aiskillstore/marketplace / skills/aaronabuusama/create-skill
create-skill
VerifiedGuide for creating new skills in Kai's personal AI infrastructure. Use when user wants to create, update, or structure a new skill that extends capabilities with specialized knowledge, workflows, or tool integrations. Follows both Anthropic skill standards and PAI-specific patterns.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.3 KB |
| skill-report.json | config | 22.8 KB |
| templates/CLAUDE-template.md | markdown | 5.8 KB |
| templates/README.md | markdown | 4.6 KB |
| templates/complex-skill-template.md | markdown | 2.1 KB |
| templates/simple-skill-template.md | markdown | 1.5 KB |
| templates/skill-with-agents-template.md | markdown | 5.2 KB |
| workflows/create-new.md | markdown | 1.2 KB |
| workflows/update-existing.md | markdown | 1.1 KB |
templates/complex-skill-template.md
View on GitHub---
name: skill-name
description: Comprehensive description. Mention key methods and tools. USE WHEN user says 'trigger phrase 1', 'trigger phrase 2', or requests related capabilities.
---
# Skill Name
## When to Activate This Skill
- Building/creating [domain] applications
- Implementing [capability]
- User requests [specific feature]
- Working with [technology stack]
- [Domain]-related tasks
## Core Workflow
### Phase 1: [Setup/Initialization]
**Command:** `/command-name` (if applicable)
[Quick setup instructions]
**Key actions:**
- Action 1
- Action 2
- Action 3
### Phase 2: [Main Work]
**Command:** `/command-name` (if applicable)
[Core execution steps]
**Key actions:**
- Action 1
- Action 2
- Action 3
### Phase 3: [Validation/Completion]
**Command:** `/command-name` (if applicable)
[Validation and completion steps]
**Key actions:**
- Action 1
- Action 2
- Action 3
## Key Components
- **Component 1**: Brief description and purpose
- **Component 2**: Brief description and purpose
- **Component 3**: Brief description and purpose
## Default Configuration / Stack
Standard setup for this skill:
- Technology 1
- Technology 2
- Technology 3
- Tool 1 (not Tool 2)
- Package manager preference
## Critical Requirements
- **Requirement 1** (MANDATORY) - Explanation
- **Requirement 2** (MANDATORY) - Explanation
- **Requirement 3** (MANDATORY) - Explanation
## Supplementary Resources
For full methodology: `read ${PAI_DIR}/skills/[skill-name]/CLAUDE.md`
For component details: `read ${PAI_DIR}/skills/[skill-name]/[component-dir]/`
For stack info: `read ${PAI_DIR}/skills/[skill-name]/primary-stack/CLAUDE.md`
## Available Commands
- `/command-1` - What it does and when to use
- `/command-2` - What it does and when to use
- `/command-3` - What it does and when to use
## Key Principles
1. Principle 1 with brief explanation
2. Principle 2 with brief explanation
3. Principle 3 with brief explanation
4. Principle 4 with brief explanation
5. Principle 5 with brief explanation
## Quick Reference
### Common Tasks
**Task 1:**
```bash
command-sequence-1
```
**Task 2:**
```bash
command-sequence-2
```
**Task 3:**
```bash
command-sequence-3
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |