skeall
Agent Skills (SKILL.md) builder, auditor, and improver for cross-platform LLM agents. Use for "skeall", "build a skill", "create skill", "improve skill", "audit skill", "skill review", or any SKILL.md question. Follows agentskills.io standard.
Why use this skill?
Build, audit, and improve your OpenClaw AI agent skills with Skeall. Ensure full compatibility with the agentskills.io standard and optimize your agent performance.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/dorukardahan/skeallWhat This Skill Does
Skeall is the definitive CLI companion for the OpenClaw AI agent ecosystem, designed to streamline the lifecycle of Agent Skills. It acts as an architect, auditor, and quality assurance engine, ensuring that all custom skills adhere strictly to the agentskills.io open standard. Whether you are scaffolding a new skill from a simple idea or refactoring legacy instructions for cross-platform compatibility, Skeall automates the structural requirements and best practices for you.
Installation
To install Skeall, run the following command in your terminal:
clawhub install openclaw/skills/skills/dorukardahan/skeall
Ensure your OpenClaw environment is initialized to correctly map the skill directory.
Use Cases
- Rapid Prototyping: Quickly generate a compliant
SKILL.mdfile by answering a few guided questions during the creation flow. - Quality Assurance: Audit existing skill repositories to detect potential runtime errors, missing references, or configuration gaps before deployment.
- Maintenance: Refactor growing skill bases by splitting monolithic instructions into modular reference files, maintaining optimal token usage and clarity.
- Compatibility Testing: Verify that skills are ready for cross-platform usage through automated health checks that validate local and external dependencies.
Example Prompts
- "/skeall --create"
- "/skeall --improve ./my-research-skill"
- "/skeall --scan ."
Tips & Limitations
- Token Management: Keep your
SKILL.mdunder 5000 tokens to ensure the agent maintains high recall and performance during execution. - Modularize: Use the
references/folder for technical documentation to keep your primary instruction set clean and concise. - Proactive Auditing: Run
--healthcheck-allperiodically to catch stale URL references or orphaned dependencies that might break in new agent versions. - Limitations: Skeall works best with standard directory structures. Non-standard, deeply nested configurations may require manual path adjustments during the audit phase.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-dorukardahan-skeall": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, file-write
Related Skills
traktor
Extract all assets and content from websites including images, SVGs, fonts, videos, and page structure. Parallel agents with thorough scraping coverage. Triggers: "extract assets", "scrape website", "download site assets", "get all images from", or "/traktor url". Supports multiple URLs.
ralph-security
Comprehensive security audit with 100 iterations (~30-60 min). Use when user says 'security audit', 'ralph security', 'weekly security check', 'audit this project', 'new project security review', or 'check for vulnerabilities'. Covers OWASP Top 10, auth, secrets, infrastructure, and code quality.
humanizer-enhanced
Advanced AI text humanizer for blog content. Detects and removes 34 AI writing patterns, adds personality/soul, and handles crypto/Web3 specific tells. Use when user says /humanizer, "humanize this", "remove AI patterns", "make it sound human", or asks to clean up blog posts, articles, or drafts. Features: 28 base patterns from Wikipedia's "Signs of AI writing", 6 crypto/Web3 specific patterns, severity scoring (HIGH/MEDIUM/LOW), stat attribution fixer, soul/personality injection, batch mode.
research-reprompter
Transform rough research questions into executable USACF research prompts. Use when user says "research", "research this", "investigate", "deep dive", "researcher", or pastes a research topic. Generates complete multi-agent swarm configuration with algorithm selection, claude-flow commands, and adversarial review.
ralph-quick
Fast security spot-check with 10 iterations (~5-10 min). Use when user says 'quick security check', 'pre-deploy audit', 'ralph quick', 'fast security scan', 'spot check before deploy', or 'daily security check'. Covers secrets, OWASP basics, auth, rate limiting, and containers.