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

Register Generated Program

by myunwang in myunwang/LLMPET

Register a runnable project created or modified by Claude Code in LLMPET Launcher after it passes a real launch check.

MITAuto-check passedDevelopment

Install Register Generated Program

skills CLI
$ npx skills add myunwang/LLMPET --skill register-generated-program -a claude-code

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

GitHub CLI
$ gh skill install myunwang/LLMPET register-generated-program --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/myunwang/LLMPET.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/register-generated-program .claude/skills/register-generated-program && 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
register-generated-program
GitHub stars
123
Token cost
~555 tokens
SKILL.md length
207 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Register a runnable project created or modified by Claude Code in LLMPET Launcher after it passes a real launch check.

  • Works in 4 steps: Identify the user-facing launch path.… → Launch it in the real target… → Confirm an observable successful… → …
  • Other executable deliverables
  • SKILL.md covers Workflow and Boundaries
  • Calls node

What it does

Register Generated Program is an agent skill from myunwang/LLMPET. Register a runnable project created or modified by Claude Code in LLMPET Launcher after it passes a real launch check. Use for websites, apps, demos, servers, CLIs, and other executable deliverables. Do not use for source-only libraries, incomplete scaffolds, build-only outputs, or anything that has not actually launched successfully.

Its SKILL.md is about 560 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 Development, covering Project scaffolding. It works with macOS. The repository describes itself as: 🐙 盯着 Claude Code 的桌面宠物：随 agent 状态变表情、弹消息气泡、一键授权，并统计 token 用量与花费。本地优先、MIT。 The licence is MIT.

When your agent uses it

  • Other executable deliverables
  • Source-only libraries
  • Incomplete scaffolds
  • Build-only outputs

Example prompts

  • “/register-generated-program”

Workflow steps

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

  1. Identify the user-facing launch path. Prefer the same command or file the user should run later.
  2. Launch it in the real target environment. Compilation, lint, or unit tests alone do not count.
  3. Confirm an observable successful startup. If that remains unverified, do not register anything.
  4. Use exactly one of the following forms. Keep --provider claude; this skill must never attribute a program to Codex.

What it can do on your machine

Read from SKILL.md and the folder at commit 55f55f3. 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:

    • node

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

  • Network

    No URLs in SKILL.md.

    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

Register Generated Program loads about 555 tokens when it runs. Until then it costs about 91 tokens; SKILL.md has 207 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~91
When it runs · the whole SKILL.md, loaded when a task matches
~555

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 myunwang/LLMPET at commit 55f55f3, republished under its MIT licence (© myunwang). 207 words, ~555 tokens.

Download SKILL.mdSave it as .claude/skills/register-generated-program/SKILL.md (or your agent's skills folder).
name
register-generated-program
description
Register a runnable project created or modified by Claude Code in LLMPET Launcher after it passes a real launch check. Use for websites, apps, demos, servers, CLIs, and other executable deliverables. Do not use for source-only libraries, incomplete scaffolds, build-only outputs, or anything that has not actually launched successfully.

Register Claude Code Program

Add a Claude Code-created shortcut to LLMPET Launcher only after proving the deliverable really runs.

Workflow

  1. Identify the user-facing launch path. Prefer the same command or file the user should run later.
  2. Launch it in the real target environment. Compilation, lint, or unit tests alone do not count.
  3. Confirm an observable successful startup. If that remains unverified, do not register anything.
  4. Use exactly one of the following forms. Keep --provider claude; this skill must never attribute a program to Codex.

For a command:

sh
node "$HOME/.octopus/bin/register-generated-program.js" --verified \
  --name "Program name" \
  --description "What the shortcut opens" \
  --cwd "/absolute/project/path" \
  --command "npm" --arg "run" --arg "dev" \
  --provider claude

For an app bundle or directly openable file:

sh
node "$HOME/.octopus/bin/register-generated-program.js" --verified \
  --name "Program name" \
  --cwd "/absolute/project/path" \
  --open "/absolute/project/path/Program.app" \
  --provider claude
  1. Add --icon /absolute/path only when a suitable local icon already exists.
  2. Report registration only after the command prints JSON with "ok": true.

Boundaries

  • Use absolute paths.
  • If the registrar is missing, ask the user to open LLMPET Workbench → Generated Programs and authorize the Claude Code skill. Do not recreate LLMPET's registry format manually.
  • Pass arguments as repeated --arg values. Do not embed shell pipelines in --command.
  • Register the canonical project once; the same path and launch command update the existing shortcut.
  • Never pass --verified before a real launch succeeds.
  • Registration changes only LLMPET's local shortcut index. It does not copy, deploy, publish, or delete the project.

© myunwang, 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/register-generated-program of myunwang/LLMPET.

Open the folder on GitHubat commit 55f55f3

Compare with similar skills

Register Generated Program 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.

Register Generated Program compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Register Generated Program this skillmyunwang/LLMPET123—~555Automated safety check: PassMIT
Databricks Appsdatabricks/databricks-agent-skills345—~5.4kAutomated safety check: PassCustom licence
Update Dependenciessesori-ai/sesori_apps_monorepo126—~7.8kAutomated safety check: PassCustom licence
Flutter MCP Toolkit Maintain macOSArenukvern/mcp_flutter386—~665Automated safety check: PassMIT
Mole Bug Patternstw93/Mole70k—~2kAutomated safety check: PassGPL-3.0
Nx Generatenomcopter/react-mosaic4.8k7 repos~1.9kAutomated safety check: PassCustom licence

Similar skills

  • Databricks Apps

    databricks/databricks-agent-skills

    Official

    Build apps on Databricks Apps platform. An agent skill from databricks/databricks-agent-skills.

    345 GitHub stars~5.4k tokensUpdated today
    DevelopmentAuto-check passed

  • Update Dependencies

    sesori-ai/sesori_apps_monorepo

    Weekly dependency update workflow for Sesori Apps Monorepo. An agent skill from sesori-ai/sesori_apps_monorepo.

    126 GitHub stars~7.8k tokensUpdated today
    DevelopmentAuto-check passed

  • Flutter MCP Toolkit Maintain macOS

    Arenukvern/mcp_flutter

    Maintains showcase/fluttertestapp macOS showcase, native intentcall hooks (codegen, applinks invoke), and VM MCP validation.

    386 GitHub stars~665 tokensUpdated 5 days ago
    MobileAuto-check passed

  • Mole Bug Patterns

    tw93/Mole

    A catalog of recurring bug shapes in the Mole Mac cleaner, used to review safety-sensitive diffs for deletion safety, unbounded commands, shell traps and weak tests.

    70k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed

  • Nx Generate

    nomcopter/react-mosaic

    Generate code using nx generators. An agent skill from nomcopter/react-mosaic.

    4.8k GitHub starsUsed in 7 repos~1.9k tokens
    DevelopmentAuto-check passed

  • Ponytail

    DavidObando/gsharp

    Forces the laziest solution that actually works, simplest, shortest, most minimal.

    565 GitHub starsUsed in 8 repos~1.7k tokens
    DevelopmentAuto-check passed

More from myunwang/LLMPET

  • Register Generated Program

    myunwang/LLMPET

    Register a runnable project created or modified by Codex in LLMPET Launcher after it passes a real launch check.

    123 GitHub stars~549 tokensUpdated 24 days ago
    Auto-check passed

Works with

Categories

Questions about Register Generated Program

What does Register Generated Program do?

Register a runnable project created or modified by Claude Code in LLMPET Launcher after it passes a real launch check. Register Generated Program is an agent skill from myunwang/LLMPET. Register a runnable project created or modified by Claude Code in LLMPET Launcher after it passes a real launch check.

When should I use Register Generated Program?

Register Generated Program fits situations like: other executable deliverables; source-only libraries; incomplete scaffolds; build-only outputs.

How do I install Register Generated Program in Claude Code?

Run `npx skills add myunwang/LLMPET --skill register-generated-program -a claude-code`. Or copy the skill folder (.claude/skills/register-generated-program in myunwang/LLMPET) into .claude/skills/register-generated-program in your project. Claude Code loads it when a task matches its description.

How do I install Register Generated Program in Codex?

Run `npx skills add myunwang/LLMPET --skill register-generated-program -a codex`. Or copy the skill folder (.claude/skills/register-generated-program in myunwang/LLMPET) into .agents/skills/register-generated-program in your project. Codex loads it when a task matches its description.

Can I use Register Generated Program 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 myunwang/LLMPET --skill register-generated-program -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/register-generated-program, .gemini/skills/register-generated-program, .github/skills/register-generated-program and .opencode/skills/register-generated-program in your project.

What does Register Generated Program need to run?

Going by SKILL.md and its folder, Register Generated Program needs the command-line tools its instructions call (node).

Does Register Generated Program access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Register Generated Program 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 Register Generated Program use?

Register Generated Program 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 Register Generated Program use?

About 555 tokens (SKILL.md is roughly 2.2k 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 Register Generated Program?

Skills that share tags, products or a category with Register Generated Program: Databricks Apps (databricks/databricks-agent-skills, 345 stars), Update Dependencies (sesori-ai/sesori_apps_monorepo, 126 stars), Flutter MCP Toolkit Maintain macOS (Arenukvern/mcp_flutter, 386 stars) and Mole Bug Patterns (tw93/Mole, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Register Generated Program?

myunwang (a GitHub user) maintains it in myunwang/LLMPET, which has 123 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 14, 2026.

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