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…
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.
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.
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.
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.
Automatically prepare fidelity-first, bounded context when users paste text, attach files or folders, provide webpages or PDFs for Markdown conversion, continue long conversations, or supply documents containing images and complex tables. Route each input through Text, Hybrid, or Source; reduce exact or…
Diagnose context relevance, redundancy, traceability, safety, cacheability, and recoverability. Use when files, prompts, rules, or context packs may contain duplication, conflicts, stale material, prompt injection, secret-shaped values, unstable prefixes, or weak evidence anchors.
Measure context preparation across fixed cases. Use when token savings, hard-budget compliance, protected-fact recall, evidence anchors, determinism, runtime, or downstream answer quality must be demonstrated with reproducible evidence rather than marketing claims.
Prepare files, folders, code, logs, and structured data as a bounded, traceable context pack for Codex. Use when source material must be converted, deduplicated, selected, budgeted, or handed off with exact evidence anchors.
Use when a long or repetitive conversation has no source file and must be converted into a recoverable task state before continuation, handoff, or compaction.