mgiovani/ai-arsenal / skills/create-skill
create-skill
VerifiedCreate a new agent skill (or Claude Code slash command) from a plain-language description, using live spec fetching, pattern research, and an approval-gated blueprint before any files are written. Use whenever the user wants to build, scaffold, or author a new skill, subagent capability, or slash command, including phrasings like 'make a command for X', 'create a slash command', 'turn this into a reusable skill', or 'package this workflow as a skill'. Not for editing CLAUDE.md/AGENTS.md memory rules (use create-rule) or discovering/installing existing third-party skills (use find-skills).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 20.3 KB |
| evals/evals.json | config | 3.5 KB |
| evals/trigger-eval.json | config | 2.2 KB |
| references/agent-prompts.md | markdown | 4.5 KB |
| references/eval-system.md | markdown | 5.6 KB |
| references/frontmatter-fields.md | markdown | 2.8 KB |
| references/schemas.md | markdown | 6.3 KB |
| references/skill-anatomy.md | markdown | 10.2 KB |
| references/specification-urls.md | markdown | 2.6 KB |
| scripts/generate_report.py | script | 11.5 KB |
| scripts/improve_description.py | script | 16.7 KB |
| scripts/package_skill.py | script | 4.5 KB |
| scripts/quick_validate.pyexecutable | script | 11.1 KB |
| scripts/run_eval.py | script | 8.1 KB |
references/specification-urls.md
View on GitHub# Specification URLs
Canonical URLs for skill specifications, best practices, and examples. These should be fetched fresh in Phase 0 of every skill creation.
## Primary Specifications
### Agent Skills Standard
- What Are Skills: https://agentskills.io/what-are-skills.md
- Extract: Definition of skills, when to use them, anatomy overview
- Specification: https://agentskills.io/specification.md
- Extract: YAML frontmatter fields (required vs optional), directory structure rules
### Claude Code Best Practices
- Official Best Practices: https://platform.claude.com/docs/skills/best-practices.md
- Extract: Progressive disclosure, writing style, tool selection, anti-hallucination patterns
- Fallback: If URL fails, use bundled `<skill-dir>/references/skill-anatomy.md`
## Example Sources
### Skills Repositories
- skills.sh Ecosystem: https://skills.sh
- Public registry of community skills
- Search for similar skills to understand patterns
- Anthropic Official Skills: https://github.com/anthropics/skills
- Reference implementations from Anthropic
- High-quality examples of skill structure
- Anthropic skill-creator (actively fetched in Phase 2): https://raw.githubusercontent.com/anthropics/skills/main/skills/skill-creator/SKILL.md
- Anthropic's own reference implementation for skill creation
- Extract: workflow phases, frontmatter patterns, anti-hallucination techniques
- cc-arsenal Skills: Local `skills/` directory
- See the current listing for the live count, good source for tool usage and verification patterns
- mgiovani/skills: https://github.com/mgiovani/skills
- Cross-platform skills following Agent Skills standard
- Examples of model-invoked vs user-invoked patterns
## Fallback References
If WebFetch fails for any URL, use bundled fallback documentation:
- Frontmatter Fields: `<skill-dir>/references/frontmatter-fields.md`
- Complete list of frontmatter fields, argument substitution, and the `context: fork` pattern
- Skill Anatomy: `<skill-dir>/references/skill-anatomy.md`
- Folder conventions and composition patterns
## Fetch Strategy
Phase 0 of create-skill should:
1. WebFetch agentskills.io specification directly (no subagent, it's one small fetch)
2. WebFetch platform.claude.com best practices, falling back to bundled references above if it fails
3. Hold results in context for Phases 1-5
4. Never proceed without fresh specifications
Why fetch every time:
- Specifications evolve (new frontmatter fields, tool options)
- Best practices update with new patterns
- Cached docs lead to skills using deprecated features
- Fresh docs ensure compatibility with latest Claude Code versions
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |