Skill Creator

Creates complete, spec-compliant skill packages following AgentSkills.io and Anthropic standards.

Supports both creation and validation workflows with 100-point marketplace grading.

Overview

Skill Creator solves the gap between writing ad-hoc agent skills and producing marketplace-ready

packages that score well on the Intent Solutions 100-point rubric. It enforces the 2026 spec

(top-level identity fields, ${CLAUDESKILLDIR} paths, scored sections) and catches

contradictions that would cost marketplace points. Supports two modes: create new skills from

scratch with full validation, or grade/audit existing skills with actionable fix suggestions.

Table of Contents

• Instructions — Create mode (Steps 1-10) + Mode Detection
• Validation Workflow — Grade/audit existing skills (Steps V1-V5)
• Examples — Create, full package, and validate examples
• Edge Cases — Name conflicts, long content, legacy metadata
• Error Handling — Common errors and solutions
• Resources — Reference files and scripts
• Running and Evaluating Test Cases — Subagent-based eval with viewer
• Improving the Skill — Iteration loop based on feedback
• Description Optimization (Automated) — Automated trigger accuracy tuning
• Advanced: Blind Comparison — A/B testing between skill versions
• Packaging — Create distributable .skill files
• Platform-Specific Notes — Claude.ai and Cowork adaptations

Instructions

Mode Detection

Determine user intent from their prompt:

• Create mode: "create a skill", "build a skill", "new skill" -> proceed to Step 1
• Validate mode: "validate", "check", "grade", "score", "audit" -> jump to Validation Workflow

Step 1: Understand Requirements

Ask the user with AskUserQuestion:

Skill Identity:

• Name (kebab-case, gerund preferred: processing-pdfs, analyzing-data)
• Purpose (1-2 sentences: what it does + when to use it)

Execution Model:

• User-invocable via /name? Or background knowledge only?
• Accepts arguments? ($ARGUMENTS substitution)
• Needs isolated context? (context: fork for subagent execution)
• Explicit-only invocation? (disable-model-invocation: true — prevents auto-activati