agent-acceptance-gate

Evaluate per-task success criteria and reconciler input to produce PASS/FAIL verdicts.

23|5|Updated Apr 28, 2026
One-click install
npx skills add https://github.com/WenyuChiou/agent-collab-skills --skill agent-acceptance-gate
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-acceptance-gate
Source: https://github.com/WenyuChiou/agent-collab-skills/tree/main/skills/agent-acceptance-gate
Command: npx skills add https://github.com/WenyuChiou/agent-collab-skills --skill agent-acceptance-gate

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

The acceptance gate provides a final quality check for multi-agent rounds by evaluating per-task success criteria, applying reconciler guidance, and verifying budget constraints before a merge.

Core Features & Use Cases

  • Validate per-task success criteria against plan.yml results and reconciler input.
  • Generate an acceptance report and a PASS/FAIL verdict to .coord/acceptance_<NNN>.md.
  • Optionally run prose audits, aggregate risks, and respect reconciler instructions to gate or block merges.

Quick Start

Run the acceptance gate for the current multi-agent round to produce a PASS/FAIL verdict and an accompanying report.

Frequently Asked Questions about agent-acceptance-gate

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

FAQPage Schema
How do I gate multi-agent outputs before merging results?

To gate multi-agent outputs before merging, run an acceptance gate that evaluates per-task success criteria and reconciler input to compute a formal PASS or FAIL verdict and generate an acceptance report.

What is an acceptance gate in a multi-agent workflow?

An acceptance gate is a final quality check that validates per-task success criteria, applies reconciler guidance, and verifies budget constraints to decide if multi-agent outputs are mergeable.

How do I validate per-task success criteria against a plan?

Validating per-task success criteria involves orchestrating checks across plan.yml and result.json files to verify that delegate tasks meet the required conditions before generating a formal acceptance report.

Can I run conditional passes based on reconciler guidance when verifying multi-agent tasks?

Yes, the acceptance gate supports conditional passes by applying reconciler guidance from reconciliation files to gate or block merges, optionally running prose audits and aggregating risks.

When should I run an acceptance gate for my multi-agent round?

You should run the acceptance gate after all delegate tasks complete, allowing it to read plan.yml and reconciliation files to produce a final PASS or FAIL verdict and metadata.

Does the acceptance gate support budget checks for multi-agent task outputs?

Yes, the acceptance gate verifies budget constraints as part of its end-to-end gating process, ensuring multi-agent outputs respect defined limits before deciding mergability and generating the report.