This is the meta-skill that builds other skills. It scaffolds the directory structure (SKILL.md, scripts/, references/, assets/), validates frontmatter, and enforces the progressive disclosure pattern where only relevant parts load into context. The core insight here is treating the context window as a scarce resource: lean activation triggers, body under 500 lines, heavy docs in references/, fragile code in scripts/. It uses skill_manage for creation with auto-validation, and includes degree-of-freedom guidance so you know whether to write natural language instructions or exact executable scripts. If you're extending Claude with new capabilities or API integrations, this is where you start.

skills.sh installs
7.8K
GitHub stars
32
last updated
Aug 21, 2026

Install

$ npx -y skills add starchild-ai-agent/official-skills --skill skill-creator --agent claude-code

Installs into .claude/skills of the current project.

Files

logo.png

Core Principles

Concise is key. The context window is a shared resource between the system prompt, skills, conversation history, and your reasoning. Every line in a SKILL.md competes with everything else. Only add what you don't already know — don't document tool parameters visible in the system prompt, don't prescribe step-by-step workflows for things you can figure out. Focus on domain knowledge, interpretation guides, decision frameworks, and gotchas.

Progressive disclosure. Skills load in three levels:

  1. Always in context — name, emoji, and description appear in <available_skills> in every conversation. This is how you decide which skill to activate. The description must be a strong trigger.
  2. On activation — the full SKILL.md body is loaded via read_file when you decide the skill is relevant. This is where workflow, guidelines, and decision trees live.
  3. On demand — scripts/, references/, and assets/ are only loaded when explicitly needed. Heavy content goes here, not in the body.

Sponsors

Details

Repository
github.com/starchild-ai-agent/official-skills
Categories
Frontend Development, Backend & APIs, AI & Agent Building, Skill Development, Automation & Workflows
First seen
May 16, 2026

More from starchild-ai-agent/official-skills

All 43
1wondelai avatarclean-architecturewondelai/skillsStructure software around the Dependency Rule: source code dependencies point inward from frameworks to use cases to entities. Use when the user mentions "archi7.7Kskills.sh installs
2lackeyjb avatarplaywright-skilllackeyjb/playwright-skillComplete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check respon7.5Kskills.sh installs
3anthropics avatarhook-developmentanthropics/claude-plugins-officialThis skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", 7.5Kskills.sh installs
4agricidaniel avatarseo-imagesagricidaniel/claude-seoImage optimization analysis for SEO and performance. Checks alt text, file sizes, formats, responsive images, lazy loading, CLS prevention, image SERP rankings 7.5Kskills.sh installs
5pproenca avatarzodpproenca/dot-skillsZod schema validation best practices for type safety, parsing, and error handling. This skill should be used when defining z.object schemas, using z.string vali7.2Kskills.sh installs
6wondelai avatarmicrointeractionswondelai/skillsDesign the small details -- triggers, rules, feedback, loops and modes -- that separate good products from great ones. Use when the user mentions "microinteract7.2Kskills.sh installs