jeo-skills

Assist with Colibri: pure-C LLM inference engine for running GLM-5.2 (744B MoE) on consumer machines with ~25 GB RAM. Use when setting up, building, converting models, running inference, configuring expert streaming and caching, optimizing speculative decoding (MTP), GPU integration, and integrating Colibri into production pipelines. Includes build setup, model download & conversion, chat/inference modes, performance tuning, and API integration patterns.

Discover and apply curated prompts from the prompts.chat collection to optimize AI interactions. Use when refining prompt engineering, finding domain-specific prompt templates, improving response quality, or building prompt-based workflows. Triggers on: prompt optimization, prompt templates, prompt engineering, prompt library, curated prompts, prompt discovery, and AI prompt patterns.

Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage", a narrated explainer or short ad built from AI-generated collage posters, a scrapbook-style tribute, or wants to turn a topic / product / person into a punchy narrated collage video — even if they don't say the word "Vox". Also use when reproducing Stav Zilber / rom1trs / Higgsfield-style collage ad workflows, or when the user asks for a motion collage or a scrapbook-style tribute. Triggers: "vox video", "collage video", "motion collage", "paper collage explainer", "make a collage ad", "turn this topic into a collage video".

Assist with Motion Previs Studio v4: a cross-platform desktop app for AI-film previsualization. Use when setting up, configuring, troubleshooting, or extending motion-previs-studio for pose extraction, depth mapping, camera motion solving, control layer export, and bundle production for AI-video workflows (Seedance, ComfyUI, Blender, Runway, Kling). Includes build setup, feature integration, UI/logic debugging, and export pipeline optimization.

Work with Lapian Notes / 拉片笔记 (github.com/bkingfilm/lapian-notes) — a local- first React/Vite tool that turns a film into an editable shot-by-shot study notebook: local frame extraction, AI-assisted structure analysis (bring your own AI, no API key required), story-line swimlane timeline, structure tree, and audience-emotion curve. Use when the user asks about Lapian Notes, "拉片笔记", "拉片" (shot-by-shot film analysis) tooling, cloning/running this repo (npm run dev, run.bat/run.command), the AI-analysis-package (ZIP) round-trip workflow, or contributing a PR to lapian-notes. Not for generic video editing (use `opencut` for that) or generic film-analysis theory unrelated to this codebase.

Set up, run, and contribute to TokHub (github.com/yaojingang/TokHub) — an open-source AI API relay monitoring, recommendation, and OpenAI-compatible gateway system with L1/L2/L3 channel health probing, usage metering, alerts, audit, and Docker self-hosting. Use when the user asks about TokHub, "AI API 中转站监控", cloning/running the Go + React monorepo (TOKHUB_ROLE, sqlc, TimescaleDB, NATS), the L1/L2/L3 probe algorithm, the OpenAI-compatible `/gateway/v1/*` endpoint, or contributing a PR to TokHub. Do not use for connecting a running agent to a live TokHub instance's own API (that is covered by the project's own bundled `agent-skills/tokhub` skill inside the TokHub repo, not this one).

Build fully customizable, agent-ready design systems with Astryx — Meta's production design system now open source. Ships 150+ React components built on StyleX with zero styling lock-in, component swizzling, brand theming, dark mode, and CLI tooling. Use when building component libraries, design systems, UI applications, design tokens, or when teams need consistent accessible components that AI agents can understand and extend. Triggers on: astryx, design system, component library, design tokens, react components, accessible components, astryx design, stylesheets, theme customization, component composition.

Work with the OpenCut open-source video editor repo (github.com/OpenCut-app/OpenCut) — clone/setup, run the web/desktop dev servers, understand the Rust/WASM compositor core, and follow current contribution focus areas. Use when the user asks about OpenCut, the "open-source CapCut alternative", opencut-classic, setting up the OpenCut monorepo (moon/proto or Bun/Docker), the OpenCut Rust core, or contributing a PR to OpenCut. Also triggers on "opencut.app", "new.opencut.app", and "opencut-app/opencut-classic".

Lazyweb is the design-evidence skill for AI coding agents. Use it when designing, critiquing, or changing product UI — it provides real app screenshots, competitor references, best practices, quick examples, creative cross-category ideas, paywall optimization guidance, and mobile growth + monetization A/B test context. Routes to the right Lazyweb mode (design workflow, quick search, update, flowchart, or A/B test research) using MCP tools and the Lazyweb server at https://www.lazyweb.com/mcp. Use before designing any screen when you need design evidence instead of training-data vibes.

Route web-scraping work into the lightest workable Scrapling mode instead of defaulting to a browser. Use when the user needs HTML extraction, JS-rendered page retrieval, protected-target escalation, quick CLI scraping, agent-facing MCP access, or a larger crawl with Scrapling spiders. Triggers on: scrapling, scrape website, crawl site, adaptive scraping, selector drift, stealthy fetch, browser scraping, scrape to markdown, scrapling mcp, scrapling spider, research harvesting, literature scraping, paper metadata.

A comprehensive reference of benchmarks for evaluating large language models on scientific reasoning and discovery.

Turn a weak/cheap "Flash" model into a "Pro" performer by wrapping HKUDS UpSkill — captures agent session failures, has a strong Teacher model analyze them and draft a skill, then validates it against the weak Student model in a closed Ralph Loop (up to 3 rounds) before storing it for automatic reuse. Use when the user wants to install UpSkill, run `/upskill-init`, `/upskill-configure`, `/upskill-build`, `/upskill-run`, `/upskill-list`, `/upskill-status`, `/upskill-mode`, `/upskill-model`, `/upskill-remove`, or `/upskill-uninstall`, wants a cheap model to perform closer to a Pro model without switching, or wants a good session (success or failure) distilled into a validated skill. Triggers on: upskill, up-skill, flash to pro, teacher student distillation, ralph loop skill validation, distill agent failures into skills. Routes skill-quality ratcheting to `skill-autoresearch`, scaffolding to `write-a-skill`, and spec-compliance rewrites to `skill-standardization`.

Run the Ouroboros specification-first development loop: reduce ambiguity with a Socratic interview grounded in live git data (commits, churn, contributors), freeze an immutable seed/spec, render the execution plan through spec-kit (/speckit.plan → /speckit.tasks), execute against that contract through cli-anything agent-native CLI harnesses (cli-hub, --json evidence), verify before claiming success, and keep looping until completion is actually verified. Use when the user wants spec-first clarification, git-aware interviews, immutable requirements, drift-aware implementation, harness-driven execution, or a persistent completion loop that should keep going until tests / checks / acceptance criteria pass. Triggers on: ooo, ouroboros, interview, seed, run workflow, evaluate, evolve, ooo ralph, specification first, socratic interview, git-aware interview, ambiguity reduction, execution plan, cli harness execute, persistent completion.

Run AI-powered code review through Alibaba's open-code-review (`ocr`) CLI instead of hand-reviewing diffs. Use when the user asks to review code, review a PR/MR, review staged/unstaged/untracked changes, review a single commit, compare two branches, or scan whole files for bugs, security issues, performance problems, and quality concerns. Picks the lightest invocation (workspace review, branch range, single commit, or full-file scan), passes business context via `--background`, classifies findings by priority, and optionally applies fixes. Triggers on: open code review, ocr review, ocr scan, alibaba code review, ai code review cli, review my changes, review this pr, review this commit, review this branch, scan repository for issues.

Build and maintain a persistent markdown wiki that an LLM updates on the user's behalf, usually inside an Obsidian vault or git-tracked notes repo. Use when raw sources such as web articles, papers, meeting notes, transcripts, screenshots, or past analyses need to be turned into an interlinked knowledge base with immutable source files, LLM-written wiki pages, `index.md`, `log.md`, schema rules in `AGENTS.md` or `CLAUDE.md`, source summaries, query notes, and recurring lint passes. Triggers on: llm-wiki, personal wiki, obsidian wiki, research vault, knowledge base, source ingest, persistent notes, wiki maintenance, source summaries, query filing.

Run Heretic — a fully automatic directional-ablation ("abliteration") and LLM-interpretability toolkit that removes refusal/over-refusal behaviour from open-weight transformer models without post-training, and analyses the geometry of refusal directions. Use when the user wants to decensor / abliterate / un-refuse an open-weight model they have the right to modify, tune the ablation (KL-divergence target, trial budget, quantization), evaluate refusal-rate vs KL against the original, or do interpretability research (refusal-direction difference-of-means, residual geometry tables, PaCMAP residual plots). Packages p-e-w/heretic (AGPL-3.0). Triggers on: heretic, abliterate, abliteration, decensor / uncensor a model, remove refusals, refusal direction, directional ablation, residual geometry, plot residuals. Model discovery, harmful/harmless prompt datasets, and benchmark/prior-art research route web extraction through the `scrapling` skill. Simple "which uncensored model should I download" recommendations are ans

Route academic-figure work into the lightest workable PaperBanana mode instead of jumping straight to a full multi-agent generation run. Use when the user needs publication-quality methodology diagrams, statistical plots, figure evaluation, polishing an existing figure, batch/sweep generation, or a full-paper figure package from text or PDF. Even if the user does not say "paperbanana" — also triggers on: academic figure, methodology diagram, publication figure, generate diagram from paper, statistical plot from CSV, figure evaluation, polish figure, NeurIPS/ICML figure, arxiv illustration, plan-then-refine diagram pipeline.

Make the agent solve coding tasks with the least code that remains correct. Before writing code, walk the Ponytail ladder: skip what need not exist, then prefer stdlib, native platform features, already-installed dependencies, one line, and only then the minimum custom code. Use when the user asks for ponytail mode, less code, YAGNI, anti-bloat, minimal code, an over-engineering review, a current-diff delete-list, a whole-repo bloat audit, or a `ponytail:` tech-debt harvest. Keep validation, data-loss handling, security, and accessibility. Mark shortcuts with `ponytail:` plus the upgrade path. Triggers on: ponytail, /ponytail, /ponytail-review, /ponytail-audit, /ponytail-debt, write less code, YAGNI, over-engineering, anti-bloat, minimal code, do I need this, lazy dev.

AI 애니메이션 스프라이트 생성. 텍스트 설명 한 줄로 캐릭터 + 동작 애니메이션(걷기·달리기·공격·마법 등 100여 종) + 8방향 스프라이트 세트를 만들고, 게임 엔진용 번들(스프라이트시트 · manifest.json · Aseprite JSON · 상태별 GIF/APNG · 개별 프레임 PNG)로 내보냅니다. Use when the user wants to generate game sprites, character animations, sprite sheets, sprite atlases, or 8-direction sprite sets from a text description. Triggers on: perfectpixel, ppgen, sprite generation, character animation, sprite sheet, sprite atlas, 8-direction sprite, god-tibo-imagen sprite, gemini sprite.

Routing front door for a structured, human-in-the-loop deep-research workflow (Weizhena/Deep-Research-skills). Turns any topic into an extensible outline, fans out parallel web-search agents to investigate each item into validated JSON, then renders a complete markdown report. One skill, 4 reference pipelines: outline (research / add-items / add-fields), deep (parallel per-item investigation + field-coverage validation), report (TOC + per-field markdown), and web-search (the research agent with 5 routed source modules: github-debug, general-web, academic-papers, chinese-tech, stackoverflow). Classifies the request into a phase, loads that pipeline, and executes with its exact prompt templates and output contracts. Triggers on: deep research, structured research, research outline, research a topic, survey, benchmark review, literature review, competitor analysis, due diligence, technology comparison, build a research report, fan out research, parallel web search, /research, /research-deep, /research-report. In

Run an end-to-end webtoon production harness — a 27-agent / 4-phase Claude Code agent team that takes a single episode from trend research to a finished vertical-scroll viewer. Use when the user wants to produce a webtoon episode: research popular webtoon trends, write a dialogue-heavy, high-tension, twist-every-episode scenario, render character reference sheets first, render 50+ panels per episode with in-image speech-bubble (Korean dialogue) baking via codex-image, run a generation–validation loop, and assemble a vertical-scroll viewer. Triggers on: webtoon harness, make a webtoon, produce a webtoon episode, webtoon scenario to image, next episode, redraw panel, stronger twist, webtoon trend research. Web data gathering for the trend-research phase routes through the `scrapling` skill. Pure webtoon recommendation/critique is answered directly.

">"

">"

Use this skill when >

">"

">"

">"

">"

">"

">"

">"

">"

">"

">"

">"

">"

Use this skill when >

">"

Write and maintain release-history artifacts for shipped changes: `CHANGELOG.md` updates, release notes, migration/deprecation updates, and lightweight game patch notes. Use when the main job is turning shipped evidence into the smallest truthful release-writing packet for developers, customers, internal stakeholders, or players. Triggers on: changelog, release notes, patch notes, migration update, deprecation notice, version notes, what shipped, what changed, and what's new. Route internal specs/runbooks to `technical-writing`, API portals to `api-documentation`, end-user tutorials to `user-guide-writing`, rollout execution to `deployment-automation`, and launch messaging to `marketing-automation`.

">"