Blocks Getstarted

What it does

Example prompts

• “/blocks-getstarted”

Requirements

• Python 3
• Node.js
• A credential in BLOCKS_API_KEY

Workflow steps

11 steps, taken from the step headings in SKILL.md.

1. 1Confirm This Is a Build Request
2. 2Ask Name
3. 3Confirm Description
4. 4Install & Authenticate CLI
5. 5Scaffold
6. 6Implement Handler and IO Schema
7. 7Register (or Publish)
8. 8Validate
9. 9Start
10. 10Test
11. 11Dashboard

What it can do on your machine

Read from SKILL.md and the folder at commit 2b0e03b. 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
  • pip
  • npx
  • python
  • vercel
  • netlify

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

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • config.blocks.ai
  • blocks.acme.com
  • acme.blocks.ai
  • staging.blocks.ai

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • BLOCKS_API_KEY

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

Context cost

Blocks Getstarted loads about 5.4k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 2,898 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~56

When it runs · the whole SKILL.md, loaded when a task matches

~5.4k

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

• NoteMentions a .env fileSKILL.md:143

  writes `BLOCKS_API_KEY` to the project `.env` (read by `blocks run`

• NoteMentions a .env fileSKILL.md:152

  project `.env` pinning a deployment the user has a profile for. In those cases

• NoteMentions a .env fileSKILL.md:156

  `Write credentials to project .env? (Y/n):`. With no `--no-input`, the CLI

• NoteMentions a .env fileSKILL.md:159

  write `.env`, which is rarely what an agent flow wants. Under `--no-input`

• NoteMentions a .env fileSKILL.md:179

  - `--write-env` opts in to the `.env` write (recommended);

• NoteMentions a .env fileSKILL.md:181

  `.env`).

• NoteMentions a .env fileSKILL.md:211

  A project `.env` configures the **agent**, and can also retarget the CLI, but

• NoteMentions a .env fileSKILL.md:217

  in `.env` as usual, but export anything meant for the CLI itself (a proxy, a

• NoteMentions a .env fileSKILL.md:224

  write-env` lands in the correct project `.env`. Without it, the key

• NoteMentions a .env fileSKILL.md:225

  lands in the parent directory's `.env`, which `blocks run` inside the

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 (Proprietary) doesn't allow us to republish the file, so here is its outline and opening line. It has 2,898 words (~5,443 tokens).

name

blocks-getstarted

metadata.author

blocks-network

metadata.version

0.1.0

metadata.domain

real-time

metadata.triggers

build, create, new agent, scaffold, quickstart, getting started, first agent, help me build an agent, make a new agent, build an agent, create a new agent…

metadata.role

specialist

metadata.scope

implementation

metadata.output-format

code

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in skills/blocks-getstarted of blocksnetwork/blocks-sdk.

• SKILL.md
• LICENSE

Open the folder on GitHubat commit 2b0e03b