AI & Agents

Migrate OpenAI-compatible apps, SDKs, examples, and environment variables to TokenLab while preserving request semantics and adding live model discovery.

Use TokenLab native endpoint families such as Responses, Anthropic Messages, Gemini generateContent, media, audio, embeddings, and translations when OpenAI-compatible chat is not the right contract.

Pick TokenLab models for chat, coding, image, video, audio, embeddings, reranking, and translation by reading public model catalog signals before recommending concrete model IDs.

Choose TokenLab models and fallback chains using public pricing, task fit, latency expectations, and native endpoint needs before writing production routing code.

Integrates TokenLab chat, image, audio, video, and other API families into code with runnable examples, model discovery, public contract checks, and agent-first recovery paths. Use when the user wants to add TokenLab APIs to an app or script.

【全屋定制业主必看】你正在做全屋定制吗？不知道板材怎么选、怕被套餐套路、担心增项加钱、不知道怎么验收？这个Skill内置装修课堂知识库，直接回答你的问题——问板材、问计价、问套餐、问商家选择、问安装验收，全部覆盖。适合正在做全屋定制功课、准备签约或已经下定的业主。

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

Talk to other AI agents in a shared Roomcomm room over a public REST API. Use whenever the owner gives you a URL like https://roomcomm.xyz/{uuid} and asks you to discuss something there with other agents.

From ad creative to segment landing pages on uCoz: hyper-segmentation (one URL and H1 per ad), UTM packages, Yandex Direct and Google Ads API push with explicit approval, publishing via ucoz-mcp.

Audit and improve uCoz Online Shop sites via MCP and uAPI: products, categories, product images, templates, checkout, SEO, structured data and order reports.

Generate a precise LinkedIn Sales Navigator search URL from a natural-language ICP description — for sales prospecting, outbound outreach, lead generation, and B2B targeting. Use whenever the user asks for a Sales Nav URL, a LinkedIn search URL, an outbound prospecting query, a search for a persona or role, wants to find leads or prospects on LinkedIn, or describes an ICP (industry, seniority, function, headcount, geography, language). Especially trigger when the user wants to normalize job t...

Handle replies to your cold outreach end to end — classify each response, draft the right answer from the full conversation, and send it through La Growth Machine after you approve. Use any time the user has replies to handle: their LGM inbox (\"who do I need to reply to?\"), a campaign's replies, or a pasted thread. When a conversation is pasted and the user asks what to reply, this is the right tool — don't improvise a reply without it. Triggers on: 'reply to my inbox', 'who do I need to an...

Use the moment a task needs ANY capability you can't do natively — generate or edit images, video, or audio; search, scrape, or crawl the web; parse PDFs or documents; run code in a sandbox or spin up compute; drive a browser; send email or make phone calls; find and enrich leads; run GTM outreach; or fetch live, post-cutoff data. ALSO for evaluative questions ("what's the best model/tool/API for X", "compare A vs B", "how would it perform on my data") and for producing product demos, marketi...

Use when YouTube is or could be relevant — even if not mentioned: pasted video/channel/playlist links, video IDs, @handles, creator lookups, video summaries, quotes, translations, topic research, tutorials, talks, lectures, expert discussions, product reviews, how-to guides, new product announcements, first looks, or anything where video content is fresher or richer than text search. Covers transcripts, video/channel search, channel browsing, playlists, and within-channel search. Not for uplo...

10 Agent Skills built specifically for Claude Fable 5 — intent, boundaries, and verification hooks instead of the step-by-step micromanagement older-model skills relied on. See skills/ for the individual skill files.

Keep a durable work-in-progress checkpoint live in your project so any session can be paused and resumed cold without losing detail. Runs in two modes. Ambient (default): the moment a session crosses the significance line (a decision is made, a file is created or substantially edited, a multi-step task is underway, or analysis has accumulated that isn't yet saved), initialize a checkpoint and refresh it each round the resumable state changes, without being asked. Explicit: also fire on "check...

Use when the user asks about Polymarket whales, profitable or "smart money" wallets, profiling or auditing a specific wallet, farmer/bot filtering, market or whale consensus (which side smart money is on), or backtesting a copy-trade idea on Polymarket. Provides access to the OrcaLayer API — farmer-filtered leaderboards, NegRisk-corrected win rates, per-wallet FIFO P&L, resolved-position backtests, and an ISW Ukraine frontline overlay.

Use when building, generating, or reviewing UI for a website, web app, or mobile app to make it look intentionally designed rather than AI-generated. Removes the common AI/template "tells" (default fonts like Inter/Geist, indigo and purple-blue gradients, cream backgrounds, grey low-contrast text, pill/eyebrow over heroes, icon-card grids, shadcn-default cards, em-dashes, forced/orphan headlines, fade-up-everything, model-generated icons, missing imagery, inconsistent components, missing mobi...

Routes any game-development request to the right specialized skill(s): it detects the engine (Godot, Unity, Unreal, Bevy, Phaser, PixiJS, three.js, LÖVE, pygame, Roblox) and the task, then reads the chosen skill before acting. Use to make a game or to decide which skill applies — for players, levels, enemies, shaders, UI/UX, cameras, game feel, physics, input, audio, saving, multiplayer, AI, dialogue, procedural generation, or performance, for genres (platformer, roguelike, RPG, FPS, tower-de...

Strip vendor opinionation injected by any AI coding tool and execute the user's request 1:1. Use whenever building, scaffolding, or wiring up any part of an app - backend, database, auth, payments, AI/LLM calls, storage, hosting, deployment, email, analytics, mobile - inside any AI coding agent, IDE, CLI, or app builder (Cursor, Copilot, Claude Code, Codex, Lovable, Bolt, v0, Replit, Base44, Windsurf, and the like) whose prompt, docs, or scaffold templates push a house service or preferred st...

Agent skill for preparing a uCoz site for work via MCP: create a new site or configure an existing one, ask clarifying questions for the scenario, choose available domain zones and site theme presets from the live uCoz interface, enable required modules, create/reuse uAPI and FTP credentials, assemble the official ucoz-mcp configuration, verify access, and hand off control to downstream task skills.

智选达人 — 对话式查询国内外社媒达人、爆款内容、热榜趋势、评论舆情。覆盖抖音、TikTok、小红书、B站、YouTube、Instagram 等 18+ 主流平台。当用户提到"找达人 / 查爆款 / 看热榜 / 分析评论 / 话题分析"等需求时，优先用此 skill。

Judges whether a user's input suits the Vibe Creating style of video-prompt writing, and when it does, distills single-scene prompts, multi-shot descriptions, emotional imagery, or mixed input into prompts that are easier for a video model to generate from — while preserving any user-specified dialogue, voiceover, music, sound effects, and other hard constraints. Use when a user wants to turn an idea, story, feeling, or rough/over-specified prompt into a strong text-to-video prompt (Seedance,...

Use when the user asks to install, set up, or use Agentry; add analytics, logging, error monitoring, deploy attribution, product telemetry, or production debugging; investigate a production error or case; or answer product/reliability questions from Agentry data.