Audit a prompt file (system prompt, agent definition, voice script, chained workflow) across four lenses — conflict, dominance, gap, drift — plus an optional Turkish phonetic lens for voice agents. Use when the user invokes /prompt-check, asks to "audit a prompt", "check this prompt for contradictions / silent overrides / gaps / drift / voice readability", or passes a path to a prompt file for review. On first run in a repo, walks the user through a 5-question wizard and saves repo defaults to .promptchecker.json. Produces line-anchored findings as report.md + findings.json in an isolated run directory. Never modifies the original prompt file.
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategoryGeneralStars0
About this skill
Audit a prompt file (system prompt, agent definition, voice script, chained workflow) across four lenses — conflict, dominance, gap, drift — plus an optional Turkish phonetic lens for voice agents. Use when the user invokes /prompt-check, asks to "audit a prompt", "check this prompt for contradictions / silent overrides / gaps / drift / voice readability", or passes a path to a prompt file for review. On first run in a repo, walks the user through a 5-question wizard and saves repo defaults to .promptchecker.json. Produces line-anchored findings as report.md + findings.json in an isolated run directory. Never modifies the original prompt file.
Quick start
Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Audit a prompt file (system prompt, agent definition, voice script, chained workflow) across four lenses — conflict, dominance, gap, drift — plus an optional Turkish phonetic lens for voice agents. Use when the user invokes /prompt-check, asks to "audit a prompt", "check this prompt for contradictions / silent overrides / gaps / drift / voice readability", or passes a path to a prompt file for review. On first run in a repo, walks the user through a 5-question wizard and saves repo defaults to `.promptchecker.json`. Produces line-anchored findings as `report.md` + `findings.json` in an isolated run directory. Never modifies the original prompt file.
About this listing
Category
General
Reported license
MIT
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.