Explorar skills

This structured principal are three-phase agentic development pipeline for desktop software developers. Use this principe whenever a developer wants to build a new tool, utility, daemon, CLI app, or any desktop software project from scratch — or when they say things like "let's plan a program", "help me prototype", "scaffold a project", "convert my bash to Go/Rust/Python", or "I want to start buil

RateVC (查VC) — Rate any investor before you meet them. Michelin 3-star system on a 1-4 scale. Works for both Chinese and US investors. Trigger on: investor evaluation, VC background check, fundraising decisions, investor names, fund names, term sheets, FA recommendations, meeting decisions, 查VC, 投资人, 基金, 融资, 见投资人, 背调, 值不值得见, 靠不靠谱, 收到TS, FA推荐, 帮我查一下这个投资人, 这个基金怎么样, 要不要见这个投资人, rate this VC, check thi

Read, scrape, and analyze ANY listing from kleinanzeigen.de — cars, electronics, furniture, real estate, clothing, or any other category. Use this skill whenever the user shares a kleinanzeigen.de URL, asks to "check this listing", wants to compare multiple ads, needs to detect if a seller is a dealer or private person, wants to find duplicate listings, or asks "is this a good deal?" for any Germa

J.A.R.V.I.S. for your Claude Code project. On start — bootstrap with archetype classification, skill selection, wiki setup. For existing projects — soft adopt via gap analysis (installs only missing features, respects existing config). After start/adopt — quiet persistent assistant via hooks that maintains wiki, recommends model/plan-mode for tasks, surfaces existing solutions, tracks project evol

Build personal brands that convert customers, not just rack up views. Use this skill whenever the user wants to define, scale, or operationalize a personal brand or content operation — including brand positioning, content strategy, posting cadence, platform selection, storytelling, media team hiring, onboarding, 1:1 cadences, work-mode design, or trust-first monetization. Trigger on phrases like "

Write production-grade prompts for ComfyUI Cloud (cloud.comfy.org) and local ComfyUI blueprints. Provides MCSLA prompt structure (Model · Camera · Subject · Look · Action), cinematic vocabulary, model routing across BFL Flux, OpenAI DALL-E, Stability SD3, Ideogram, xAI Grok, ByteDance Seedance, Pika, Runway, Vidu, Recraft, Reve, Google nano-banana, plus the 60+ local blueprints in ~/ComfyUI/bluepr

Translate text and files between any languages using LLM APIs (OpenAI, Anthropic, Chinese LLMs, etc.). Use when users request translation tasks like "translate this to English", "翻译成中文", "batch translate these files", or "translate this Markdown file while preserving formatting". Supports direct API calls, config files, environment variables, and multiple translation scenarios (plain text, batch f

Audit any URL for on-page SEO issues. Returns a 0-100 score and a prioritized list of fixes covering meta tags, headings, images, links, technical SEO, social previews, and structured data. Use when a user asks to "check SEO", "audit a site", "score a webpage", or wants to improve search rankings.

Probability-based options income advisor. Morning strategic session + afternoon tactical session. Reads portfolio, checks VIX, reviews positions, suggests trades.

AI image generation and image editing via fangxinapi.com using gpt-image-2. Supports text-to-image, image-to-image, multi-image composite edits, masks, PNG/JPEG output, and quality/background controls. Use when the user wants to generate images, edit uploaded images, merge multiple reference photos, or create illustrations. Triggered by phrases like "画一张", "生成图片", "改图", "合成照片", "draw", "generate i

召集多位历史/思想人物的AI分身开圆桌会议，围绕用户议题展开真实多轮讨论，最终给出整合方案。 通过子代理真实调用各人物的 perspective skill，产生有实质交锋的对话。 核心机制：动态人物发现→议题解构→锁定发言→对抗交锋→整合方案。 触发词：「圆桌」「召集讨论」「多角度分析」「roundtable」「让他们讨论」「开个会」。

Reference library of 2,269 real-world Seedance 2.0 video-generation prompts with structural patterns and authored exemplars. Use this skill whenever the user mentions Seedance, drafts a video prompt, asks for an image-to-video (i2v) or text-to-video (t2v) prompt, plans a multi-shot AI video brief, or asks for help structuring a video generation prompt — even if they don't say "Seedance" by name. P