Skip to content
Agentmart
Submit a tool

automation-offer-workbench

Use when productizing automation into reviewable offers.

Skill by AvaTar-ArTs

IndexedMIT
Write a review

Chalk Labs

Need help deploying automation-offer-workbench?

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/avatar-arts-automation-offer-workbench

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

Use when productizing automation into reviewable offers.

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/automation-offer-workbench

What's inside

Skill name
automation-offer-workbench
Description
Use when productizing automation into reviewable offers.
License
MIT
Instructions
62 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Automation Offer Workbench

## Overview

Create a provider-agnostic workbench that turns a client need into an automation plan, tool or MCP adapter, service package, proof asset, documentation, and buyer-facing handoff.

## When to Use

Use when combining Seller OS, media organizer, Fiverr, MCP, Python automation, evidence, and fulfillment workflows into one buyer-safe system.

## Prerequisites

- Preserve `~/fiverr` as the canonical root.
- Separate historical conversation evidence from current-market validation.
- Use agents: `project-launch-manager`, `project-shipper`, `technical-writer`, and `code-reviewer`.
- Start with read-only or preview-only behavior.

## How to Run

1. Gather the request, buyer scenario, source evidence, and desired deliverable.
2. Model entities: Offer, Buyer Scenario, Evidence Item, Source Asset, Workflow State, Approval Gate, Tool, Package, and Handoff.
3. Define states: clarify → fill → preview → approve → package → validate → handoff → platform hold.
4. Define provider-agnostic tool contracts and least-privilege MCP access.
5. Build the smallest local vertical slice.
6. Add preview and dry-run output before write-capable behavior.
7. Generate service copy and proof assets only from approved evidence.
8. Add regression tests and independent review.
9. Produce a local-ready handoff and explicit manual next actions.

## Quick Reference

```text
Skills: content-strategy → domain-modeling → build-mcp-server → mcp-integration
        → quality-regression-testing → narrative-documentation
Agents: project-launch-manager → project-shipper → technical-writer → code-reviewer
Canonical root: ~/fiverr
Default mode: local, preview-first, provider-agnostic
```

## Approval Gates

Require explicit approval before importing drafts, changing canonical state, enabling write-capable MCP tools, exposing a tunnel, using credentials, automating a marketplace, contacting buyers, publishing, submitting, or claiming current pricing/demand/outcomes.

## Common Pitfalls

- Duplicating or relocating `~/fiverr`.
- Claiming current buyer demand from historical material.
- Adding write-capable MCP tools before preview and regression coverage.
- Publishing offer language without evidence or scope boundaries.

## Verification Checklist

- [ ] Canonical root is preserved.
- [ ] Buyer scenario and scope are explicit.
- [ ] Historical claims are marked separately from current claims.
- [ ] Preview and dry-run output exist before mutation.
- [ ] Secret redaction and hold behavior are tested.
- [ ] MCP permissions and tool boundaries are documented.
- [ ] Generated buyer package links to evidence.
- [ ] Independent code and workflow review completed.

From AvaTar-ArTs/all-agent-skills, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 18, 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 AvaTar-ArTs

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 automation-offer-workbench 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 automation-offer-workbench?

CallGet help
Cite this page

automation-offer-workbench skill. Agent Mart. https://agentmart.dev/skills/avatar-arts-automation-offer-workbench (last updated 2026-10-24)