Agent skill

Petshare Setup

by portons in portons/codex-pet-share

A skill your agent uses when an agent needs to fork, rebrand, deploy, adapt, or rebuild a Codex Pet Share style app with animated pet uploads, generated previews, gallery downloads, provider…

MITAuto-check: notesMarketing & SEO

Install Petshare Setup

skills CLI
$ npx skills add portons/codex-pet-share --skill petshare-setup -a claude-code

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

GitHub CLI
$ gh skill install portons/codex-pet-share petshare-setup --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/portons/codex-pet-share.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/petshare-setup .claude/skills/petshare-setup && 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
petshare-setup
GitHub stars
135
Token cost
~1.9k tokens
SKILL.md length
882 words
Files
4 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when an agent needs to fork, rebrand, deploy, adapt, or rebuild a Codex Pet Share style app with animated pet uploads, generated previews, gallery downloads, provider…

  • Works in 6 steps: Identify whether the task is setup,… → Load only the reference file needed for… → Inspect current source before deciding;… → …
  • An agent needs to fork
  • SKILL.md covers First Read, Non-Negotiables, Core Workflow and Repository Map, plus 3 more sections
  • Calls npm, node and npx; needs VITE_REALTIME_PUBLIC_KEY and AUTH_SECRET

What it does

Petshare Setup is an agent skill from portons/codex-pet-share. Use when an agent needs to fork, rebrand, deploy, adapt, or rebuild a Codex Pet Share style app with animated pet uploads, generated previews, gallery downloads, provider adapters, and multiplayer playground rooms.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/petshare-architecture.md` and `references/security-boundary.md`).

It sits in Marketing & SEO, covering Brand strategy and identity. It works with Vite. The licence is MIT.

When your agent uses it

  • An agent needs to fork
  • Rebuild a Codex Pet Share style app with animated pet uploads
  • Generated previews
  • Gallery downloads

Example prompts

  • “/petshare-setup”

Requirements

  • Node.js
  • A credential in VITE_REALTIME_PUBLIC_KEY
  • A credential in AUTH_SECRET

Workflow steps

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

  1. Identify whether the task is setup, provider work, upload/asset work,
  2. Load only the reference file needed for that surface.
  3. Inspect current source before deciding; this repo has explicit adapter and
  4. Make the smallest code/doc changes that satisfy the user request.
  5. Run the relevant validation commands below.
  6. If publishing or handing off public code, run the exposure checks from

What it can do on your machine

Read from SKILL.md and the folder at commit 27996ca. 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
    • node
    • 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 these keys or tokens, usually read from environment variables:

    • VITE_REALTIME_PUBLIC_KEY
    • AUTH_SECRET

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

Context cost

Petshare Setup loads about 1.9k tokens when it runs, and up to ~5.3k if it reads all its reference files. Until then it costs about 57 tokens; SKILL.md has 882 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.3k

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:41
    - Never commit `.env`, `.env.local`, API tokens, salts, database passwords,
  • NoteMentions a .env fileSKILL.md:97
    cp .env.example .env.local
  • NoteMentions a .env fileSKILL.md:135
    ne, install, and copy `.env.example` to `.env.local`.

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 portons/codex-pet-share at commit 27996ca, republished under its MIT licence (© portons). 882 words, ~1,936 tokens.

Download SKILL.mdSave it as .claude/skills/petshare-setup/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
petshare-setup
description
Use when an agent needs to fork, rebrand, deploy, adapt, or rebuild a Codex Pet Share style app with animated pet uploads, generated previews, gallery downloads, provider adapters, and multiplayer playground rooms.

Petshare Setup

Use this skill when an agent is asked to spin up, fork, rebrand, deploy, or modify this repository or a close derivative. The app is a self-hostable React/Vite pixel-pet sharing surface: users upload Codex-compatible pet packages, browse animated previews, download packages/GIFs, and join multiplayer playground rooms.

This is a repo-scoped Codex skill. Keep it under .agents/skills/petshare-setup/ so Codex can discover it from the repository.

First Read

Before editing, read:

  • README.md
  • docs/GETTING_STARTED.md
  • docs/PROVIDER_ADAPTERS.md
  • AGENTS.md
  • references/petshare-architecture.md when touching app behavior, uploads, previews, animations, rooms, provider adapters, or deployment
  • references/security-boundary.md when publishing, documenting public setup, reviewing exposure risk, or changing auth/moderation/provider surfaces

Non-Negotiables

  • Keep changes literal to the request. Do not add fallbacks, backwards compatibility, provider-specific public env vars, or unrelated hardening.
  • Keep the browser public contract provider-neutral. Public build vars are only: VITE_APP_API_BASE_URL, VITE_PUBLIC_APP_ORIGIN, VITE_REALTIME_URL, VITE_REALTIME_PUBLIC_KEY, VITE_APP_NAME, VITE_APP_HANDLE, VITE_APP_TAGLINE, and VITE_APP_REPO_URL.
  • Never commit .env, .env.local, API tokens, salts, database passwords, provider account identifiers, generated migration exports, or local auth data.
  • Use provider adapters as replaceable boundaries. Feature code under src/ should not branch on provider names.
  • Do not turn this skill into an abuse manual. Do not add copy-paste scripts, unauthenticated client examples, raw room-event payload recipes, rate-limit thresholds, bypass instructions, scraping loops, or moderation-evasion advice.
  • For ports, follow AGENTS.md: check a requested port before starting a process, and never kill reserved ports unless explicitly asked.

Core Workflow

  1. Identify whether the task is setup, provider work, upload/asset work, preview/GIF work, animation/playground work, multiplayer rooms, rebranding, or security/publication review.
  2. Load only the reference file needed for that surface.
  3. Inspect current source before deciding; this repo has explicit adapter and feature boundaries.
  4. Make the smallest code/doc changes that satisfy the user request.
  5. Run the relevant validation commands below.
  6. If publishing or handing off public code, run the exposure checks from references/security-boundary.md.

Repository Map

  • src/domain/*: shared types, route parsing, API URLs, session storage, gallery constants, pet kind/tag config, and sprite atlas constants.
  • src/app/*: SPA composition, route effects, API/session hooks, shell chrome, modal composition, and cross-feature refresh/navigation.
  • src/uploads/*: file inputs, manifest parsing, slug normalization, upload validation preview, generated share.png, generated preview.webp, generated poster.webp, and POST /api/pets form assembly.
  • src/pets/*: gallery/detail pet surfaces, sprite previews, cursor preview, metadata editing, tag/kind management, delete, share, and GIF export wiring.
  • src/downloads/*: package modal, install command UI, spritesheet fetch, GIF encoding, and client-side blob download.
  • src/gallery/*: browse/search/filter/sort/pagination, creator pages, collections, live room rail, and leaderboard.
  • src/playground/*: Three.js playground, sprite animation, room overlays, realtime handlers, UI controls, minimap, chat, NPCs, ball, and trampoline.
  • src/realtime/providerClient.ts and src/realtime/roomChannel.ts: generic frontend realtime exports.
  • src/realtime/adapters/*: current provider-specific realtime implementation.
  • adapters/cloudflare-worker/*: checked-in API, D1 schema, R2 storage, Durable Object realtime, Worker Assets hosting, and Cloudflare deployment.
  • adapters/cloudflare-pages/*: optional crawler/social-share page functions for static hosts.
  • scripts/*: public env validation and generated brand/social-card assets.

If a feature file starts absorbing unrelated behavior, extract into the matching feature folder rather than adding another section to a large component.

Setup Path

bash
npm install
cp .env.example .env.local
node scripts/check-public-build-env.mjs
npm run build
npm run dev

Vite defaults to http://127.0.0.1:5173.

The build validator fails if required public env vars are missing, malformed, or if a VITE_* name looks secret-like. For provider/env changes, verify .env.example, scripts/check-public-build-env.mjs, docs, and adapter config agree exactly.

Show full SKILL.md (359 more words)Show less

Validation Before Handoff

Always run:

bash
npx tsc -b --pretty false
npm run build

When the Cloudflare adapter changed, also run:

bash
npm run adapter:cloudflare:typecheck

For frontend/UI/playground changes, open the changed route in a real browser and verify the interaction. For room changes, test at least one hosted room and one joined room with two sessions. For upload changes, upload or seed one valid pet and inspect detail, gallery preview, package download, GIF export, and playground load.

Common Change Recipes

Spin Up A New Fork
  1. Clone, install, and copy .env.example to .env.local.
  2. Set provider-neutral public env and brand env.
  3. Choose a backend provider.
  4. For Cloudflare, create Worker, D1, R2, and Durable Object resources; set AUTH_SECRET and PET_STATS_SALT with Wrangler secrets; update only the adapter config values that correspond to created resources.
  5. Run D1 migrations.
  6. Build and run the app.
  7. Register, sign out, sign in, upload one valid pet, open detail, open playground, and open a room.
Add A New Backend Provider
  1. Add provider code under adapters/<provider>/.
  2. Implement the same HTTP response shapes from src/domain/types.ts.
  3. Implement the same upload asset contract and validation behavior.
  4. Add realtime code under src/realtime/adapters/.
  5. Update only currentClient.ts and currentRoomChannel.ts to point to the new implementation after it satisfies the room interface.
  6. Keep docs provider-neutral except for the adapter-specific README.
Change The Sprite Atlas
  1. Update src/domain/config.ts and src/playground/core/config.ts together.
  2. Update backend validation dimensions in adapters/cloudflare-worker/src/api/validation.ts.
  3. Update preview generation and GIF export assumptions.
  4. Verify upload validation, gallery previews, detail previews, GIF export, solo playground, and room playback.
Change Multiplayer Behavior
  1. Start from src/realtime/roomTypes.ts and the RoomHandle contract.
  2. Update the provider adapter and all room handlers together.
  3. Keep event payloads serializable and small.
  4. Verify host, guest, leave/close, pet swap, chat, position, NPCs, toys, and collection permanent rooms.
Change Uploads Or Asset Storage
  1. Keep pet.json and spritesheet.webp as the package contract unless the user explicitly changes it.
  2. Preserve generated share.png, preview.webp, and poster.webp as app assets.
  3. Update frontend generation, backend validation, storage writes, serializer URLs, and download endpoint together.
  4. Verify upload error messages, validation card, detail route, share image, preview strip, package zip, and room sprite loading.

© portons, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in .agents/skills/petshare-setup of portons/codex-pet-share.

  • SKILL.md
  • agents/openai.yaml
  • references/petshare-architecture.md
  • references/security-boundary.md

Open the folder on GitHubat commit 27996ca

Compare with similar skills

Petshare Setup 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.

Petshare Setup compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Petshare Setup this skillportons/codex-pet-share135—~1.9kAutomated safety check: NotesMIT
Startup Designferdinandobons/startup-skill1.2k—~8.1kAutomated safety check: PassMIT
Brand Architecturearnabbagxd/Brand-building-skills719—~1.7kAutomated safety check: PassMIT
Linkedin Employee Advocacysergebulaev/linkedin-skills4.3k1 repos~1.5kAutomated safety check: PassMIT
Afa Brandafadtc/afa-dtc-skills1681 repos~3.9kAutomated safety check: PassCustom licence
Brand Contextarnabbagxd/Brand-building-skills719—~842Automated safety check: PassMIT

Similar skills

  • Startup Design

    ferdinandobons/startup-skill

    Design, validate, and plan a startup from scratch. An agent skill from ferdinandobons/startup-skill.

    1.2k GitHub stars~8.1k tokensUpdated 3 mo ago
    Marketing & SEOAuto-check passed
  • Brand Architecture

    arnabbagxd/Brand-building-skills

    Define how multiple brands, sub-brands, and product lines relate to each other under one organization.

    719 GitHub stars~1.7k tokensUpdated 3 mo ago
    Marketing & SEOAuto-check passed
  • Linkedin Employee Advocacy

    sergebulaev/linkedin-skills

    Stand up and run a LinkedIn employee advocacy program for a marketing or sales team.

    4.3k GitHub starsUsed in 1 repo~1.5k tokens
    Marketing & SEOAuto-check passed
  • Afa Brand

    afadtc/afa-dtc-skills

    DTC 品牌定位与识别引擎——品牌定位画布、品牌声音架构、品牌故事、视觉识别系统、品牌健康审计。Use when user mentions: 品牌定位, brand positioning, 品牌声音, brand voice, 品牌故事, brand story, 视觉识别, visual identity, 品牌策略, brand strategy, 品牌画布, 品牌建设, 品牌升级…

    168 GitHub starsUsed in 1 repo~3.9k tokens
    Marketing & SEOAuto-check passed
  • Brand Context

    arnabbagxd/Brand-building-skills

    Foundation skill that captures and stores core brand context — identity, audience, positioning, values, and voice.

    719 GitHub stars~842 tokensUpdated 3 mo ago
    Marketing & SEOAuto-check passed
  • Brand Naming

    arnabbagxd/Brand-building-skills

    Full brand naming workflow for founders, agencies, and businesses.

    719 GitHub stars~2.3k tokensUpdated 3 mo ago
    Marketing & SEOAuto-check passed

Works with

Categories

Questions about Petshare Setup

What does Petshare Setup do?

A skill your agent uses when an agent needs to fork, rebrand, deploy, adapt, or rebuild a Codex Pet Share style app with animated pet uploads, generated previews, gallery downloads, provider…. Petshare Setup is an agent skill from portons/codex-pet-share. Use when an agent needs to fork, rebrand, deploy, adapt, or rebuild a Codex Pet Share style app with animated pet uploads, generated previews, gallery downloads, provider adapters, and multiplayer playground rooms.

When should I use Petshare Setup?

Petshare Setup fits situations like: an agent needs to fork; rebuild a Codex Pet Share style app with animated pet uploads; generated previews; gallery downloads.

How do I install Petshare Setup in Claude Code?

Run `npx skills add portons/codex-pet-share --skill petshare-setup -a claude-code`. Or copy the skill folder (.agents/skills/petshare-setup in portons/codex-pet-share) into .claude/skills/petshare-setup in your project. Claude Code loads it when a task matches its description.

How do I install Petshare Setup in Codex?

Run `npx skills add portons/codex-pet-share --skill petshare-setup -a codex`. Or copy the skill folder (.agents/skills/petshare-setup in portons/codex-pet-share) into .agents/skills/petshare-setup in your project. Codex loads it when a task matches its description.

Can I use Petshare Setup 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 portons/codex-pet-share --skill petshare-setup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/petshare-setup, .gemini/skills/petshare-setup, .github/skills/petshare-setup and .opencode/skills/petshare-setup in your project.

What does Petshare Setup need to run?

Going by SKILL.md and its folder, Petshare Setup needs the command-line tools its instructions call (npm, node and npx) and credentials named VITE_REALTIME_PUBLIC_KEY and AUTH_SECRET. Our summary lists: Node.js; A credential in VITE_REALTIME_PUBLIC_KEY; A credential in AUTH_SECRET.

Does Petshare Setup 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 Petshare Setup 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 Petshare Setup use?

Petshare Setup 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 Petshare Setup use?

About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.4k tokens, read only when the agent opens those files.

What are the alternatives to Petshare Setup?

Skills that share tags, products or a category with Petshare Setup: Startup Design (ferdinandobons/startup-skill, 1.2k stars), Brand Architecture (arnabbagxd/Brand-building-skills, 719 stars), Linkedin Employee Advocacy (sergebulaev/linkedin-skills, 4.3k stars) and Afa Brand (afadtc/afa-dtc-skills, 168 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Petshare Setup?

portons (a GitHub user) maintains it in portons/codex-pet-share, which has 135 GitHub stars. The repository was last updated on September 30, 2026.

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