AI SDK
vercel-labs/ai-facts
Answer questions about the AI SDK and help build AI-powered features.
Build an AI-agent application end-to-end — from an empty repo or an existing codebase.
Install Build Agent
$ npx skills add chmonitor/chmonitor --skill build-agent -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install chmonitor/chmonitor build-agent --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/chmonitor/chmonitor.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/build-agent .claude/skills/build-agent && rm -rf skills-srcUse ~/.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/
Install the "build-agent" agent skill from https://github.com/chmonitor/chmonitor/tree/main/.agents/skills/build-agent into .claude/skills/build-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "build-agent", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/chmonitor/chmonitor/tree/main/.agents/skills/build-agentType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add chmonitor/chmonitor --skill build-agent -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install chmonitor/chmonitor build-agent --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chmonitor/chmonitor.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/build-agent .agents/skills/build-agent && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "build-agent" agent skill from https://github.com/chmonitor/chmonitor/tree/main/.agents/skills/build-agent into .agents/skills/build-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "build-agent", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add chmonitor/chmonitor --skill build-agent -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install chmonitor/chmonitor build-agent --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chmonitor/chmonitor.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/build-agent .cursor/skills/build-agent && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "build-agent" agent skill from https://github.com/chmonitor/chmonitor/tree/main/.agents/skills/build-agent into .cursor/skills/build-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "build-agent", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/chmonitor/chmonitor.git --path .agents/skills/build-agent--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add chmonitor/chmonitor --skill build-agent -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install chmonitor/chmonitor build-agent --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chmonitor/chmonitor.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/build-agent .gemini/skills/build-agent && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "build-agent" agent skill from https://github.com/chmonitor/chmonitor/tree/main/.agents/skills/build-agent into .gemini/skills/build-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "build-agent", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install chmonitor/chmonitor build-agentInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add chmonitor/chmonitor --skill build-agent -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/chmonitor/chmonitor.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/build-agent .github/skills/build-agent && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "build-agent" agent skill from https://github.com/chmonitor/chmonitor/tree/main/.agents/skills/build-agent into .github/skills/build-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "build-agent", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add chmonitor/chmonitor --skill build-agent -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install chmonitor/chmonitor build-agent --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chmonitor/chmonitor.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/build-agent .opencode/skills/build-agent && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "build-agent" agent skill from https://github.com/chmonitor/chmonitor/tree/main/.agents/skills/build-agent into .opencode/skills/build-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "build-agent", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
build-agent- GitHub stars
- 299
- Token cost
- ~1.8k tokens
- SKILL.md length
- 789 words
- Files
- 19 (incl. references)
- Skills in repo
- 53
- Repo updated
- First seen
- Licence
- GPL-3.0
At a glance
Build an AI-agent application end-to-end — from an empty repo or an existing codebase.
- Works in 5 steps: Determine the entry mode → Interview deeply (when in Interview mode) → Choose the framework → …
- The user wants to build an agent
- SKILL.md covers Operating principle: verify…, Step 1 — Determine the entry…, Step 2 — Interview deeply… and Step 3 — Choose the framework, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Build Agent is an agent skill from chmonitor/chmonitor. Build an AI-agent application end-to-end — from an empty repo or an existing codebase. Use when the user wants to "build an agent", "scaffold an agent app", "add an agent API", "build an agent UI/chat", "pick an agent framework", or set up tool calling, tracing, or an AI gateway. Interviews the user when requirements are unclear; detects the stack when a project already exists. Knows LangGraph, DeepAgents, Vercel AI SDK, Cloudflare Agents SDK, TanStack AI, Google ADK, and the Claude Agent SDK. Always verifies…
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 22 other files, including reference files (for example `references/README.md`, `references/concepts/ai-gateways.md` and `references/concepts/skills.md`).
It sits in AI & LLM Engineering, covering Building AI agents, AI search optimization and Structured output and tool calling. It works with Claude Agent SDK, LangGraph, Vercel AI SDK and Cloudflare. The repository describes itself as: Open-source operational advisor for ClickHouse — real-time monitoring plus AI-driven index/partition/materialized-view recommendations. The licence is GPL-3.0.
When your agent uses it
- The user wants to build an agent
- Scaffold an agent app
- Add an agent API
- Build an agent UI/chat
Example prompts
- “build an agent”
- “scaffold an agent app”
- “add an agent API”
- “/build-agent”
Requirements
- Python 3
- Docker
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit fc39ef0. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Build Agent loads about 1.8k tokens when it runs, and up to ~7.3k if it reads all its reference files. Until then it costs about 152 tokens; SKILL.md has 789 words of instructions outside code blocks.
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
The full file from chmonitor/chmonitor at commit fc39ef0, republished under its GPL-3.0 licence (© chmonitor). 789 words, ~1,764 tokens.
Download SKILL.mdSave it as
.claude/skills/build-agent/SKILL.md (or your agent's skills folder). This skill also uses 18 other files; get the full folder from GitHub.- name
- build-agent
- description
- Build an AI-agent application end-to-end — from an empty repo or an existing codebase. Use when the user wants to "build an agent", "scaffold an agent app", "add an agent API", "build an agent UI/chat", "pick an agent framework", or set up tool calling, tracing, or an AI gateway. Interviews the user when requirements are unclear; detects the stack when a project already exists. Knows LangGraph, DeepAgents, Vercel AI SDK, Cloudflare Agents SDK, TanStack AI, Google ADK, and the Claude Agent SDK. Always verifies against live official docs (Context7 / llms.txt / WebFetch) before writing code.
build-agent
Scaffold and grow AI-agent applications. This skill is stack-agnostic: it helps you choose a framework, then builds the agent loop, tools, API surface, UI, observability, and deployment to match the user's real requirements.
Operating principle: verify before you build
Agent frameworks move fast. Never rely on memory for framework APIs. Before writing framework code, pull live docs in this order:
- Context7 MCP (if available) —
resolve-library-id→query-docs. - Official
llms.txt/llms-full.txt/.mdvia WebFetch — seereferences/frameworks/*for the canonical URLs. - The installed package itself — read
node_modules/<pkg>or the Python package source; the user's pinned version is the source of truth.
The references/ tree here is a thin glossary + link index, deliberately
kept small so it does not go stale. It tells you what exists and where the real
docs are — not the full API. Treat any code snippet in references as
illustrative, then confirm against live docs.
If the host agent already has Context7, WebSearch, zread, or a relevant skill — use it. Don't reinvent retrieval.
Step 1 — Determine the entry mode
Decide which of these you're in, then jump to the matching workflow:
| Situation | Mode | Workflow |
|---|---|---|
| Empty/near-empty repo, or user says "from scratch" | Interview | workflows/from-scratch.md |
| Existing project with code | Detect | workflows/from-existing.md |
| User explicitly asks to (re)interview | Interview | workflows/from-scratch.md |
Quick check: list the repo, look for package.json / pyproject.toml /
wrangler.jsonc / go.mod. Nothing meaningful → Interview. Something there →
Detect the techstack first, confirm it with the user, then only ask what the
code can't answer.
Step 2 — Interview deeply (when in Interview mode)
Use the host's ask-user tool. Don't ask one shallow question — gather as much
as possible across these dimensions. Follow workflows/from-scratch.md for the
full question bank. Cover at minimum:
- Purpose / use case — what should the agent do? (RAG assistant, coding agent, workflow automation, customer support, research, multi-agent system…)
- Language — TypeScript / Python / Go / other.
- Framework — see the chooser below; recommend, don't impose.
- Architecture — single agent, supervisor/multi-agent, graph/state machine, human-in-the-loop, durable/long-running, streaming vs batch.
- Model + provider — Claude / GPT / Gemini / open models; direct or via a gateway (OpenRouter / AnyRouter / AI gateway).
- Tools / integrations — what external actions (search, code exec, DB, MCP servers, APIs) the agent needs.
- UI/UX — chat UI, dashboard, headless API only, CLI, embedded widget.
- Persistence / memory — conversation state, vector store, checkpointing.
- Observability — tracing, evals, cost/latency tracking (see
references/concepts/tracking-observability.md). - Deploy target — Docker, VM, k3s/Kubernetes, a cloud (AWS/GCP/Azure), Cloudflare Workers, Vercel, serverless.
Restate the assembled requirements back to the user before scaffolding.
Step 3 — Choose the framework
Match the dominant requirement to a framework. Full notes in
references/frameworks/.
| If the user wants… | Lean toward | Lang |
|---|---|---|
| Stateful graphs, supervisor/multi-agent, human-in-loop, checkpointing | LangGraph | Py / TS |
| Opinionated "deep" planning agent (subagents, file tools, todo) on top of LangGraph | DeepAgents | Py / TS |
| Web app with streaming chat, tool calls, generative UI; Next.js/React | Vercel AI SDK | TS |
| Edge-native, durable, stateful agents that scale to zero | Cloudflare Agents SDK (Durable Objects) | TS |
| Provider-agnostic, type-safe streaming/tools/structured output in any TS app | TanStack AI | TS |
| Google-ecosystem, Gemini-first, code-first multi-agent with eval tooling | Google ADK | Py / Java |
| Build on the same harness Claude Code uses; subagents, MCP, hooks, permissions | Claude Agent SDK | Py / TS |
Mixed needs are common (e.g. LangGraph backend + AI SDK frontend, or Claude Agent SDK behind a Cloudflare Worker). Compose; don't force one box.
Show full SKILL.md (254 more words)Show less
Step 4 — Scaffold
Build the minimum that runs, then layer on. Match the chosen framework's conventions exactly — pull its quickstart from live docs first.
Typical layers (build only what the requirements call for):
- Agent core — the loop / graph / state. Confirm the current API shape.
- Tools — define and wire tool calls. See
references/concepts/tool-calling.md. - Model access — direct provider or gateway. See
references/concepts/ai-gateways.mdfor OpenRouter / AnyRouter / AI gateway. - API surface — HTTP/streaming endpoints, or MCP server, per deploy target.
- UI/UX — chat or dashboard. For React, prefer the framework's own UI primitives (AI SDK UI / AI Elements, Assistant UI, TanStack). For design quality, defer to the host's frontend-design skill if present.
- Persistence & memory — checkpointer / store / vector DB.
- Observability — tracing + evals + cost tracking from day one.
- Deploy — Dockerfile / wrangler / k8s manifests / cloud config for the chosen target.
After each layer: make it run, verify, then continue. Fail loud if a step is skipped.
Step 5 — Agent-engineering concepts
These cut across frameworks — read the matching reference when relevant:
- Building skills for agents →
references/concepts/skills.md - Tool calling (schemas, validation, parallel calls, MCP) →
references/concepts/tool-calling.md - Tracking / observability (traces, evals, cost) →
references/concepts/tracking-observability.md - AI gateways (OpenRouter, AnyRouter, AI gateway, BYOK) →
references/concepts/ai-gateways.md - Model-specific prompting →
references/engineering/{claude,gemini,gpt}.md
Guardrails
- Don't pick a framework silently — recommend with a one-line why, let the user decide.
- Don't embed stale API code — verify against live docs first.
- Build the smallest thing that runs before expanding.
- Keep secrets out of the repo; use env vars / the platform's secret store.
- Match the existing codebase's conventions when in Detect mode.
© chmonitor, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 18 other files (references) in .agents/skills/build-agent of chmonitor/chmonitor.
- SKILL.md
- references/README.md
- references/concepts/ai-gateways.md
- references/concepts/skills.md
- references/concepts/tool-calling.md
- references/concepts/tracking-observability.md
- references/engineering/claude.md
- references/engineering/gemini.md
- references/engineering/gpt.md
- references/frameworks/ai-sdk.md
- references/frameworks/claude-agent-sdk.md
- references/frameworks/cloudflare-agents.md
- references/frameworks/deepagents.md
- references/frameworks/google-adk.md
- references/frameworks/langgraph.md
- references/frameworks/tanstack-ai.md
- workflows
- … and 2 more
Open the folder on GitHubat commit fc39ef0
Compare with similar skills
Build 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Build Agent this skillchmonitor/chmonitor | 299 | — | ~1.8k | Automated safety check: Pass | GPL-3.0 | |
| AI SDKvercel-labs/ai-facts | 168 | 21 repos | ~1.2k | Automated safety check: Pass | None | |
| Failproof AI SDK IntegrationFailproofAI/failproofai | 5.3k | — | ~6k | Automated safety check: Pass | Custom licence | |
| Edgeone Makers MigrationTencentEdgeOne/edgeone-makers-tools | 1.9k | 1 repos | ~4.1k | Automated safety check: Pass | MIT | |
| Edgeone Makers AgentsTencentEdgeOne/edgeone-makers-tools | 1.9k | 1 repos | ~5.8k | Automated safety check: Notes | MIT | |
| LangGraph Decision Modelslangchain-ai/langchain-skills | 1.3k | — | ~2.3k | Automated safety check: Pass | MIT |
Similar skills
- Official
Failproof AI SDK Integration
FailproofAI/failproofai
Helps instrument a custom Python or TypeScript agent to record events for Failproof AI, verify what gets written, and run an evaluator worker that scores the runs.
Edgeone Makers Migration
TencentEdgeOne/edgeone-makers-tools
Migrate existing AI agent projects (LangChain, LangGraph, OpenAI Agents SDK, Claude Agent SDK, CrewAI) to EdgeOne Makers platform conventions.
Edgeone Makers Agents
TencentEdgeOne/edgeone-makers-tools
This skill guides building AI agent endpoints on EdgeOne Makers — five framework routes (DeepAgents, LangGraph, CrewAI, OpenAI Agents SDK, Claude Agent SDK), platform-injected context.store /…
- Official
LangGraph Decision Models
langchain-ai/langchain-skills
Routes LangGraph agents with typed decision models that return probabilities, and finds LLM calls that only exist to produce a routing decision.
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).
More from chmonitor/chmonitor
All 53 skills in this repoHyperframes Creative
chmonitor/chmonitor
Non-animation creative direction for HyperFrames videos. An agent skill from chmonitor/chmonitor.
Hyperframes Media
chmonitor/chmonitor
Audio and media assets for HyperFrames compositions, produced by one shared audio engine (scripts/audio.mjs) — multi-provider TTS (HeyGen / ElevenLabs / Kokoro local), background music + sound…
Remotion To Hyperframes
chmonitor/chmonitor
Port an existing Remotion (React) composition to HyperFrames HTML.
Music To Video
chmonitor/chmonitor
A skill your agent uses when the user has a music track (an audio file, or a video to pull audio from) and wants a beat-synced HyperFrames video, calm to hard-hitting.
Hyperframes Animation
chmonitor/chmonitor
All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus…
Faceless Explainer
chmonitor/chmonitor
turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video, up to ~3 min (sweet spot 30-90s), where every visual is invented (typography, abstract graphics…
Related
Categories
Questions about Build Agent
What does Build Agent do?
Build an AI-agent application end-to-end — from an empty repo or an existing codebase. Build Agent is an agent skill from chmonitor/chmonitor. Build an AI-agent application end-to-end — from an empty repo or an existing codebase.
When should I use Build Agent?
Build Agent fits situations like: the user wants to build an agent; scaffold an agent app; add an agent API; build an agent UI/chat.
How do I install Build Agent in Claude Code?
Run `npx skills add chmonitor/chmonitor --skill build-agent -a claude-code`. Or copy the skill folder (.agents/skills/build-agent in chmonitor/chmonitor) into .claude/skills/build-agent in your project. Claude Code loads it when a task matches its description.
How do I install Build Agent in Codex?
Run `npx skills add chmonitor/chmonitor --skill build-agent -a codex`. Or copy the skill folder (.agents/skills/build-agent in chmonitor/chmonitor) into .agents/skills/build-agent in your project. Codex loads it when a task matches its description.
Can I use Build 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 chmonitor/chmonitor --skill build-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/build-agent, .gemini/skills/build-agent, .github/skills/build-agent and .opencode/skills/build-agent in your project.
What does Build Agent need to run?
SKILL.md names no scripts, command-line tools or credentials: Build Agent is instructions for the agent only. Our summary lists: Python 3; Docker.
Does Build Agent 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 Build Agent 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 Build Agent use?
Build Agent is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Build Agent use?
About 1.8k tokens (SKILL.md is roughly 7.1k 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 5.5k tokens, read only when the agent opens those files.
What are the alternatives to Build Agent?
Skills that share tags, products or a category with Build Agent: AI SDK (vercel-labs/ai-facts, 168 stars), Failproof AI SDK Integration (FailproofAI/failproofai, 5.3k stars), Edgeone Makers Migration (TencentEdgeOne/edgeone-makers-tools, 1.9k stars) and Edgeone Makers Agents (TencentEdgeOne/edgeone-makers-tools, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Build Agent?
chmonitor (a GitHub organization) maintains it in chmonitor/chmonitor, which has 299 GitHub stars. The repository holds 53 skills in this directory. The repository was last updated on October 5, 2026.
Source: chmonitor/chmonitor on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.