checklist-runner

Execute markdown checklists and score items with PASS, FAIL, PARTIAL, or N/A.

Updated May 28, 2026

Search Tags:#code review #markdown #checklist #quality gate #git diff #test evidence #QA validation

Ready to run

npx skills add https://github.com/GustaPaes/aiox-sprint-canvas --skill checklist-runner-gustapaes

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The checklist-runner Skill removes ambiguity from reviews by consistently checking whether submitted work satisfies every requirement in a markdown checklist, producing a clear pass/fail/partial decision and actionable recommendations.

Core Features & Use Cases

Checklist resolution & fuzzy matching: Finds the requested checklist by name across the expected AIOX core development paths and can suggest matches when exact names are missing.
YOLO and interactive execution modes: Runs all sections autonomously for fast grading, or pauses between sections for human confirmation.
Evidence-driven item verdicts: Scores each checklist item as PASS, FAIL, PARTIAL, or N/A by looking for supporting context such as relevant docs/files, test results, and the current git diff.

Quick Start

Run checklist-runner in YOLO mode for your pre-push quality gate by telling the agent: /checklist-runner pre-push-checklist --mode yolo.

Frequently Asked Questions about checklist-runner

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

FAQPage Schema

How do I validate code review requirements against a markdown checklist?▼

You can automate markdown checklist validation by resolving a checklist name, loading local evidence like code and test results, and scoring each item as PASS, FAIL, PARTIAL, or N/A. The execution produces a computed pass-rate summary with final decision recommendations.

What is the best way to run a pre-push quality gate using markdown?▼

Running a pre-push quality gate using markdown is best achieved by executing the checklist in YOLO mode. This autonomously evaluates all sections against local evidence like docs and git diff, generating a final pass/fail decision without requiring interactive human confirmation.

Can I pause checklist execution for human confirmation between sections?▼

Yes, you can pause checklist execution for human confirmation by using the interactive execution mode. This mode pauses between sections to allow human review of the aggregated evidence before proceeding to the next validation checkpoint.

Does checklist validation work with fuzzy name matching if the exact file is missing?▼

Checklist validation does work with fuzzy name matching when the exact file is missing. It searches expected development paths to find the requested checklist and suggests matching alternatives when an exact name is not found.

What evidence sources are used to score QA validation items in a markdown checklist?▼

Evidence sources used to score QA validation items include relevant local docs, code files, test results, and the current git diff. The system aggregates this evidence to determine if each markdown checklist item satisfies story, PR, or release requirements.