creating-skills
Creating Skills
This skill walks you through creating a well-structured agent skill from scratch. Follow the workflow below step by step. Use the reference files for detailed guidance on specific topics.
Reference Files
| File | Read When |
|---|---|
references/format-specification.md |
Checking format rules, frontmatter constraints, or naming conventions |
references/skill-patterns.md |
Choosing a skill pattern or viewing skeleton templates |
references/workflow-and-output-patterns.md |
Designing workflows, output formats, or feedback loops |
references/quality-checklist.md |
Running the pre-ship quality checklist |
references/anti-patterns.md |
Reviewing common mistakes to avoid |
references/evaluation-guide.md |
Creating evaluations to measure skill quality objectively |
references/hooks-recipes.md |
Setting up hooks in skills or understanding hook patterns |
Core Principles
More from riccardogrin/skills
creating-sprites
Guides pixel-art sprite creation via OpenAI gpt-image-1.5 image generation with automated processing. Covers sizing, prompting, transparency verification, downscaling, and cropping. Use when creating game sprites or pixel art assets
18looping-tasks
Generates an autonomous implementation loop that executes tasks from a plan across Claude sessions, with periodic audit passes that inject follow-up tasks. Covers loop script, prompt design, and audit cadence. Use when setting up autonomous task execution or Ralph-style iterative workflows
16planning
Creates implementation-ready plans through discovery interviews, external research, and codebase analysis. Covers requirements, competitor research, architecture decisions, and change sequencing. Use when planning features, roadmaps, specs, or any work that needs discovery before coding
14listing-docs
Scans docs/ folder for markdown files with YAML front-matter and lists their summaries and read_when hints. Helps identify relevant documentation before coding. Use when starting a task, checking available docs, or asking "what docs exist
14enforcing-architecture
Sets up automated architecture enforcement via check scripts and hooks that catch layer violations on every file edit. Run after `/initializing-projects` for complex projects with 3+ distinct layers, or when no ARCHITECTURE.md exists and the codebase has clear architectural boundaries worth enforcing mechanically
14initializing-projects
Generates a minimal, self-maintaining CLAUDE.md for projects through auto-detection and developer interview. Covers project identity, do/don't rules, hooks, and self-maintenance. Use when starting a new project or adding Claude Code support to an existing one
13