patina
01Plugin Claude Code
patina — a deterministic, auditable AI-writing humanizer for Korean, English, Chinese, and Japanese.
Plugin Claude Code
patina — a deterministic, auditable AI-writing humanizer for Korean, English, Chinese, and Japanese.
Plugin Claude Code
Detect and rewrite AI writing patterns in Korean, English, Chinese, and Japanese so text reads as if a human wrote it. Meaning-preservation (MPS) verified, audit-friendly. The root SKILL.md is loaded as the /patina skill.
Skill Claude CodeCodex
Detect and rewrite AI writing patterns in Korean, English, Chinese, and Japanese text so it reads as if a human wrote it. Meaning-preservation (MPS) verified.
Agent
Triggers when Claude needs to find AI-writing patterns or suspect zones in KO/EN/ZH/JA text. Use this agent to run a full detection pass — pattern scanning across all applicable packs, stylometric analysis (burstiness CV + MATTR + AI-lexicon density), and Korean diagnostic signals — and receive a structured…
Agent
Triggers to audit whether a patina rewrite preserved meaning versus the original text. Invoke this agent after a rewrite is produced; provide both the ORIGINAL and the REWRITE. It checks all four fidelity criteria from core/scoring.md §§9-14 (claims, fabrication, audience/register, length) and returns a…
Agent
Triggers to re-scan a patina rewrite for residual AI tells and over-editing risk. Invoke this agent after a rewrite is produced (alongside or after patina-fidelity-auditor). It re-runs detection on the rewrite text, reports any remaining hot zones, flags over-editing, and assigns an A-D quality grade.
Plugin Claude Code
Plugin marketplace listing 1 plugin: oh-my-gajae-code.
Instructions file CodexOpenCode
Instructions for devswha/oh-my-gajae-code, covering agents.md — working in oh-my-gajae-code, v0.28.0 identity cutover and migration, what this repo is, setup / environment and gjc.
Skill Claude CodeCodex
A response-adjustment rule that changes explanation depth and format only when a specific approval-gate command is requested. It uses evidence from the current conversation to account for the reader’s role and familiarity.
Skill Claude CodeCodex
A guided, read-only process for understanding an unfamiliar code repository when its documentation or structure is unclear. It produces a project map, proposed architecture decisions, and a handoff document after confirmation.
Skill Claude CodeCodex
Activate only when the user explicitly invokes /omg:multi-harness or explicitly names the multi-harness-research skill. It sends one confirmed read-only research task directly to four fixed harnesses; ordinary research, review, comparison, or model-delegation requests never auto-activate it.
Skill Claude CodeCodex
Activate only when the user explicitly invokes /omg:ouroboros-setup. Ordinary planning, interviewing, specification, update, or implementation language never activates this external Ouroboros integration.
Skill Claude CodeCodex
A manually activated setup for merging named model presets into an agent configuration file. It provides separate presets for interactive and unattended sessions.
Plugin Claude Code
Starter template plugin for oh-my-gajae-code. Ships one slash command and one skill so you can see the full structure before authoring your own.
Command
Summarize staged git changes into a concise changelog/commit message.
Skill Claude CodeCodex
Template skill shipped by the example-plugin oh-my-gajae-code plugin. Use when you want a worked reference for how an oh-my-gajae-code plugin packages a skill. Replace this body with your own workflow before publishing.
Plugin Claude Code
oh-my-gajae-code — focused Gajae Code suite with 5 skills and 5 commands. Skills: no-english, extragoal, insane-review, insane-search, gpt-image. Commands: /omg, /omg:setup, /omg:no-english, /omg:insane-review, /omg:gpt-image.
Skill Claude CodeCodex
A final review process that sends a completed code change to an independent reviewer before it is merged. The reviewer sees the finished changes and supporting requirements, but not the author's working conversation.
Skill Claude CodeCodex
/omg:gpt-image explicit-only ChatGPT Images generation. Activate only when that command loads this skill; never activate from ordinary image, drawing, or design requests.
Skill Claude CodeCodex
A code-review skill that sends carefully selected repository code to a subscribed ChatGPT Pro web session for a second opinion. It uses a local browser-automation process to collect the relevant files and retrieve the review.
Skill Claude CodeCodex
Fetch and extract public web content when ordinary read/web access is blocked, incomplete, or challenged. Activate only after a URL read returns 402/403/WAF/challenge/thin SPA content. The only direct exception is an explicit public caption/media extraction request whose official route requires yt-dlp or a public…
Skill Claude CodeCodex
A Korean-language writing rule that reduces unnecessary English mixing and literal translations. It keeps code identifiers, commands, filenames, API names, and other exact technical labels unchanged.