一键导入
skillcheck
Validates SKILL.md files for spec-facing structure, sizing, references, cross-agent compatibility, and agent-authored critique or graph diagnostics.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Validates SKILL.md files for spec-facing structure, sizing, references, cross-agent compatibility, and agent-authored critique or graph diagnostics.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | skillcheck |
| description | Validates SKILL.md files for spec-facing structure, sizing, references, cross-agent compatibility, and agent-authored critique or graph diagnostics. |
| version | 1.3.0 |
| author | Brad Kinnard (moonrunnerkc), Aftermath Technologies Ltd |
Use this skill when validating a SKILL.md file or a directory of skill files with the skillcheck CLI.
Run the default symbolic checks:
skillcheck SKILL.md
skillcheck skills/ --format json
The report includes errors, warnings, and info diagnostics. Exit code 0 means no errors. Exit code 1 means at least one error, or warnings with --strict, or a regression with --fail-on-regression. Exit code 2 means input or argument error. Exit code 3 means symbolic validation passed but ingested agent critique found semantic errors.
For semantic self-critique, emit a prompt and ingest the returned JSON:
skillcheck SKILL.md --emit-critique-prompt > prompt.txt
skillcheck SKILL.md --ingest-critique response.json
For capability graph work, use:
skillcheck SKILL.md --analyze-graph
skillcheck SKILL.md --emit-graph --format json
skillcheck.toml can set CLI defaults and frontmatter extension fields:
[frontmatter]
extension_fields = ["my-org-tag", "internal-id"]
Validates and scores SKILL.md files against the agentskills.io specification; use when linting skills for cross-agent compatibility, description quality, or capability graph structure.
Placeholder skill for authors to copy before publishing.