do

Execute manifest-defined deliverables against acceptance criteria with verification loops and logging.

70|9|Updated Jan 27, 2026
One-click install
npx skills add https://github.com/doodledood/manifest-dev --skill do-doodledood
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: do
Source: https://github.com/doodledood/manifest-dev/tree/main/claude-plugins/manifest-dev/skills/do
Command: npx skills add https://github.com/doodledood/manifest-dev --skill do-doodledood

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manifest-driven execution automates validating that deliverables meet acceptance criteria by iterating, adapting, and verifying results, reducing manual rework.

Core Features & Use Cases

  • Iterative execution: runs through Deliverables and Acceptance Criteria, adapting when reality diverges, with an emphasis on verifiable outcomes.
  • Verification loop: automatically invokes /verify to ensure all acceptance criteria and global invariants pass, enabling early detection and fixes.
  • Robust logging: records each AC attempt and decision point to support disaster recovery and audit trails.
  • Use Case: A team defines a manifest with multiple deliverables and acceptance criteria and uses /do to drive execution and ensure verifiable completion.

Quick Start

Provide the manifest file path to start execution.

Frequently Asked Questions about do

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
What is manifest-driven execution for acceptance criteria?

Manifest-driven execution automates validating deliverables by iterating through acceptance criteria and verification steps. It reads a manifest file defining required outputs, logs every attempt, and escalates issues to ensure verifiable completion of end-to-end automation tasks.

How do I automate verification of deliverables using a manifest file?

Provide the manifest file path to start execution. The workflow iterates through deliverables, logs every acceptance criteria attempt, invokes verification steps, and adapts execution when reality diverges from expected outcomes.

Can I recover progress if an automation execution fails midway?

Yes, progress is preserved via a memento log. The workflow records each acceptance criteria attempt and decision point, supporting disaster recovery and audit trails so execution can resume or be reviewed after interruptions.

When should I use automated manifest execution for my deliverables?

Use automated manifest execution for end-to-end tasks where a manifest defines deliverables, acceptance criteria, and verification steps. It reduces manual rework by validating that outputs meet criteria through iterative adaptation and early issue detection.

How does the verification loop handle failed acceptance criteria?

The verification loop invokes /verify to ensure all acceptance criteria and global invariants pass. When reality diverges or criteria fail, it escalates as needed while logging the attempt, enabling early detection and targeted fixes.