潜力新星（90天）

Tiny local text-to-24x24 pixel art model, trained on roughly 200K samples in 30 minutes on an RTX 5090.

A tiny, vendor-neutral LLM client library — one interface (LLMClient) with pluggable adapters for OpenAI, AWS Bedrock and Google Gemini, or bring your own backend.

Make Claude Opus, Sonnet, GPT, or Gemini produce work close to what Claude Fable 5 would ship. 21 craft standards written and audited by the frontier model itself; single-response lift, or a full convergence loop with a taste gate.

Open agentic prompt-expansion harness for image and video generation, bridging polished demos, public APIs, and deployable workflows.

A native iOS app for re-shooting regular photos from different angles.

Governed, provenance-sealed creative rendering for Databricks — a Streamlit App + Unity Catalog ai_render() function that turns any governed source (Sample Lakehouse, UC, Genie, or BYO data) into infographics, reports, decks, video briefings, music, and podcasts.

AI visual director for turning personal photos into structured, editable visual narratives.

Transparent proxy for Claude Code that auto-routes image-bearing requests to a multimodal model — so a non-multimodal primary model never crashes your long-running sessions.

Agent Skill that silently refines prompts for the currently running model

Battle-tested model-dispatch doctrine for Claude Code — portable ops rules that let Sonnet/Haiku reliably run projects. Iterated in real deployments, not one-shot generated.

东方文化编辑海报 v2 Codex skill：Image 2 出图、中文标题精炼、真实文化物证、A/B/C 三联测试

19 套可直接生图的视觉风格 Skills，为 gpt-image-2 编写。把文章、主题、产品或已有视觉资产编译成完整提示词。/ 19 visual-style prompt skills for gpt-image-2.

The vision plugin for OpenCode that truly understands images. Inspect, read, and reason about any screenshot or picture with deeper understanding than any other plugin — fully local, private, and free.

`xxg-portrait-rebuild-light` is an image-edit skill for existing portrait photos. It reconstructs the key light, fill, shadows, and background atmosphere with a director-led lighting workflow while restoring clean, healthy, low-contrast photographic skin microtexture.

Distill teacher chains-of-thought into a LoRA adapter via a strict boxed-answer format contract + two-phase Train→Nudge (silver-medal NVIDIA Nemotron reasoning recipe, as a tested library).

The htop for LLM inference see exactly where every GB of VRAM goes and get measured quantization savings.

A WebRTC-native, audio-first conversational-AI framework for Go.

An evidence-led, eight-locale LLM playbook: a transferable core, the Codex flagship track, and adapters for ChatGPT, Claude Code, Gemini, DeepSeek, and Grok.

Turn raw footage into brand-ready, platform-optimized video with one command. Local-first: FFmpeg + WhisperX/MLX + Ollama.

Free open source disk cleaner for developers. Clean Hugging Face, Ollama, npm, pip, conda, Docker caches, app leftovers, and junk files on macOS and Windows. Built with Tauri.