TIKAZ AI Skills for Codex — seven composable, evidence-first workflow suites
Skill Codex
Read one or many public-platform or local videos through a portable evidence workflow using available metadata, subtitles, timestamped speech recognition, keyframes, and official-source verification. Use for video summaries, knowledge extraction, comparisons, tutorials, and auditable claims across Bilibili, YouTube…
Skill Codex
Orchestrate article illustration, logistics explainers, writing cleanup, and lawful music discovery with explicit style routing, asset provenance, accessibility text, and visual QA. Use for content packages that need coherent visuals without generic image generation.
Skill Codex
Remove AI filler, vague claims, repetitive structure, inflated transitions, and low-information phrasing while preserving meaning and voice. Use when writing sounds generic, padded, templated, or difficult to trust.
Skill Codex
A music-finding skill for locating downloadable tracks from public-domain, Creative Commons, artist-approved, Bandcamp, and Internet Archive sources.
Skill Codex
Art-direct concise hand-drawn Chinese article illustrations from an article thesis using a small dark character, white space, sparse color annotations, visual metaphor, shot cards, and publishing-size QA. Use for conceptual article images, workflow metaphors, knowledge posts, and explanatory editorial illustrations.
Skill Codex
Art-direct 16:9 Chinese logistics explainers with aligned process structures, short labels, restrained teal-green emphasis, a small guide character, source-aware claims, and publishing-size QA. Use for logistics education, supply-chain workflows, risk checks, comparisons, and operational knowledge cards.
Skill Codex
Use deployed local conversion, OCR, audio/video, visual, retrieval, reranking, and guarded compression to build high-fidelity bounded Codex context. Use only for a valid uppercase ON prefix or explicit invocation.
Skill Codex
Route long text, files, webpages, code, tables, images, audio, video, or long conversations between default Context Economy and explicit ON-triggered Context On-Premise while keeping one evidence and cost contract.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: