Skip to content
Agentmart
Submit a tool

ai-automation-builder

Design, implement, verify, and hand over bounded AI-assisted business automations from buyer-supplied workflows and test data; use for custom agents…

Skill by Daisuke134

IndexedMIT★ 8
Write a review

Chalk Labs

Need help deploying ai-automation-builder?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/daisuke134-ai-automation-builder

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Design, implement, verify, and hand over bounded AI-assisted business automations from buyer-supplied workflows and test data; use for custom agents, integrations, browser workflows, and recurring maintenance after a working system exists.

Use cases: design, testing, data

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/ai-automation-builder

What's inside

Skill name
ai-automation-builder
Description
Design, implement, verify, and hand over bounded AI-assisted business automations from buyer-supplied workflows and test data; use for custom agents, integrations, browser workflows, and recurring maintenance after a working system exists.
License
MIT
Instructions
54 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# AI Automation Builder

Turn one repeatable buyer workflow into a working, testable automation. The deliverable is the
implemented system plus evidence and operating instructions, not advice, prompts, or an unsupported
claim that AI can automate the work.

## Intake contract

Require before estimating implementation:

- the current trigger, inputs, decisions, outputs, tools, accounts, and approval points;
- redacted representative samples and the expected result for each sample;
- frequency, volume, failure cost, execution environment, and required delivery date;
- which external actions may run automatically and which require buyer approval.

If these facts are missing, deliver a bounded workflow assessment first. Do not promise an
implementation price, completion date, accuracy, savings, or fully autonomous operation from a
verbal description alone.

## Build contract

Choose the smallest implementation that completes one end-to-end workflow. Reuse the buyer's
existing tools and native integrations before adding services or infrastructure. Keep credentials
outside source, logs, screenshots, and deliverables. Fence every external effect with a stable
identity, checkpoint it before execution, and read the provider result back after execution.

The working package includes:

- source and pinned dependencies or a reproducible project package;
- configuration schema with secret values excluded;
- tests using the agreed redacted samples and expected outputs;
- an execution command or deployed entry point;
- retry, duplicate-prevention, failure and human-approval behavior;
- setup, operation, rollback and ownership instructions.

## Acceptance

Demonstrate the agreed workflow from representative input through the real output boundary. Record
the tested environment, artifact hashes, commands, results, unresolved limitations, and any external
readback. A local model response, process ID, dry run, or screenshot without matching artifact and
provider identity is not acceptance.

Reject or rescope work that requires a buyer's voice, attendance, undisclosed identity, regulatory
judgment, physical action, CAPTCHA/3DS bypass, unauthorized account access, or an external effect the
buyer has not approved.

## Recurring maintenance

Offer recurring support only after the base automation passes acceptance. Define a monthly change
budget, monitored workflows, response window, supported dependencies, exclusions, usage/tool costs,
and renewal/termination boundary. Maintenance may repair and improve the accepted system; it does
not silently expand into new workflows or guarantee uninterrupted third-party services.

From Daisuke134/life-manager, MIT.

More from Daisuke134/life-manager

Signals

Stars
8
Forks
2
Open issues
2,737
Last commit (this folder)
Aug 27, 2026 (2 months ago)
Last release
Aug 15, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Daisuke134

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get ai-automation-builder running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying ai-automation-builder?

CallGet help
Cite this page

ai-automation-builder skill. Agent Mart. https://agentmart.dev/skills/daisuke134-ai-automation-builder (last updated 2026-10-24)