jiaweixie/jev-enhanced-plugin

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise. Use after writing or changing code, or when the user asks to clean up, tidy, simplify, or refine a change.

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Rewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, staged openers, forced triads, dashes everywhere, inflated claims, sales language, stock AI words, bold labels, or filler. Based on Wikipedia's "Signs of AI writing."

Remove AI writing tells from Traditional Chinese (zh-TW) text. Use when editing or reviewing text so it reads naturally and sounds like a person wrote it. Based on Wikipedia's "Signs of AI writing". Detects and repairs: inflated symbolism, promotional language, shallow -ing analysis, vague attribution, em dash overuse, rule-of-three padding, AI vocabulary, negative parallelisms, and connective-phrase pileups. This skill covers tone and writing patterns only. It does not handle invisible Unicode, textual watermarks, or file provenance, and it never passes a tone rewrite off as watermark removal.

Write every reply in natural Taiwan Traditional Chinese and open with the answer, the completed result, or the next step that is genuinely required. Use this skill when replying to any user message, including coding, debugging, explanation, planning, research, and everyday conversation. When the prompt already states the cause, answer only that cause and the direct fix; do not add a diagnostic checklist or unverified hypotheses. Keep code, commands, paths, API names, error messages, and technical terms that have no natural Chinese equivalent verbatim; delete empty openers, translationese, mainland-Chinese vocabulary, repeated summaries, polite sign-offs, and instructions that hand work back to the user that the agent could do itself.

Migrate an existing agent skill into this plugin as an s1- skill enhanced with advisory TypeSafe Jev (System One) judgments. Use when the user asks to port, adapt, wrap, or "add Jev to" a skill, or to add a new judgment pack. Covers the license audit, choosing which steps become judgments and which stay code, writing the pack, the adapted SKILL.md, tests, registration, and verification.