AI & ML

justcyl Bundle

Generate/edit images with Gemini image models (default: gemini-3.1-flash-image-preview). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image. Use --model to select a different model.

justcyl Bundle

Visual QA sub-agent for AI-generated images. Spawns a dedicated pi sub-agent via herdr to evaluate image quality, content fidelity, and scene-specific criteria (academic / slides / general). Returns structured pass/fail report with regeneration guidance. Use when you need programmatic visual QA on a generated figure, diagram, or slide.

justcyl Bundle

先澄清目标与约束，再把需求拆成按依赖层次排序的可执行任务并输出 tasks.json；只做规划不做实现。

justcyl Bundle

Generate/edit images with Gemini image models (default: gemini-3.1-flash-image-preview). Use for any image create/modify request. Supports text-to-image + image-to-image editing; 1K/2K/4K resolution; base-url gateways and provider fallback (gemini-native/openai-chat-compat). Use --model to select a different model.

justcyl Skill

通过 A/B 双 agent 对话式渐进披露深度解读 arXiv 论文。A 持有全文、给出结构化摘要，B 模拟未读原文的好奇读者、循环追问；用对话桥接作者意图与读者理解的 gap。适用于 '帮我深度读这篇论文'、'对话式阅读 arxiv:xxxx'、'dialog paper reading'、'渐进式论文解读' 等场景。

cold-iq Skill

Adversarially reviews whatever you bring it — prompts, strategies, plans, arguments, decisions, or workflows — and returns a structured, honest critique with scored dimensions and specific improvements. Combines a full prompt health check rubric with devil's advocate challenge modes for ideas, strategies, and decisions. Trigger this skill when the user says: "devil's advocate", "challenge this", "stress test", "poke holes in", "critique this", "what's wrong with", "find the flaws", "red team this", "what am I missing", "steelman the opposition", "evaluate my prompt", "review my prompt", "prompt health check", "rate my prompt", "is this a good prompt", "how can I improve this prompt", "evaluate this plan", "what could go wrong", "pre-mortem", "pressure test", "tear this apart", or any request to find weaknesses, gaps, or blind spots in something the user has shared. Also trigger when the user pastes a prompt, plan, strategy, or argument and asks for feedback — even without using these exact words.

calven-ai Skill

Connect a tool the team uses by the MCP, CLI, script ladder in integrations/adding-an-integration.md, as one reviewable PR. Use when "we use X, connect it", "automate pulling Y", or when a skill needs an unwired tool.

calven-ai Bundle

Compute share of voice in AI answers versus competitors across the prompt set and over time. Use when "AI share of voice", "are we gaining in ChatGPT", after brand-monitor runs.

nroze22 Skill

Process meeting notes and transcripts. Extract action items with owners and due dates, create Jira tickets from action items, and generate meeting summaries for distribution.

nroze22 Skill

Build professional proposals for Talosix EDC and clinical trial software deals including executive summary, solution overview, pricing, implementation timeline, support model, and ROI projections.

nroze22 Skill

Generates detailed user flow diagrams in Mermaid syntax from Jira stories or written requirements. Pulls story details via Atlassian MCP, identifies happy paths, error paths, decision points, and system actions. Specializes in clinical trial EDC workflows including enrollment, CRF data entry, query lifecycle, e-signature, and SAE reporting flows.

nroze22 Skill

Transform any content into platform-optimized social media posts for LinkedIn, Twitter/X with A/B variants, clinical trial hashtag strategy, engagement predictions, and optimal posting schedules for clinical operations audiences.

nroze22 Skill

Generate Playwright automated test scripts for the Talosix EDC platform. Uses Page Object Model, data-testid selectors, and covers clinical trial UI patterns including forms, validation, and e-signatures.

gabrielmoreira Skill

Professional finance research toolkit — backtesting (9 engines + benchmark comparison panel), factor analysis, Alpha Zoo (462 pre-built alphas across qlib158/alpha101/gtja191/academic/fundamental), options pricing, 89 finance skills, 30 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest → render) across 25 market-data sources (tushare, yfinance, okx, binance, akshare, baostock, tencent, mootdx, ccxt, futu, mt5, tickerall, local, eastmoney, sina, stooq, yahoo, pykrx, india_broker, qveris, longbridge, plus optional-key finnhub/alphavantage/tiingo/fmp).

gabrielmoreira Skill

Inspect and optionally adjust the agent's runtime state. Use to check the current model or preset, context window, iteration progress and limits, token usage, workspace and tool configuration, subagent status, and request routing metadata such as channel, chat ID, and sender ID; diagnose unavailable capabilities; change allowed runtime settings; or store temporary session scratchpad values.

gabrielmoreira Bundle

Detect splice donor and acceptor sites in DNA sequences using the Genomic Intelligence G0 BigBird transformer, via the hosted /v1/tasks/splice/predict API. Returns per-position site probabilities and called sites.

gabrielmoreira Bundle

Manage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Cursor, and OpenCode engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel code review, autoloop autonomous workspace iteration, ultraapp building deployable web apps from a structured Q&A interview, switching models/tools at runtime, exposing the orchestrator's 69 tools as an MCP server to Hermes Agent / Claude Desktop / Cursor / Cline / Continue / Zed / Windsurf / Goose, or running as an Agent Client Protocol (ACP) agent that Zed / JetBrains / Neovim / Emacs / VS Code / dsh can drive directly. Triggers on "start a session", "send to session", "run council", "ultraplan", "ultrareview", "autoloop", "ultraapp", "Forge tab", "build a web app", "one-click app", "AppSpec", "autonomous iteration", "iterate until goal", "deep paper review", "auto research", "switch model", "multi-ag

gabrielmoreira Bundle

Predict enhancer activity in DNA sequences using the Genomic Intelligence G0 DeepSTARR model, via the hosted /v1/tasks/enhancer/predict API. Returns per-window activity scores.

gabrielmoreira Bundle

Detect promoter regions in DNA sequences using the Genomic Intelligence G0 transformer (GENA-LM BERT Large), via the hosted /v1/tasks/promoter/predict API. Returns per-window promoter probabilities and called regions.

gabrielmoreira Bundle

Run ComfyUI workflows from any AI agent (Claude Code, OpenClaw, Codex, Hermes) via a single CLI. Import workflows, manage dependencies, execute across multiple servers, and track history — all through shell commands. **Use this Skill when:** (1) The user requests to "generate an image", "draw a picture", or "execute a ComfyUI workflow". (2) The user has specific stylistic, character, or scene requirements for image generation. (3) The user asks you to import, register, sync, or configure saved ComfyUI workflows for later reuse.

gabrielmoreira Skill

The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture. Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base, or needs guidance on the three-layer architecture (raw sources → wiki → schema). Also use when discussing knowledge management strategy, wiki structure decisions, or how to organize distilled knowledge. This is the "theory" skill — other skills handle specific operations (ingesting, querying, linting).

gabrielmoreira Bundle

Predict tissue / cell-type expression (log TPM + TPM) from a 9,198 bp TSS-centered DNA sequence using the Genomic Intelligence G0 Expression model, via the hosted /v1/tasks/expression/predict API. The model is conditioned on a free-text cell-type / assay description.

francostino Skill

Compiled CLI covering all 52 endpoints of the Anytype local API — objects, properties, tags, search, chat, files — one binary, no MCP server needed.

b-open-io Skill

Use BSV MCP to inspect Bitcoin SV transactions, addresses, ordinals, and service availability, or help connect a wallet and request paid services.

clawd-maf Bundle

CAD Agent

davad00 Bundle

Sefaria API MCP

davidmosiah Skill

YouTube Shorts Agent. Prefer MCP tools if connected; otherwise the package CLI.

davidmosiah-tiktok-agent-publisher Skill

TikTok Agent Publisher. Prefer MCP tools if connected; otherwise the package CLI.

davidmosiah-short-video-agent-kit Skill

Short Video Agent Kit. Prefer MCP tools if connected; otherwise the package CLI.

davidmosiah-google-ads-intent-mcp Skill

Google Ads Intent MCP. Prefer MCP tools if connected; otherwise the package CLI.

0xtommythomas-dev Bundle

SoulFlow v2.0 - Multi-Agent Workflow Orchestrator

adjia Bundle

Mail MCP Skill

andyshaman Skill

Tech-lead orchestration for a session on your top-tier model: the lead keeps decomposition, architecture and final synthesis, and routes implementation, mechanical work and long investigations to cheaper subagents. Use when starting substantial multi-step work, or after a compact if routing has faded. Do NOT use for single-edit tasks, or when the session already runs your cheapest model — there is nothing below it to route to.

labring Bundle

为 agent-sandbox-adaptor 项目添加新的沙盒提供商适配器。当用户想要添加新的沙盒提供商支持、提到添加适配器、或提供沙盒服务文档时使用此技能。触发短语包括"添加 X 适配器"、"集成 X 沙盒"、"支持 X 提供商"，或当用户分享沙盒服务的 API 文档时。

labring Bundle

指导 Codex 或开发者从零准备环境并开发 FastGPT 官方插件。Use when the user asks to set up, fork, clone, install dependencies, create, scaffold, implement, test, build, check, or package a FastGPT plugin/tool/tool-suite in labring/fastgpt-official-plugins, especially under packages/tools, and when an agent may only have this raw SKILL.md text as onboarding context.

landing-ai Bundle

Parses documents into structured Markdown, extracts fields with JSON schemas, classifies pages, and splits mixed document batches using LandingAI's Agentic Document Extraction (ADE) REST APIs, with official Python and TypeScript libraries. Builds document pipelines: batch and async processing for large files, classify-then-extract routing, RAG chunking and embeddings, multi-page table stitching, bounding box visualization, cropping, word-level highlighting, and grounding extracted fields to their source citations. Use when processing PDFs, images, scans, Office documents (Word, PowerPoint), invoices, forms, or bank statements, when migrating between ADE API versions, or when the user mentions ADE, parsing, extraction, classification, document splitting, table of contents generation, grounding, bounding boxes, blocks, chunks, ranges, citations, or word confidence scores.