Official agent skill

Bootstrapping Agent

by airbytehq in airbytehq/airbyte-agent-sdk

Wires up an Airbyte connector for use in a PydanticAI, Claude SDK, or other agent.

OfficialCustom licenceAuto-check: notesAI & LLM Engineering

Install Bootstrapping Agent

skills CLI
$ npx skills add airbytehq/airbyte-agent-sdk --skill bootstrapping-agent -a claude-code

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

GitHub CLI
$ gh skill install airbytehq/airbyte-agent-sdk bootstrapping-agent --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/airbytehq/airbyte-agent-sdk.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/bootstrapping-agent .claude/skills/bootstrapping-agent && 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
bootstrapping-agent
GitHub stars
135
Token cost
~1.7k tokens
SKILL.md length
420 words
Files
2
Skills in repo
4
Repo updated
First seen
Licence
Custom licence

At a glance

Wires up an Airbyte connector for use in a PydanticAI, Claude SDK, or other agent.

  • Adding a connector to an agent
  • SKILL.md covers Install the SDK, Core Pattern (PydanticAI), Custom Tool Bodies (agent_tool) and Unsupported Frameworks, plus 6 more sections
  • Calls uv; needs AIRBYTE_CLIENT_SECRET
  • Setting up a new agent with a connector

What it does

Bootstrapping Agent is an agent skill from airbytehq/airbyte-agent-sdk, published by the product's own GitHub organization. Wires up an Airbyte connector for use in a PydanticAI, Claude SDK, or other agent. Generates auth config, connector initialization, prebuilt connector tools, or agenttool-decorated custom tool functions. Use when adding a connector to an agent or setting up a new agent with a connector.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in AI & LLM Engineering, covering Building AI agents. It works with Airbyte, Anthropic API, Pydantic AI and LangChain. The repository describes itself as: 🐙 Drop-in tools that give AI agents reliable, permission-aware access to external systems.

When your agent uses it

  • Adding a connector to an agent
  • Setting up a new agent with a connector

Example prompts

  • “Use the bootstrapping-agent skill to wire up an Airbyte connector for use in a PydanticAI, Claude SDK, or other agent”
  • “/bootstrapping-agent”

Requirements

  • Python 3
  • A credential in AIRBYTE_CLIENT_SECRET

What it can do on your machine

Read from SKILL.md and the folder at commit 33a1502. 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:

    • uv

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

  • Network

    No URLs in SKILL.md. Its commands use uv, 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:

    • AIRBYTE_CLIENT_SECRET

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

Context cost

Bootstrapping Agent loads about 1.7k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 420 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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:139
    The developer needs these in their `.env`:

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 420 words (~1,654 tokens).

“The single airbyte-agent-sdk package ships every typed connector. Import them from airbyte_agent_sdk.connectors.{slug}.”

— opening of SKILL.md by airbytehq, Custom licence
name
bootstrapping-agent

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in .codex/skills/bootstrapping-agent of airbytehq/airbyte-agent-sdk.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 33a1502

Compare with similar skills

Bootstrapping Agent 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.

Bootstrapping Agent compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bootstrapping Agent this skillairbytehq/airbyte-agent-sdk135—~1.7kAutomated safety check: NotesCustom licence
Agent Squad Python Guide2FastLabs/agent-squad7.8k—~4.7kAutomated safety check: PassApache-2.0
Agent Prompt Engineeringagentailor/fullstack-langgraph-nextjs-agent132—~3.6kAutomated safety check: PassMIT
Agent Inspectrajudandigam/agent-inspect165—~424Automated safety check: PassMIT
Tool Designagentailor/fullstack-langgraph-nextjs-agent132—~3.2kAutomated safety check: PassMIT
Agent Eval Casesagentailor/fullstack-langgraph-nextjs-agent132—~5.3kAutomated safety check: PassMIT

Similar skills

  • Agent Squad Python Guide

    2FastLabs/agent-squad

    Map of the agent-squad Python framework for async multi-agent orchestration: which agent, classifier, storage and tool provider to pick, and the pitfalls to avoid.

    7.8k GitHub stars~4.7k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Agent Prompt Engineering

    agentailor/fullstack-langgraph-nextjs-agent

    Comprehensive guide for designing, refining, and auditing system prompts for autonomous AI agents based on Anthropic's production practices.

    132 GitHub stars~3.6k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • Agent Inspect

    rajudandigam/agent-inspect

    Local evidence debugger and trajectory-test toolkit for TypeScript AI agents.

    165 GitHub stars~424 tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Tool Design

    agentailor/fullstack-langgraph-nextjs-agent

    Design and verify tools that AI agents can actually use — for any framework or language (MCP servers, LangChain/LangGraph, function-calling, raw JSON schema; TypeScript, Python, or otherwise).

    132 GitHub stars~3.2k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • Agent Eval Cases

    agentailor/fullstack-langgraph-nextjs-agent

    Decide which AI agent behaviors are worth an eval case, then write those cases — harness-, framework-, and language-agnostic.

    132 GitHub stars~5.3k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • Solana Agent Kit

    internet-court/internet-court-skill

    Walks through building AI agents that run Solana operations such as token deploys, NFT minting, swaps and staking with SendAI's toolkit, in chat or fully autonomous mode.

    6.4k GitHub starsUsed in 3 repos~3.8k tokens
    AI & LLM EngineeringAuto-check: notes

More from airbytehq/airbyte-agent-sdk

  • Building Multi Connector Agent

    airbytehq/airbyte-agent-sdk

    Official

    Builds a complete agent with multiple Airbyte connectors using PydanticAI or Claude SDK.

    135 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check: notes
  • Discovering Connectors

    airbytehq/airbyte-agent-sdk

    Official

    Discovers available Airbyte connectors, explores their entities/actions/schemas, and checks auth requirements.

    135 GitHub stars~582 tokensUpdated yesterday
    Auto-check passed
  • Airbyte SDK Reference

    airbytehq/airbyte-agent-sdk

    Official

    Reference documentation for the Airbyte per-connector typed SDK packages

    135 GitHub stars~202 tokensUpdated yesterday
    Auto-check passed

Questions about Bootstrapping Agent

What does Bootstrapping Agent do?

Wires up an Airbyte connector for use in a PydanticAI, Claude SDK, or other agent. Bootstrapping Agent is an agent skill from airbytehq/airbyte-agent-sdk, published by the product's own GitHub organization. Wires up an Airbyte connector for use in a PydanticAI, Claude SDK, or other agent.

When should I use Bootstrapping Agent?

Bootstrapping Agent fits situations like: adding a connector to an agent; setting up a new agent with a connector.

How do I install Bootstrapping Agent in Claude Code?

Run `npx skills add airbytehq/airbyte-agent-sdk --skill bootstrapping-agent -a claude-code`. Or copy the skill folder (.codex/skills/bootstrapping-agent in airbytehq/airbyte-agent-sdk) into .claude/skills/bootstrapping-agent in your project. Claude Code loads it when a task matches its description.

How do I install Bootstrapping Agent in Codex?

Run `npx skills add airbytehq/airbyte-agent-sdk --skill bootstrapping-agent -a codex`. Or copy the skill folder (.codex/skills/bootstrapping-agent in airbytehq/airbyte-agent-sdk) into .agents/skills/bootstrapping-agent in your project. Codex loads it when a task matches its description.

Can I use Bootstrapping Agent 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 airbytehq/airbyte-agent-sdk --skill bootstrapping-agent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bootstrapping-agent, .gemini/skills/bootstrapping-agent, .github/skills/bootstrapping-agent and .opencode/skills/bootstrapping-agent in your project.

What does Bootstrapping Agent need to run?

Going by SKILL.md and its folder, Bootstrapping Agent needs the command-line tools its instructions call (uv) and credentials named AIRBYTE_CLIENT_SECRET. Our summary lists: Python 3; A credential in AIRBYTE_CLIENT_SECRET.

Does Bootstrapping Agent access the network?

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

Is Bootstrapping Agent 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 Bootstrapping Agent use?

Bootstrapping Agent 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 Bootstrapping Agent use?

About 1.7k tokens (SKILL.md is roughly 6.6k 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 Bootstrapping Agent?

Skills that share tags, products or a category with Bootstrapping Agent: Agent Squad Python Guide (2FastLabs/agent-squad, 7.8k stars), Agent Prompt Engineering (agentailor/fullstack-langgraph-nextjs-agent, 132 stars), Agent Inspect (rajudandigam/agent-inspect, 165 stars) and Tool Design (agentailor/fullstack-langgraph-nextjs-agent, 132 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bootstrapping Agent?

airbytehq (a GitHub organization, an official publisher) maintains it in airbytehq/airbyte-agent-sdk, which has 135 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 6, 2026.

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