fixer

Generate approval-gated repair plans from evaluator reports and apply fixes via ralphy verbs.

118|12|Updated May 5, 2026
One-click install
npx skills add https://github.com/alecs5am/ralphy --skill fixer-alecs5am
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: fixer
Source: https://github.com/alecs5am/ralphy/tree/main/.agents/skills/fixer
Command: npx skills add https://github.com/alecs5am/ralphy --skill fixer-alecs5am

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The fixer consumes evaluator outputs and turns them into a deterministic, action-ready repair plan, gating costs and ensuring no paid-model calls occur before user approval.

Core Features & Use Cases

  • Reads eval output (eval-deep-vision.json or eval.json) to classify findings by ownership (art-director / scenarist / editor) and orders them by severity.
  • Generates and presents a grouped repair plan via the repair-plan verb, then waits for user approval before applying fixes through existing ralphy verbs, re-renders, and re-evaluates.
  • Provides a safe-guarded workflow for batch or single-item repair with append-only versioning and zero-model-invocations until approved.

Quick Start

Run the evaluator to generate a report, then use ralphy project repair-plan <id> to generate a repair plan and apply approved fixes via the existing ralphy verbs.

Frequently Asked Questions about fixer

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

FAQPage Schema
How do I turn video quality evaluation reports into actionable repair plans?

Video quality evaluation reports are converted into actionable repair plans by reading evaluator outputs, classifying findings by ownership and severity, and generating an approval-gated plan before applying fixes. This ensures no expensive operations occur without explicit user approval.

Can I automate video repairs without triggering paid model calls before approval?

Yes, you can automate video repairs without paid model calls by using a deterministic, zero-model plan that strictly gates expensive operations. The workflow waits for user approval before applying fixes through existing re-render and re-evaluate verbs.

What is the process for classifying evaluator findings to plan video quality repairs?

Classifying evaluator findings for video quality repairs involves reading eval output files, sorting issues by severity, and grouping them by ownership roles like art-director, scenarist, or editor to generate a structured and actionable repair plan.

How do I generate a repair plan for evaluated videos and apply approved fixes?

To generate a repair plan for evaluated videos, run the evaluator to produce a report, then use the repair-plan verb to output a grouped plan. After reviewing and approving the plan, apply fixes through existing verbs to re-render and re-evaluate.

Does the video repair workflow support batch processing and version control?

Yes, the video repair workflow supports batch or single-item repair with append-only versioning. This provides a safe-guarded process ensuring deterministic fixes are tracked and applied without overwriting previous file states.