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

LobeHub Builtin Tool Authoring

by lobehub in lobehub/lobehub

Guides building LobeHub builtin agent tools, from the manifest and execution runtime to executors, chat UI renders and registry wiring.

Custom licenceAuto-check passedDevelopment

Install LobeHub Builtin Tool Authoring

skills CLI
$ npx skills add lobehub/lobehub --skill builtin-tool -a claude-code

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

GitHub CLI
$ gh skill install lobehub/lobehub builtin-tool --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/lobehub/lobehub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/builtin-tool .claude/skills/builtin-tool && 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
builtin-tool
GitHub stars
83k
Token cost
~2.4k tokens
SKILL.md length
728 words
Files
14 (incl. references)
Skills in repo
50
Repo updated
First seen
Licence
Custom licence

At a glance

Guides building LobeHub builtin agent tools, from the manifest and execution runtime to executors, chat UI renders and registry wiring.

  • Works in 8 steps: lobe- identifier is permanent. It's… → ApiName is an as const object, not a TS… → Three result fields, three audiences → …
  • Creating a new builtin tool package in the LobeHub repository
  • SKILL.md covers Read These First, When to Use This Skill, Top-Level Design Principles and Package Layout (preferred,…, plus 2 more sections
  • Calls bunx and bun

What it does

A builtin tool is a package the agent runtime can call, and the skill describes it as five faces: the manifest, types and system role the model sees, an execution runtime usable on server or desktop, a frontend executor that wraps stores and services, the client UI for the chat, and the registry wiring that lets the framework find it.

Three entry points tell the agent what to read: an architecture reference for file locations and wiring, a tool-design reference for naming, API design and manifest writing, and a set of UI references covering inspectors, renders, placeholders, streaming, intervention and portals, with shared rules and diagnostics. It targets creating a new tool package, adding an API method, restyling client surfaces, registering a tool and debugging errors such as tool not found, API not found, a render that does not show or a placeholder that stays stuck.

When your agent uses it

  • Creating a new builtin tool package in the LobeHub repository
  • Adding an API method to an existing builtin tool
  • Building or restyling a tool's inspector, render or placeholder
  • Debugging a tool-not-found or stuck-placeholder error

Example prompts

  • “Add a new API method to an existing builtin tool and give it an inspector.”
  • “Why does my builtin tool's render never show in chat? Check the registry wiring.”
  • “Scaffold a new builtin tool package with a manifest, runtime and executor.”

Requirements

  • A checkout of the LobeHub repository

Workflow steps

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

  1. lobe- identifier is permanent. It's stored in message history. Renames need legacy aliases kept alongside the new name (see the // Legacy…
  2. ApiName is an as const object, not a TS enum. It doubles as the runtime list BaseExecutor iterates over.
  3. Three result fields, three audiences
  4. Split execution from frontend wiring.
  5. UI defaults to "do nothing". Inspector is required (the header strip). Render/Placeholder/Streaming/Intervention/Portal are added only…
  6. Style with createStaticStyles + cssVar.* (zero-runtime). Fall back to createStyles + token only when you genuinely need runtime values…
  7. i18n keys live in packages/locales/src/default/plugin.ts. Inspector titles must come from t('builtins..apiName.') so something renders…
  8. A failed long-running call should be continuable, not just inspectable. Example: when callSubAgent stops halfway, the user says "keep…

What it can do on your machine

Read from SKILL.md and the folder at commit 6aaeeee. 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:

    • bunx
    • bun

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

  • Network

    No URLs in SKILL.md. Its commands use bunx, 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

LobeHub Builtin Tool Authoring loads about 2.4k tokens when it runs, and up to ~22k if it reads all its reference files. Until then it costs about 33 tokens; SKILL.md has 728 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
~2.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~22k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 728 words (~2,375 tokens).

“A builtin tool is a package the agent runtime can call. It ships five faces:”

— opening of SKILL.md by lobehub, Custom licence
name
builtin-tool

Read the full SKILL.md on GitHub

Files

SKILL.md and 13 other files (references) in .agents/skills/builtin-tool of lobehub/lobehub.

  • SKILL.md
  • references/architecture.md
  • references/tool-design.md
  • references/ui/README.md
  • references/ui/composition.md
  • references/ui/diagnostics.md
  • references/ui/inspector.md
  • references/ui/intervention.md
  • references/ui/placeholder.md
  • references/ui/portal.md
  • references/ui/principles.md
  • references/ui/render.md
  • references/ui/shared-rules.md
  • references/ui/streaming.md

Open the folder on GitHubat commit 6aaeeee

Compare with similar skills

LobeHub Builtin Tool Authoring 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.

LobeHub Builtin Tool Authoring compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
LobeHub Builtin Tool Authoring this skilllobehub/lobehub83k—~2.4kAutomated safety check: PassCustom licence
Adk Sample Creatorgoogle/adk-python22k—~1.3kAutomated safety check: PassApache-2.0
E2b Sandboxagent-sandbox/agent-sandbox218—~2.6kAutomated safety check: PassApache-2.0
Release Noteslangchain-ai/langchain-azure147—~1.2kAutomated safety check: PassMIT
GitHubswarmclawai/swarmclaw688—~820Automated safety check: PassMIT
Create Agent Templateharness/harness-skills115—~2.2kAutomated safety check: PassApache-2.0

Similar skills

  • Adk Sample Creator

    google/adk-python

    Official

    Creates a new sample agent in the ADK Python repository — the sample directory, its agent.py, and its README.md — following the conventions the existing samples already use.

    22k GitHub stars~1.3k tokensUpdated today
    DevelopmentAuto-check passed

  • E2b Sandbox

    agent-sandbox/agent-sandbox

    Create, manage, and use E2B sandboxes — run commands, manage files, use git, persist state, and configure networking.

    218 GitHub stars~2.6k tokensUpdated 18 days ago
    DevelopmentAuto-check passed

  • Release Notes

    langchain-ai/langchain-azure

    Official

    Skill for compiling and writing release notes for langchain-azure packages.

    147 GitHub stars~1.2k tokensUpdated today
    DevelopmentAuto-check passed

  • GitHub

    swarmclawai/swarmclaw

    GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries.

    688 GitHub stars~820 tokensUpdated 3 mo ago
    DevelopmentAuto-check passed

  • Create Agent Template

    harness/harness-skills

    Generate Harness Agent Template files for AI-powered automation agents.

    115 GitHub stars~2.2k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Claude Code Templates

    aiskillstore/marketplace

    Boilerplate templates for Claude Code extensions. An agent skill from aiskillstore/marketplace.

    430 GitHub starsUsed in 1 repo~764 tokens
    DevelopmentAuto-check passed

More from lobehub/lobehub

All 50 skills in this repo

  • LobeHub Interactive Prototype

    lobehub/lobehub

    Builds single-file interactive HTML prototypes rendered with the real LobeHub UI components and written as production-style React, so they can later be split into files.

    83k GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Acceptance Evidence for Deliveries

    lobehub/lobehub

    Verifies a delivery end to end by driving the real product on a CLI, web, desktop or iOS Simulator surface, capturing evidence and publishing a round with the lh CLI.

    83k GitHub stars~9.7k tokensUpdated today
    Auto-check passed

  • Git Worktree Cleanup

    lobehub/lobehub

    Audits stale Git worktrees and branches with a bundled script, classifies each one, and deletes only after you approve the exact candidates.

    83k GitHub stars~2.8k tokensUpdated today
    Auto-check passed

  • LobeHub Alint Rule Set Maintenance

    lobehub/lobehub

    Maintains LobeHub's model-backed alint rule set: writing rules, removing false positives against real code, deciding warn versus error and tracking token cost.

    83k GitHub stars~1.9k tokensUpdated today
    Auto-check passed

  • LobeHub Data Fetching Layers

    lobehub/lobehub

    Explains how LobeHub client code fetches data through services, SWR store hooks and cache keys, and when to avoid useEffect fetching or duplicated state.

    83k GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Product Full-Text Search

    lobehub/lobehub

    Guides work on LobeHub's own product search: the shared search repository, provider choice, Elasticsearch mappings, change syncing and reindexing.

    83k GitHub stars~4.1k tokensUpdated today
    Auto-check passed

Categories

Questions about LobeHub Builtin Tool Authoring

What does LobeHub Builtin Tool Authoring do?

Guides building LobeHub builtin agent tools, from the manifest and execution runtime to executors, chat UI renders and registry wiring. A builtin tool is a package the agent runtime can call, and the skill describes it as five faces: the manifest, types and system role the model sees, an execution runtime usable on server or desktop, a frontend executor that wraps stores and services, the client UI for the chat, and the registry wiring that lets the framework find it.

When should I use LobeHub Builtin Tool Authoring?

LobeHub Builtin Tool Authoring fits situations like: creating a new builtin tool package in the LobeHub repository; adding an API method to an existing builtin tool; building or restyling a tool's inspector, render or placeholder; debugging a tool-not-found or stuck-placeholder error.

How do I install LobeHub Builtin Tool Authoring in Claude Code?

Run `npx skills add lobehub/lobehub --skill builtin-tool -a claude-code`. Or copy the skill folder (.agents/skills/builtin-tool in lobehub/lobehub) into .claude/skills/builtin-tool in your project. Claude Code loads it when a task matches its description.

How do I install LobeHub Builtin Tool Authoring in Codex?

Run `npx skills add lobehub/lobehub --skill builtin-tool -a codex`. Or copy the skill folder (.agents/skills/builtin-tool in lobehub/lobehub) into .agents/skills/builtin-tool in your project. Codex loads it when a task matches its description.

Can I use LobeHub Builtin Tool Authoring 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 lobehub/lobehub --skill builtin-tool -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/builtin-tool, .gemini/skills/builtin-tool, .github/skills/builtin-tool and .opencode/skills/builtin-tool in your project.

What does LobeHub Builtin Tool Authoring need to run?

Going by SKILL.md and its folder, LobeHub Builtin Tool Authoring needs the command-line tools its instructions call (bunx and bun). Our summary lists: A checkout of the LobeHub repository.

Does LobeHub Builtin Tool Authoring 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 LobeHub Builtin Tool Authoring 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 LobeHub Builtin Tool Authoring use?

LobeHub Builtin Tool Authoring 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 LobeHub Builtin Tool Authoring use?

About 2.4k tokens (SKILL.md is roughly 9.5k 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 20k tokens, read only when the agent opens those files.

What are the alternatives to LobeHub Builtin Tool Authoring?

Skills that share tags, products or a category with LobeHub Builtin Tool Authoring: Adk Sample Creator (google/adk-python, 22k stars), E2b Sandbox (agent-sandbox/agent-sandbox, 218 stars), Release Notes (langchain-ai/langchain-azure, 147 stars) and GitHub (swarmclawai/swarmclaw, 688 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains LobeHub Builtin Tool Authoring?

lobehub (a GitHub organization) maintains it in lobehub/lobehub, which has 83,044 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on October 8, 2026.

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