skeall

# Skeall

Create, improve, and audit Agent Skills following the [Agent Skills open standard](https://agentskills.io). This skill encodes lessons from real-world skill development and cross-platform compatibility testing.

## Quick start

```text
/skeall --create              # Interview, then scaffold new skill
/skeall --improve <path>      # Analyze and improve existing skill
/skeall --scan <path>         # Audit only, no changes (report)
/skeall --scan .              # Audit skill in current directory
/skeall --scan-all            # Batch scan all skills in ~/.claude/skills/
/skeall --scan-all <dir>      # Batch scan all skills in custom directory
/skeall --healthcheck <path>  # Runtime check single skill (orphans, deps, env, URLs)
/skeall --healthcheck-all     # Runtime check all skills in ~/.openclaw/skills/
/skeall --healthcheck-all <dir> # Runtime check all skills in custom directory
```

---

## Mode 1: Create (scaffold a new skill)

### Process

1. Interview the user (ask questions 1-4 always, then 5-6 if user hasn't already specified complexity or distribution scope):
   - What does this skill do? (one sentence)
   - What category? Reference / Task / MCP Enhancement / Hybrid. See [references/advanced-patterns.md](references/advanced-patterns.md)
   - What triggers should activate it? (keywords users would type)
   - Does it accept arguments? (e.g., file path, topic — use `$ARGUMENTS` or `$ARGUMENTS[N]` in body)
   - How complex is it? (single file vs references/ needed)
   - Will this skill be shared? (personal / project / public) — affects README, license, metadata

2. Generate the skill structure:

```text
{skill-name}/
├── SKILL.md                    # Core instructions (always loaded)
├── references/                 # On-demand detail files
│   ├── {topic-1}.md
│   └── {topic-2}.md
└── README.md                   # GitHub-facing (optional)
```

3. Write SKILL.md following these rules:
   - YAML frontmatter with `name` and `description` (see Frontmatter...

# Skeall

Build, improve, and audit [Agent Skills](https://agentskills.io) for cross-platform LLM coding agents.

Skeall encodes real-world lessons from building and restructuring production skills across Claude Code, OpenAI Codex, Cursor, Gemini CLI, OpenClaw, and 20+ other platforms that support the Agent Skills open standard.

## What it does

- **Create** new skills from scratch with guided interviews and scaffolding
- **Improve** existing skills with specific before/after edit proposals
- **Scan** skills for spec compliance, LLM-friendliness, and cross-platform issues
- **Batch scan** your entire skill collection at once
- **Health check** runtime issues that static scan misses: orphans, duplicates, broken deps, stale endpoints

## Installation

```bash
# Claude Code
git clone https://github.com/dorukardahan/skeall ~/.claude/skills/skeall

# OpenAI Codex
git clone https://github.com/dorukardahan/skeall ~/.agents/skills/skeall

# OpenClaw
git clone https://github.com/dorukardahan/skeall ~/.openclaw/skills/skeall
```

## Usage

```text
/skeall --create              # Interview + scaffold new skill
/skeall --improve <path>      # Analyze and improve existing skill
/skeall --scan <path>         # Audit only, severity-tagged report
/skeall --scan-all            # Batch scan all skills
/skeall --healthcheck <path>  # Runtime check single skill
/skeall --healthcheck-all     # Runtime check all skills
```

## What it checks

**Static scan:** 42 checklist items across 6 categories:

| Category | Checks | Examples |
|----------|--------|---------|
| Structure | 8 | SKILL.md exists, name matches dir, references/ dir, no junk files |
| Frontmatter | 6 | Description length (spec + recommended), trigger phrases, naming |
| Content | 11 | Token budget, redundancy, framing style, routing table, count consistency, stale refs |
| LLM-friendliness | 8 | Tables vs bullets, emoji, heading style |
| Security | 5 | No XML injection, no reserved names, no secrets, credential pattern d...