القائمة
Audits questions, recommendations, PRD, AC, policy, measurement, and decision logs for AI-like wording while preserving practical product terms.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Writes testable acceptance criteria using Given/When/Then, linking each AC to requirement, priority, operating intent, scalability, screen data-req-id, policy ID, and measurement/logging ID.
Extracts reusable patterns from competitor or reference examples without copying them, then rates Must-have/Nice-to-have fit as Green, Yellow, or Red.
Records why product decisions were made, including question, choices, user selection, recommendation, deferred alternatives, policy links, measurement links, and AC links.
Writes Claude Design handoff briefs and prototype prompts from confirmed product decisions, including screens, actions, states, policies, measurement requirements, Must-have/Nice-to-have priority, operating intent, scalability, and unresolved items.
Designs user behavior events, state change logs, operational records, KPI links, privacy cautions, and information that should not be recorded.
Extracts permission policies, state policies, input policies, restrictions, notification rules, search/filter policies, operating policies, exceptions, and retention rules.
| name | human-writing-auditor |
| description | Audits questions, recommendations, PRD, AC, policy, measurement, and decision logs for AI-like wording while preserving practical product terms. |
Remove AI-like wording from questions, choices, recommendation cards, PRD, AC, policy, measurement, and decision log documents.
https://github.com/blader/humanizer is a reference and benchmark only.
Do not require it as an external dependency.
references/humanizer-reference.mdreferences/ai-wording-patterns.mdreferences/rewrite-rules.mdreferences/banned-phrases.mdreferences/tone-examples.mdreferences/final-audit-checklist.md