param in generateStaticParams" for dynamically added routes — use static build instead
  • Homepage may show "Loading bounties" indefinitely in dev mode if the data file path doesn't resolve — this is a dev-mode issue, not a production bug
  • The serve package requires explicit --no-clipboard on headless environments

Devin Secrets Needed

None — no authentication required for local testing.

© FuZoe, 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/testing-pd-hunter-frontend of FuZoe/PD-Hunter.

Open the folder on GitHubat commit 014b5ae

Compare with similar skills

Testing Pd Hunter Frontend 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.

Testing Pd Hunter Frontend compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Testing Pd Hunter Frontend this skillFuZoe/PD-Hunter123—~681Automated safety check: PassMIT
Chakra UI v3 Builderchakra-ui/chakra-ui41k—~3.1kAutomated safety check: PassMIT
React View Transitions Guidevercel-labs/next-beats16810 repos~3.1kAutomated safety check: PassMIT
Website ClonerJCodesMore/ai-website-cloner-template36k—~1.7kAutomated safety check: PassMIT
Wcag Audit PatternsvmDeshpande/ai-agent-automation17811 repos~610Automated safety check: PassApache-2.0
Vercel React Best Practicessanity-io/sanity6.4k129 repos~1.6kAutomated safety check: PassMIT

Similar skills

  • Chakra UI v3 Builder

    chakra-ui/chakra-ui

    Builds responsive, accessible Chakra UI v3 components and layouts, sets up Chakra in new or existing projects, and designs themes with tokens, semantic tokens and recipes.

    41k GitHub stars~3.1k tokensUpdated 3 days ago
    Frontend & DesignAuto-check passed
  • React View Transitions Guide

    vercel-labs/next-beats

    Official

    Guides implementing animated page and state transitions in React with the native View Transition API, covering shared elements, list reorders and directional navigation.

    168 GitHub starsUsed in 10 repos~3.1k tokens
    Frontend & DesignAuto-check passed
  • Website Cloner

    JCodesMore/ai-website-cloner-template

    Rebuilds existing web pages as editable local code that matches their content, assets, responsive layout and interactions, including Framer sites and animated pages.

    36k GitHub stars~1.7k tokensUpdated 4 days ago
    Frontend & DesignAuto-check passed
  • Wcag Audit Patterns

    vmDeshpande/ai-agent-automation

    Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance.

    178 GitHub starsUsed in 11 repos~610 tokens
    Frontend & DesignAuto-check passed
  • Official

    React and Next.js performance optimization guidelines from Vercel Engineering.

    6.4k GitHub starsUsed in 129 repos~1.6k tokens
    Frontend & DesignAuto-check passed
  • Turnstile Spin

    cloudflare/skills

    Official

    Set up, repair, or migrate to Cloudflare Turnstile bot verification in an existing frontend and backend, including server-side Siteverify.

    3k GitHub starsUsed in 4 repos~7.2k tokens
    Frontend & DesignAuto-check: notes

Works with

Questions about Testing Pd Hunter Frontend

What does Testing Pd Hunter Frontend do?

Test the PD-Hunter Next.js frontend end-to-end. An agent skill from FuZoe/PD-Hunter. Testing Pd Hunter Frontend is an agent skill from FuZoe/PD-Hunter.js frontend end-to-end.

When should I use Testing Pd Hunter Frontend?

Testing Pd Hunter Frontend fits situations like: verifying UI changes.

How do I install Testing Pd Hunter Frontend in Claude Code?

Run `npx skills add FuZoe/PD-Hunter --skill testing-pd-hunter-frontend -a claude-code`. Or copy the skill folder (.agents/skills/testing-pd-hunter-frontend in FuZoe/PD-Hunter) into .claude/skills/testing-pd-hunter-frontend in your project. Claude Code loads it when a task matches its description.

How do I install Testing Pd Hunter Frontend in Codex?

Run `npx skills add FuZoe/PD-Hunter --skill testing-pd-hunter-frontend -a codex`. Or copy the skill folder (.agents/skills/testing-pd-hunter-frontend in FuZoe/PD-Hunter) into .agents/skills/testing-pd-hunter-frontend in your project. Codex loads it when a task matches its description.

Can I use Testing Pd Hunter Frontend 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 FuZoe/PD-Hunter --skill testing-pd-hunter-frontend -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/testing-pd-hunter-frontend, .gemini/skills/testing-pd-hunter-frontend, .github/skills/testing-pd-hunter-frontend and .opencode/skills/testing-pd-hunter-frontend in your project.

What does Testing Pd Hunter Frontend need to run?

Going by SKILL.md and its folder, Testing Pd Hunter Frontend needs the command-line tools its instructions call (npm and npx). Our summary lists: Python 3; Node.js.

Does Testing Pd Hunter Frontend access the network?

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

Is Testing Pd Hunter Frontend 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 Testing Pd Hunter Frontend use?

Testing Pd Hunter Frontend 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 Testing Pd Hunter Frontend use?

About 681 tokens (SKILL.md is roughly 2.7k 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 Testing Pd Hunter Frontend?

Skills that share tags, products or a category with Testing Pd Hunter Frontend: Chakra UI v3 Builder (chakra-ui/chakra-ui, 41k stars), React View Transitions Guide (vercel-labs/next-beats, 168 stars), Website Cloner (JCodesMore/ai-website-cloner-template, 36k stars) and Wcag Audit Patterns (vmDeshpande/ai-agent-automation, 178 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Testing Pd Hunter Frontend?

FuZoe (a GitHub user) maintains it in FuZoe/PD-Hunter, which has 123 GitHub stars. The repository was last updated on October 9, 2026.

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