Verified:GitHub

checklist-runner

Validate work against Markdown checklists and generate PASS/FAIL/PARTIAL/N/A reports.

Updated Aug 23, 2026

Search Tags:#workflow automation #definition of done #checklist validation #pull request readiness #CI preflight #agent quality gate #documentation evidence

Ready to run

npx skills add https://github.com/freitassph/aiox-core --skill checklist-runner-freitassph

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: checklist-runner
Source: https://github.com/freitassph/aiox-core/tree/main/.claude/skills/checklist-runner
Command: npx skills add https://github.com/freitassph/aiox-core --skill checklist-runner-freitassph

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the uncertainty of whether a deliverable truly meets agreed requirements, by providing consistent pass/fail/partial verdicts against a checklist.

Core Features & Use Cases

Checklist-based validation: Evaluates work against any .md checklist and produces a structured report.
Deterministic verdicting across agents: Applies consistent reasoning rules to mark PASS, FAIL, PARTIAL, or N/A items.
YOLO and interactive review modes: Supports fully autonomous runs or step-by-step user confirmation between sections, ideal for quality gates.

Quick Start

Ask an agent to run the checklist by saying: run /checklist-runner story-dod-checklist in yolo mode to generate a complete approval-focused report for the selected story definition of done.

Frequently Asked Questions about checklist-runner

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

FAQPage Schema

How do I validate work against a definition of done checklist?▼

Checklist validation evaluates work against a Markdown checklist to produce structured PASS, FAIL, PARTIAL, or N/A verdicts by confirming evidence from documentation, diffs, and test outputs.

Can I automate pull request readiness checks in CI preflight?▼

Yes, you can automate pull request readiness by running the checklist validation in YOLO mode for fully autonomous results, applying consistent reasoning rules to serve as an agent quality gate.

How do I run a checklist validation in interactive mode?▼

Checklist validation runs in interactive mode by executing the checklist step-by-step, allowing user confirmation between sections to evaluate work and calculate section summaries using pass-rate thresholds.

Does checklist validation support fuzzy matching for checklist names?▼

Checklist validation supports resolving checklists by name with optional fuzzy matching, allowing the agent to load relevant context artifacts before calculating section summaries and an overall decision.

What is the difference between YOLO and interactive review modes?▼

YOLO mode generates a fully autonomous complete report, while interactive review mode provides step-by-step user confirmation between sections, ideal for quality gates requiring human verification.