home/categories/code-quality/piebald-ai-claude-code-system-prompts-claude-skills-validate-prompts-skill-md
code-qualitytesting-security

validate-prompts

Validate extracted Claude Code prompt data by reading files and checking rules directly — no external scripts or API calls needed. Checks JSON structure (30+ rules), generated markdown files, README consistency, and semantic variable name correctness. Use whenever asked to validate prompt JSON files, check generated output, run pre-release checks, debug validation errors, or analyze variable naming. Trigger phrases: "validate", "check prompts", "run validation", "verify prompts", "structural checks", "semantic check", "release prep". Also use when investigating a specific validation rule (A1–A21, B1–B6, C1–C7, A23) or when encountering errors in prompt data.

Piebald-AI
maintainer
Piebald-AI
更新於 4/11/2026
星標
8581
分支
1585
quick start

Installation and usage

Validate extracted Claude Code prompt data by reading files and checking rules directly — no external scripts or API calls needed. Checks JSON structure (30+ rules), generated markdown files, README consistency, and semantic variable name correctness. Use whenever asked to validate prompt JSON files, check generated output, run pre-release checks, debug validation errors, or analyze variable naming. Trigger phrases: "validate", "check prompts", "run validation", "verify prompts", "structural checks", "semantic check", "release prep". Also use when investigating a specific validation rule (A1–A21, B1–B6, C1–C7, A23) or when encountering errors in prompt data.

安裝
$ install --globalskills.sh
使用

安裝後,您可以透過在終端機執行以下指令來使用此技能:

skills use validate-prompts