skill-creator

Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.

Best use case

skill-creator is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.

Teams using skill-creator should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/skill-creator/SKILL.md --create-dirs "https://raw.githubusercontent.com/Gentleman-Programming/gentle-ai/main/internal/assets/skills/skill-creator/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/skill-creator/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How skill-creator Compares

Feature / Agentskill-creatorStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

## When to Create a Skill

Create a skill when:
- A pattern is used repeatedly and AI needs guidance
- Project-specific conventions differ from generic best practices
- Complex workflows need step-by-step instructions
- Decision trees help AI choose the right approach

**Don't create a skill when:**
- Documentation already exists (create a reference instead)
- Pattern is trivial or self-explanatory
- It's a one-off task

---

## Skill Structure

```
skills/{skill-name}/
├── SKILL.md              # Required - main skill file
├── assets/               # Optional - templates, schemas, examples
│   ├── template.py
│   └── schema.json
└── references/           # Optional - links to local docs
    └── docs.md           # Points to docs/developer-guide/*.mdx
```

---

## SKILL.md Template

```markdown
---
name: {skill-name}
description: >
  {One-line description of what this skill does}.
  Trigger: {When the AI should load this skill}.
license: Apache-2.0
metadata:
  author: gentleman-programming
  version: "1.0"
---

## When to Use

{Bullet points of when to use this skill}

## Critical Patterns

{The most important rules - what AI MUST know}

## Code Examples

{Minimal, focused examples}

## Commands

```bash
{Common commands}
```

## Resources

- **Templates**: See [assets/](assets/) for {description}
- **Documentation**: See [references/](references/) for local docs
```

---

## Naming Conventions

| Type | Pattern | Examples |
|------|---------|----------|
| Generic skill | `{technology}` | `pytest`, `playwright`, `typescript` |
| Project-specific | `{project}-{component}` | `myapp-api`, `myapp-ui` |
| Testing skill | `{project}-test-{component}` | `myapp-test-sdk`, `myapp-test-api` |
| Workflow skill | `{action}-{target}` | `skill-creator`, `jira-task` |

---

## Decision: assets/ vs references/

```
Need code templates?        → assets/
Need JSON schemas?          → assets/
Need example configs?       → assets/
Link to existing docs?      → references/
Link to external guides?    → references/ (with local path)
```

**Key Rule**: `references/` should point to LOCAL files, not web URLs.

---

## Frontmatter Fields

| Field | Required | Description |
|-------|----------|-------------|
| `name` | Yes | Skill identifier (lowercase, hyphens) |
| `description` | Yes | What + Trigger in one block |
| `license` | Yes | Always `Apache-2.0` |
| `metadata.author` | Yes | `gentleman-programming` |
| `metadata.version` | Yes | Semantic version as string |

---

## Content Guidelines

### DO
- Start with the most critical patterns
- Use tables for decision trees
- Keep code examples minimal and focused
- Include Commands section with copy-paste commands

### DON'T
- Add Keywords section (agent searches frontmatter, not body)
- Duplicate content from existing docs (reference instead)
- Include lengthy explanations (link to docs)
- Add troubleshooting sections (keep focused)
- Use web URLs in references (use local paths)

---

## Registering the Skill

After creating the skill, add it to `AGENTS.md`:

```markdown
| `{skill-name}` | {Description} | [SKILL.md](skills/{skill-name}/SKILL.md) |
```

---

## Checklist Before Creating

- [ ] Skill doesn't already exist (check `skills/`)
- [ ] Pattern is reusable (not one-off)
- [ ] Name follows conventions
- [ ] Frontmatter is complete (description includes trigger keywords)
- [ ] Critical patterns are clear
- [ ] Code examples are minimal
- [ ] Commands section exists
- [ ] Added to AGENTS.md

## Resources

- **Templates**: See [assets/](assets/) for SKILL.md template

Related Skills

skill-registry

1699
from Gentleman-Programming/gentle-ai

Create or update the skill registry for the current project. Scans user skills and project conventions, writes .atl/skill-registry.md, and saves to engram if available. Trigger: When user says "update skills", "skill registry", "actualizar skills", "update registry", or after installing/removing skills.

sdd-verify

1699
from Gentleman-Programming/gentle-ai

Validate that implementation matches specs, design, and tasks. Trigger: When the orchestrator launches you to verify a completed (or partially completed) change.

sdd-tasks

1699
from Gentleman-Programming/gentle-ai

Break down a change into an implementation task checklist. Trigger: When the orchestrator launches you to create or update the task breakdown for a change.

sdd-spec

1699
from Gentleman-Programming/gentle-ai

Write specifications with requirements and scenarios (delta specs for changes). Trigger: When the orchestrator launches you to write or update specs for a change.

sdd-propose

1699
from Gentleman-Programming/gentle-ai

Create a change proposal with intent, scope, and approach. Trigger: When the orchestrator launches you to create or update a proposal for a change.

sdd-init

1699
from Gentleman-Programming/gentle-ai

Initialize Spec-Driven Development context in any project. Detects stack, conventions, testing capabilities, and bootstraps the active persistence backend. Trigger: When user wants to initialize SDD in a project, or says "sdd init", "iniciar sdd", "openspec init".

sdd-explore

1699
from Gentleman-Programming/gentle-ai

Explore and investigate ideas before committing to a change. Trigger: When the orchestrator launches you to think through a feature, investigate the codebase, or clarify requirements.

sdd-design

1699
from Gentleman-Programming/gentle-ai

Create technical design document with architecture decisions and approach. Trigger: When the orchestrator launches you to write or update the technical design for a change.

sdd-archive

1699
from Gentleman-Programming/gentle-ai

Sync delta specs to main specs and archive a completed change. Trigger: When the orchestrator launches you to archive a change after implementation and verification.

sdd-apply

1699
from Gentleman-Programming/gentle-ai

Implement tasks from the change, writing actual code following the specs and design. Trigger: When the orchestrator launches you to implement one or more tasks from a change.

judgment-day

1699
from Gentleman-Programming/gentle-ai

Parallel adversarial review protocol that launches two independent blind judge sub-agents simultaneously to review the same target, synthesizes their findings, applies fixes, and re-judges until both pass or escalates after 2 iterations. Trigger: When user says "judgment day", "judgment-day", "review adversarial", "dual review", "doble review", "juzgar", "que lo juzguen".

issue-creation

1699
from Gentleman-Programming/gentle-ai

Issue creation workflow for Agent Teams Lite following the issue-first enforcement system. Trigger: When creating a GitHub issue, reporting a bug, or requesting a feature.