blocks-network
A technical reference for modifying, deploying, and troubleshooting existing Blocks Network agents.
Install
mkdir -p .claude/skills/blocks-network && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18062" && unzip -o skill.zip -d .claude/skills/blocks-network && rm skill.zipInstalls to .claude/skills/blocks-network
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Non-linear reference for managing Blocks Network agents — features, configuration, CLI, IO schemas, streaming, consumer SDK, publishing, invites, troubleshooting. Use when working with an existing agent, modifying, deploying, calling agents from a script, or looking up a Blocks feature.Key capabilities
- →Manage Blocks Network agents after initial build
- →Configure agent settings and features
- →Use the Blocks CLI for agent operations
- →Handle streaming for agents
- →Utilize the consumer SDK for agents
- →Manage agent invites and publishing
How it works
This skill provides a non-linear reference for managing Blocks Network agents, covering configuration, CLI usage, streaming, and publishing, for agents that already exist.
Inputs & outputs
When to use blocks-network
- →Deploy an agent
- →Update agent configuration
- →Troubleshoot agent execution
- →Call an agent from a script
About this skill
Blocks Network Agent Skills
This directory is the skills/ component of the portable Agent Plugin declared
by ../plugin.json. Each installable skill is an immediate
child directory containing a SKILL.md whose frontmatter name matches the
directory name.
skills/
├── blocks-getstarted/
│ ├── LICENSE
│ └── SKILL.md
├── blocks-network/
│ ├── LICENSE
│ ├── SKILL.md
│ └── references/
│ ├── agent-card.schema.json
│ └── …
├── evals/
└── tile.json
blocks-getstartedowns the linear first-agent workflow.blocks-networkowns the non-linear reference workflow and the detailed reference bundle.- Each skill must remain independently installable. Do not link to files in a
sibling skill with
../<skill>/.... Cross-skill handoffs name the target skill, while shared detailed references continue to use the stablehttps://config.blocks.ai/URLs until an independent bundling mechanism is designed. blocks-network/references/agent-card.schema.jsonis the distributable copy of the canonical../schemas/agent-card.schema.json. Keep it byte-identical so installations made bynpx skillsdo not depend on files outsideskills/.- Each skill includes a distributable copy of the repository
LICENSEbecausenpx skillsinstalls skill directories independently. evals/contains development-time evaluation fixtures and is not discovered as a skill because it has noSKILL.md.tile.jsonindexes the same canonical skill files for the existing tile distribution.
Do not add flat compatibility copies such as skills/SKILL.md or
skills/GETSTARTED.md. Distribution pipelines that preserve legacy hosted URLs
should map those URLs to the canonical files above rather than create a second
hand-maintained source. Do not replace the hosted URLs inside a skill with
cross-skill relative paths until independently installable reference bundles
have been designed.
Validate the plugin/skill boundaries and both skills from the blocks-sdk
repository root:
npm run check:agent-distribution
npx --yes [email protected] validate skills/blocks-network
npx --yes [email protected] validate skills/blocks-getstarted
npx --yes skills@latest add . --list
When not to use it
- →When building a brand-new agent from scratch
- →When needing to use Python for agent development without explicit user request
Limitations
- →Not for building brand-new agents from nothing.
- →Default language is Node (TypeScript), Python only on explicit request.
How it compares
This skill offers specialized guidance for post-build agent management within the Blocks Network, unlike general agent development instructions.
Compared to similar skills
blocks-network side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| blocks-network (this skill) | 0 | 2mo | Caution | Intermediate |
| create-mcp-server | 0 | 6mo | No flags | Intermediate |
| mcp-builder | 136 | 4mo | Review | Advanced |
| playwright-browser-automation | 29 | 8mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
create-mcp-server
appliedcognetics
Scaffold a local MCP server with synthetic data for agentic system development. Use when creating a new data source, building tool endpoints, or generating test data for agents to consume.
mcp-builder
anthropics
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
playwright-browser-automation
lackeyjb
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.
codex-skill
feiskyer
Use when user asks to leverage codex, gpt-5, or gpt-5.1 to implement something (usually implement a plan or feature designed by Claude). Provides non-interactive automation mode for hands-off task execution without approval prompts.
bullmq-specialist
davila7
BullMQ expert for Redis-backed job queues, background processing, and reliable async execution in Node.js/TypeScript applications. Use when: bullmq, bull queue, redis queue, background job, job queue.
run-nx-generator
nrwl
Run Nx generators with prioritization for workspace-plugin generators. Use this when generating code, scaffolding new features, or automating repetitive tasks in the monorepo.