Skip to content

Use fastaiagent with a coding assistant

A coding assistant — Claude Code, GitHub Copilot, Cursor, Google Antigravity and the rest — was not trained on this SDK's current API. Left alone it guesses: it calls connect() without a target, imports the LangChain adapter that was removed in 1.96.0, or reaches for discover_tools(). The code looks right and fails when you run it.

The SDK ships two Agent Skills. A skill is a folder with a SKILL.md that the assistant reads when the work calls for it.

  • fastaiagent-sdk is read when the assistant is about to write fastaiagent code. It holds the ten mistakes assistants make most, a reference per area (agents, tools, teams, guardrails, evals, platform, testing, what changed), a script that checks what the assistant wrote, and a short recipe for starting a project: a layout where plain pytest works and an entry point that connects and always ends with disconnect().

It also asks the assistant to do more than write code that passes its offline tests. Those tests use scripted models, so they cannot see a wrong model id, a missing key or a dead server. When your model key is in the environment the assistant should run the real entry point once and say what it ran and what it did not. It should keep an address you give it in FASTAIAGENT_TARGET instead of in code, test an MCP tool against a real local server instead of a fake, and not add tools or helpers you did not ask for.

For an app connected to a platform, the skill says what the platform supplies (guardrail rules, prompts, eval datasets, judges, knowledge-base search) and what it receives (traces, eval verdicts). It also gives a checklist the assistant runs before calling the app done: that the plane's guardrail rules reached the agent, that one of them actually blocks, that the trace came back from the platform, and that a gated eval run was sent. - fastaiagent-studio is read when you ask for an agent to be built through Agent Studio. It teaches the fastaiagent studio commands and how to write a spec (see The Studio skill below). It needs a platform.

Install it

pip install fastaiagent
cd your-project
fastaiagent skills install

That copies both skills into the two folders assistants read:

Folder Read by
.claude/skills/ Claude Code. GitHub Copilot and Cursor read it too.
.agents/skills/ GitHub Copilot, Cursor, Google Antigravity, Codex, Gemini CLI and others

The command prints what it did as JSON and exits non-zero if it could not do what you asked. It also offers to add a three-line pointer to AGENTS.md (created if missing, appended to otherwise, never rewritten); it asks only when it has a terminal. Pass --agents-md or --no-agents-md to decide up front, and --claude-md to add the pointer to CLAUDE.md too — it never edits that file otherwise.

Command Does
fastaiagent skills list The packaged skills, and any installed copies that are out of date
fastaiagent skills install Install into the project. --tool claude\|agents\|all, --user for every project, --force to replace
fastaiagent skills path The folder the skills ship in

Each installed copy is stamped with the SDK version that installed it. After you upgrade the SDK, skills list says which copies are stale and skills install --force refreshes them.

Install it without the SDK

The same skills are in a public repository, fastaifoundry/fastaiagent-skills:

/plugin marketplace add fastaifoundry/fastaiagent-skills
/plugin install fastaiagent@fastaiagent-skills
npx skills add fastaifoundry/fastaiagent-skills
gh skill install fastaifoundry/fastaiagent-skills fastaiagent-sdk --agent github-copilot

Copy a folder from skills/ (fastaiagent-sdk/, fastaiagent-studio/) into .claude/skills/ or .agents/skills/ in your project, or into ~/.claude/skills/ or ~/.agents/skills/ for every project.

The repository is generated from the SDK at each release; it does not take pull requests. The gh skill install line above names one skill; use fastaiagent-studio for the other.

What the assistant does with it

  1. You ask for fastaiagent code.
  2. The assistant loads SKILL.md and reads the reference for the area — for example references/tools.md before it writes a tool.
  3. It writes the code and an offline test using fastaiagent.testing.TestModel.
  4. It runs the checker from the skill's folder:
python .agents/skills/fastaiagent-sdk/scripts/check_imports.py agent.py tests/

The checker resolves every fastaiagent import and every fa.something attribute against the installed SDK, and names the replacement for anything that was removed:

agent.py:3: error: cannot import discover_tools from fastaiagent.tool (removed. Use MCPTool.from_server(...) (needs the [mcp] extra).)
agent.py:7: warn: connect() needs target=... (or FASTAIAGENT_TARGET in the environment); there is no default since 1.100.0.
checked 1 file(s): 1 error(s), 1 warning(s)

It exits 0 when clean, 1 on an error (or on a warning with --strict), and 2 if the SDK is not importable from that Python. You can run it yourself, or in CI.

The Studio skill

Agent Studio can build an agent for you from a spec. With the fastaiagent-studio skill installed, ask your assistant for an agent ("build me an order-status agent with Studio, here is the orders data") and it follows this loop:

  1. fastaiagent studio context — which LLM endpoints and knowledge bases the project has. With no endpoint it stops and tells you to add one in the console.
  2. It reads what you want, and any requirements document or scan itself, and says what it could not read.
  3. It lays the design out for you — the shape, each worker, the tools, the guardrails, the eval cases — and waits for a yes. The API has no plan step, so this is where you approve; nothing is pushed before it.
  4. studio new with your sample data, then it writes the spec and runs studio spec validate. Every warning is read out to you.
  5. studio spec push --wait, then studio show, studio try and studio eval.
  6. To change something it reads the spec back, edits it and pushes a new version; the old one is kept.
  7. studio export into your repository, then it runs the exported tests and tells you how to run the agent with your own key.

It never prints or stores a key, reports a refusal and its reason instead of retrying it, tries a team one worker at a time, and stops and asks if someone changed the draft in the console. It needs a platform at 0.20.0 or later and an API key with the Agent Studio permissions.

This skill has not been tried by hand in GitHub Copilot, Cursor or Google Antigravity yet, so this page does not claim it works there: it is in the folder each of them reads, and the checklist for trying it is in the SDK repository.

What it does not do

  • It does not make an assistant reliable on its own. It removes one cause of wrong code — a guessed API — and gives you a check for it. Read what the assistant writes.
  • It does not call the model, the platform or the network. The checker runs none of your code.