Validates AI agent skill definitions (SKILL.md files) against the Anthropic agent skill specification. Checks frontmatter fields (name, description), format rules, and body guidelines. Use when validating skills, checking SKILL.md files, or reviewing skill definitions for spec compliance.
Check if aigent is available:
command -v aigent
If aigent is on $PATH, use the CLI for authoritative validation:
aigent validate <skill-directory>
Exit code 0 means valid. Non-zero means errors. Warnings are printed but do not cause failure.
If a SKILL.md file path is provided instead of a directory, aigent
automatically resolves to the parent directory.
If aigent is not available, validate manually by reading the SKILL.md
and checking these rules:
--- delimitersname field: present, string, ≤ 64 chars, lowercase + hyphens + numbers
only, no consecutive hyphens, no leading/trailing hyphens, no reserved
words ("anthropic", "claude"), no XML tags, matches directory namedescription field: present, string, non-empty, ≤ 1024 chars, no XML tagscompatibility: if present, string, ≤ 500 charslicense: if present, stringallowed-tools: if present, stringReport each issue on its own line. Prefix warnings with "warning: ".
npx skills add wkusnierczyk/aigent-validator下载完整 Skill 目录,包含 SKILL.md 及所有相关文件
Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Start voice calls via the OpenClaw voice-call plugin.
Notion API for creating and managing pages, databases, and blocks.
Gemini CLI for one-shot Q&A, summaries, and generation.
Category:developer