From example-skills
Systematic content evaluation framework progressing through Critique → Reinforcement → Risk Analysis → Growth. Use when reviewing writing, arguments, proposals, code documentation, or any content requiring rigorous multi-dimensional assessment. Supports interactive guided mode or autonomous full-report mode, with output as markdown report, structured checklist, or inline revision suggestions. Triggers on requests to evaluate, critique, improve, strengthen, or review content quality.
npx claudepluginhub organvm-iv-taxis/a-i--skills --plugin document-skillsThis skill uses the workspace's default tool permissions.
A systematic framework for transforming content through rigorous evaluation into stronger, more resilient final products.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Designs, implements, and audits WCAG 2.2 AA accessible UIs for Web (ARIA/HTML5), iOS (SwiftUI traits), and Android (Compose semantics). Audits code for compliance gaps.
A systematic framework for transforming content through rigorous evaluation into stronger, more resilient final products.
Before beginning, determine execution mode and output format.
Interactive Mode: Walk through each phase step-by-step, pausing for user input and direction between stages. Best for collaborative refinement or learning the framework.
Autonomous Mode: Execute all phases and deliver comprehensive results. Best for efficient batch evaluation or when user wants complete analysis upfront.
Markdown Report: Structured document with sections for each phase, findings, and recommendations. Best for documentation or sharing.
Structured Checklist: Itemized findings with status indicators and action items. Best for tracking and implementation.
Inline Revisions: Suggestions embedded within or alongside the original content. Best for direct editing workflow.
[Evaluation] → [Reinforcement] → [Risk Analysis] → [Growth]
Comprehensive assessment across five dimensions.
Identify strengths and weaknesses holistically.
Prompt: "Evaluate this content thoroughly. Identify its key strengths and weaknesses. Highlight which parts are effective and which need improvement, providing specific reasons."
Output structure:
Ensure internal consistency and sound reasoning.
Prompt: "Examine the content for logical consistency. Identify contradictions, gaps in reasoning, or unsupported claims, and suggest how to strengthen coherence."
Output structure:
Assess rational and factual appeal.
Prompt: "Assess the rational and factual appeal of this content. Are the arguments clear, well-supported, and persuasive? Suggest ways to enhance the logical impact."
Output structure:
Evaluate emotional resonance.
Prompt: "Analyze the emotional tone and resonance of this content. Does it create an emotional connection with its intended audience? Recommend adjustments to increase engagement."
Output structure:
Examine credibility and authority.
Prompt: "Evaluate the credibility and authority of this content. Does it reflect expertise and trustworthiness? Suggest ways to reinforce its reliability and professional tone."
Output structure:
Consolidate and strengthen based on evaluation findings.
Integrate logic check findings to eliminate contradictions and reinforce coherence.
Actions:
Identify vulnerabilities before they become failures.
Reveal overlooked areas or hidden assumptions.
Prompt: "Identify any areas in this content that may be overlooked, biased, or based on hidden assumptions. Provide suggestions to address these gaps or risks."
Output structure:
Pinpoint critical vulnerabilities.
Prompt: "Analyze the content for potential vulnerabilities or weak points that could cause failure or serious criticism. Recommend preventive measures or reinforcements."
Output structure:
Transform evaluation into evolution.
Generate new directions from the analysis.
Prompt: "From the reviewed content, generate innovative ideas, new directions, or insights that could enhance or expand its impact."
Output structure:
Produce the strengthened final version.
Prompt: "Incorporate all feedback and refinements to create a polished, stronger, and more resilient final version of the content."
Output structure:
Step 1: "I'll evaluate your content using the Evaluation-to-Growth framework.
First, let's assess strengths and weaknesses. [Critique results]
Would you like to discuss these findings before moving to logic check?"
Step 2: [Wait for response, then proceed to Logic Check]
Step 3: [Continue through each phase with pause points]
Step 4: "We've completed the evaluation phases. Ready to move into Risk Analysis?"
[Continue through all phases with user checkpoints]
"I'll provide a complete Evaluation-to-Growth analysis of your content.
## Evaluation Phase
[All five dimensions with findings]
## Reinforcement
[Synthesis and coherence improvements]
## Risk Analysis
[Blind spots and shatter points]
## Growth
[Emergent insights and evolved version]
## Summary
[Key findings and recommended next steps]"
See references/report-template.md
See references/checklist-template.md
See references/inline-template.md
| Phase | Purpose | Key Question |
|---|---|---|
| Critique | Holistic assessment | What works? What doesn't? |
| Logic Check | Internal consistency | Does it contradict itself? |
| Logos | Rational appeal | Is the argument sound? |
| Pathos | Emotional appeal | Does it connect? |
| Ethos | Credibility | Is it trustworthy? |
| Blind Spots | Hidden risks | What am I not seeing? |
| Shatter Points | Critical vulnerabilities | Where could this fail? |
| Bloom | Emergent growth | What new possibilities emerge? |
| Evolve | Final refinement | What's the strongest version? |
references/report-template.md - Full markdown report formatreferences/checklist-template.md - Structured checklist formatreferences/inline-template.md - Inline revision format