Skill Claude CodeCodex
!cat Claude-Production-Grade-Suite/.protocols/ux-protocol.md 2>/dev/null || true !cat Claude-Production-Grade-Suite/.protocols/input-validation.md 2>/dev/null || true !cat Claude-Production-Grade-Suite/.protocols/tool-efficiency.md 2>/dev/null || true !cat Claude-Production-Grade-Suite/.protocols/visual-identity.md…
Skill Claude CodeCodex
!cat Claude-Production-Grade-Suite/.protocols/ux-protocol.md 2>/dev/null || true !cat Claude-Production-Grade-Suite/.protocols/input-validation.md 2>/dev/null || true !cat Claude-Production-Grade-Suite/.protocols/tool-efficiency.md 2>/dev/null || true !cat Claude-Production-Grade-Suite/.protocols/visual-identity.md…
Plugin Claude Code
Voice-true human writing for Claude Code — 60 built-in voice profiles, a deterministic AI-tell scanner, and a closed verify-revise loop.
Plugin Claude Code
A roster of 60 fully-specified human voice profiles plus a deterministic AI-tell scanner. Write, humanize, audit, and mass-produce social posts that read as distinct, genuine people — verified by stylometry, not vibes.
Agent
Blind semantic judge of whether text reads AI-generated — the layer regex can't see. MUST BE USED for /idiolect:audit and the campaign blind pass. Deliberately receives ONLY the text (plus platform); no authorship context, no scanner results, no hints. Returns strict JSON.
Agent
Builds a complete new voice profile from a measured fingerprint (corpus mode) or a gap seed (invention mode) for /idiolect:synthesize and /idiolect:self. Owns the validate loop; returns only when the profile passes spec and roster distance.
Agent
Voice-isolated post writer for /idiolect:campaign fan-out. Receives ONE voice profile, one brief, one platform, one structure assignment — and nothing about any other voice or post, which is what makes N posts genuinely different. Self-verifies with the scanner before returning.
Hook
Runs when you submit a prompt, before the agent sees it, executing self-capture.sh. From nagisanzenin/idiolect.
Skill Claude CodeCodex
Two-layer AI-tell audit of any text — deterministic scanner (lexicon, constructions, stylometry with line numbers) plus a blind semantic judge. Use when the user wants to know whether text reads AI-generated, what specifically gives it away, and how to fix it.
Skill Claude CodeCodex
One brief, N posts, N genuinely different people — voice-isolated writers, cross-post overlap detection, per-post verification receipts. Use for launching/promoting something across multiple posts or platforms without the posts sharing a fingerprint.
Skill Claude CodeCodex
Rewrite existing text so it reads human — either scrubbed-and-souled in its own register, or fully re-voiced as one of the roster's people. Use when the user has a draft that "sounds like AI" or wants existing copy converted into a specific voice.
Skill Claude CodeCodex
Front door and router for the idiolect voice engine. Use when the user mentions idiolect, asks what voices are available or who should write something, wants writing that "doesn't sound like AI", says text "sounds like ChatGPT/AI slop", or asks for human-sounding posts and no more specific idiolect skill has already…
Skill Claude CodeCodex
Build and maintain the user's OWN voice profile from continuously captured writing plus explicit samples — status, build/refresh, add samples, capture on/off. Use when the user wants posts in their own voice, wants to see what's been learned about their style, or wants to manage capture.
Skill Claude CodeCodex
Create a new voice profile — from a writing corpus (measured, not vibed), or invented to fill a gap in the roster. Extends the roster beyond the 60+ built-ins. Use when the user wants a new/custom voice, a voice "like these samples", or a voice the roster lacks.
Skill Claude CodeCodex
Write a social post in one of the roster's voices (or the user's own self voice) — platform-native, craft-floored, scanner-verified. Use when the user wants a post, caption, announcement, reply, or any short-form text written as a distinct human voice.
Plugin Claude Code
Playbook for omni-platform agent plugins — one repo, one core, native installs everywhere.
Plugin Claude Code
The omni-platform plugin playbook, installable: gives your agent the doctrine, checklists, and per-platform crib sheets for building and porting plugins that run on Claude Code, Codex, OpenCode, Hermes, Antigravity, and more.
Instructions file
Instructions for nagisanzenin/omniplugin, covering omniplugin — agent instructions, route by task, non-negotiables when applying this playbook and maintaining this playbook.
Skill Claude CodeCodex
Playbook for building and maintaining omni-platform agent plugins (one repo, native installs on Claude Code, Codex, OpenCode, Hermes, Antigravity, Gemini CLI, and more). Use when creating a plugin meant for more than one platform, porting an existing plugin to a new agentic platform, reviewing a platform-port PR…
nagisanzenin/claude-code-skill-maker-plugin
Plugin Claude Code
Creates new Claude Code skills and plugins end-to-end: interviews on the idea, writes SKILL.md, packages as plugin, creates GitHub repo, and adds to your marketplace.
nagisanzenin/claude-code-skill-maker-plugin
Skill Claude CodeCodex
Use when user wants to create a new skill, plugin, or Claude Code extension. Triggers on "make a skill", "create a plugin", "new skill for", "build a skill", "I need a skill that", or when discussing reusable workflows that should be packaged as skills.