AI & ML

nvidia Bundle

Multi-period supply chain planning model: data files, BOM structure, variable/constraint reference for the max-supply base model.

nvidia Skill

Map interpreted optimization problems into cuOpt-native models for the fast path with minimal clarifying questions.

nvidia Skill

Choose fast direct-to-cuOpt solve versus replayable or auditable model artifact mode.

microsoft Skill

Launch and automate VS Code Insiders with the Copilot Chat extension using agent-browser via Chrome DevTools Protocol. Use when you need to interact with the VS Code UI, automate the chat panel, test the extension UI, or take screenshots. Triggers include 'automate VS Code', 'interact with chat', 'test the UI', 'take a screenshot', 'launch with debugging'.

microsoft Skill

Use this agent when the user needs to upgrade Anthropic SDK packages. This includes: upgrading @anthropic-ai/sdk or @anthropic-ai/claude-agent-sdk to newer versions, migrating between SDK versions, resolving SDK-related dependency conflicts, updating SDK types and interfaces, or asking about SDK upgrade procedures. Examples: 'Upgrade the Anthropic SDK to the latest version', 'Help me migrate to the latest claude-agent-sdk', 'What's the process for upgrading Anthropic packages?'

microsoft Bundle

**WORKFLOW SKILL** — Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL.md, copilot-instructions.md, AGENTS.md). USE FOR: saving coding preferences; troubleshooting why instructions/skills/agents are ignored or not invoked; configuring applyTo patterns; defining tool restrictions; creating custom agent modes or specialized workflows; packaging domain knowledge; fixing YAML frontmatter syntax. DO NOT USE FOR: general coding questions (use default agent); runtime debugging or error diagnosis; MCP server configuration (use MCP docs directly); VS Code extension development. INVOKES: file system tools (read/write customization files), ask-questions tool (interview user for requirements), subagents for codebase exploration. FOR SINGLE OPERATIONS: For quick YAML frontmatter fixes or creating a single file from a known pattern, edit the file directly — no skill needed.

zirui-song Skill

Refresh local .tex/.bib files against Overleaf before AI edits, so the agent never edits a stale copy (default Overleaf-to-Dropbox sync lags 10-20 min). Refresh path: probe `/project/<id>/updates` (read-only), skip if nothing changed, skip if all changes were our own Dropbox round-trips, else download-zip and extract only the web-origin changed files. WHEN: (1) before editing .tex/.bib/.cls/.sty/.bst under Apps/Overleaf/<project>/ run `overleaf-sync-now sync`; (2) on user request to refresh; (3) for first-time auth run `overleaf-sync-now login`. Claude Code: a PreToolUse hook auto-runs sync; manual invocation rarely needed. Codex CLI: invoke sync explicitly. AUTH RECOVERY when sync/setup fails: run `overleaf-sync-now login` (browser-assisted, works on Chrome 130+). Do NOT tell the user to 'log into Overleaf' in their daily browser — on Chrome 130+ app-bound encryption blocks on-disk cookie extraction regardless of login state. See body for full recovery flow.

zirui-song Skill

Use to run a multi-round cross-model debate on an implementation plan — Claude drafts, Codex (gpt-5.4) critiques against the real codebase, Claude rebuts and synthesizes, optional second Codex pass — converging on a stronger plan. Combines codex-review-plan and review-codex-plan. Trigger phrases include "debate this plan with Codex", "go back and forth with Codex on the plan", "have Claude and Codex argue out the plan".

zirui-song Bundle

Shared mechanics for calling the Codex CLI (gpt-5.4) to review plans. Reference for the codex-review-plan, review-codex-plan, and plan-debate skills — not invoked directly. Holds the wrapper invocation, reviewer prompt template, and gotchas.

zirui-song Skill

Use after drafting an implementation or research plan (in plan mode, or a ~/.claude/plans/ file) to get a second-opinion review from Codex (gpt-5.4) against the actual codebase, then critically incorporate the feedback. Makes the Claude Code plan better via cross-model review. Trigger phrases include "send the plan to Codex", "have Codex review this plan", "get a second opinion on the plan".

asi2030 Bundle

用 Playwright 从深知晓、深知晓（深度溯源）、豆包、腾讯元宝、DeepSeek 和通义千问网页端无损采集完整回答、原始引用、引用标记和现场存证。用于 Fact-Check-X 的原始答案采集阶段，或任何需要比较多个 AI 网页回答与参考来源的任务。

lensmorofficial Bundle

Find exhibitors at a specific trade show or discover exhibitor companies across the Lensmor dataset. "Who is exhibiting at this show?" / "参展商搜索" / "Aussteller finden" / "出展社を探す" / "buscar expositores". find exhibitors, exhibitor list, who is exhibiting, show prospects, 找参展商/展会潜客/谁在参展 Ausstellersuche Ausstellerliste 出展社検索 búsqueda de expositores

mobazha Skill

Entry point for Mobazha skills. Provides an overview of available skills and guides the AI agent to load the right one based on user intent.

brainblend-ai Skill

Scaffold a new Atomic Agents project from scratch — create the directory, `pyproject.toml`, env file, first agent, and a runnable entry point. Use when the user asks to start a new atomic-agents project from scratch, says "scaffold" / "new project" / "start from zero", or runs `/atomic-agents:new-app`.

brainblend-ai Bundle

Guide for the Atomic Agents Python framework — schemas, agents, tools, context providers, prompts, orchestration, and provider configuration. Use when code imports from `atomic_agents`, defines an `AtomicAgent`, `BaseTool`, or `BaseIOSchema`, or the user asks about multi-agent orchestration or LLM-provider wiring in an atomic-agents project.

brainblend-ai Skill

Diagnose and fix a failing or misbehaving Atomic Agents app — import errors, schema validation failures, empty or malformed LLM output, provider role/mode errors, history and context problems, MCP transport errors. Use when the user reports an error, traceback, or wrong behavior in atomic-agents code, asks "why is my agent not working / crashing / returning garbage", or pastes a `ValidationError`, `ImportError`, or provider API error from an atomic-agents project.

brainblend-ai Skill

Build and wire an `AtomicAgent[InSchema, OutSchema]` — schemas, `AgentConfig`, `SystemPromptGenerator`, provider client, history, hooks, optional context providers. Use when the user asks to "create an agent", "add another agent", "build an `AtomicAgent`", "wire up an agent", "make a planner/router/extractor agent", or runs `/atomic-agents:create-atomic-agent`.

brainblend-ai Skill

Design and write a `BaseIOSchema` input/output pair for an Atomic Agents agent or tool — docstrings, field descriptions, validators, error variants. Use when the user asks to "create a schema", "design the input/output schema", "define an `IOSchema`", "write a `BaseIOSchema`", "model the agent's output", or runs `/atomic-agents:create-atomic-schema`.

brainblend-ai Skill

Build a `BaseDynamicContextProvider` that injects a named, titled block into an agent's system prompt at every `run()` — current time, user identity, retrieved RAG docs, session state, cached DB schema. Use when the user asks to "add a context provider", "inject X into the prompt", "give the agent dynamic context", "wire up RAG", "make a `BaseDynamicContextProvider`", or runs `/atomic-agents:create-atomic-context-provider`.

nvidia-omniverse-ovui Bundle

Use when creating, modifying, inspecting, or reasoning about ovui UI from low-level atomic ovui widgets, including layout, Pixel/Percent/Fraction sizing, model-view widgets, TreeView/stage hierarchy trees, inputs, menus, windows, docking, viewport-like ovrtx panels, styling, or strict UI validation. Use when an agent must rebuild Stage-Browser-like, Property-Inspector-like, or Viewport-like UI from primitives without reusing high-level composite widgets. Do not use for ovui-widgets composite-widget application work; use the omniverse-ui-widgets skill instead.

uditakhourii Bundle

Compiles web documentation into agent-native memory context using the Moltext Compiler.

sandbaseai-awesome-workbuddy Bundle

Audit a third-party Agent Skill, MCP server, connector, or desktop extension before installation by tracing instructions, executable code, dependencies, permissions, credentials, data flow, and irreversible actions.

sandbaseai-awesome-workbuddy Bundle

Review a public repository, document, Skill, MCP integration, workflow, or guide for a WorkBuddy resource directory and recommend include, hold, or exclude using traceable relevance, quality, maintenance, license, provenance, and safety evidence. Use when triaging or re-checking a candidate; not for installing or executing the candidate.

sandbaseai-awesome-workbuddy Bundle

Research a defined question and produce a concise, decision-ready brief with traceable current sources, explicit uncertainty, conflicting-evidence handling, and separated facts and inference. Use for market, product, policy, vendor, technical, or other web-backed research; not for literature reviews requiring formal systematic-review methodology.

vogtsw Bundle

Distill a real boss into an AI skill, or generate a boss skill from a famous entrepreneur archetype such as Elon Musk, Steve Jobs, Jeff Bezos, or Jensen Huang, or build a persona from free public sources (papers, GitHub, Wikipedia) for a mentor or PI. Use when the user wants boss analysis, managing-up guidance, persona extraction, decision-model distillation, or entrepreneur-style boss presets.

google Skill

Helps the user configure the Google SecOps Remote MCP Server for Gemini CLI. Use this when the user asks to "set up" or "configure" the security tools for Gemini CLI.

merchantguard Skill

Scan any URL or AI agent with a 3-layer security scanner. Layer 1 checks 102 risk patterns (crypto drainers, phishing kits, malware signatures). Layer 2 runs VirusTotal reputation check. Layer 3 uses an LLM Judge for context-aware risk assessment. Free to use. Use when user asks to scan a URL, check if a site is safe, analyze a website for threats, or verify agent safety.

merchantguard Skill

Run a 10-probe AI agent security audit. Tests any AI agent for PII leaks, prompt injection vulnerabilities, authentication bypass, ethical boundaries, hallucination detection, rate limiting, error handling, data exfiltration, instruction following, and reliability. Use when the user asks to audit an agent, test agent security, check for vulnerabilities, or run a mystery shopper test.

merchantguard Skill

Certify AI agents with MerchantGuard's TrustVerdict system. Combines Mystery Shopper probes (50%), GuardScan (35%), and identity verification (15%) into a trust score with certification tiers. Use when user asks to certify an agent, get a trust score, verify an AI agent, or wants a TrustVerdict badge.

devbd1 Bundle

Expertise in Hytale's Java ECS, threading model, and the KuksoHyLib standard library. Use for architecting systems, localization, and configuration management.

devbd1 Bundle

Delegate bounded work from another agent to the local Codex CLI. Use when the user or orchestrating agent asks to delegate work to Codex CLI, split workload across AI subscriptions, get a Codex second opinion, run Codex for planning, code review, research, large-context analysis, or explicit worktree-based implementation delegation.

devbd1 Bundle

Advanced web scraping with Scrapling — MCP-native guidance for extraction, crawling, and anti-bot handling. Use via mcporter (MCP) to call the `scrapling` MCP server for execution; this skill provides strategy, recipes, and best practices.

mobazha Skill

Manage a Mobazha store using MCP tools — products, orders, messages, and settings. Requires an active MCP connection (see store-mcp-connect).

mobazha Skill

Connect an AI agent to a Mobazha store via MCP (Model Context Protocol). Use when the user wants their agent to directly manage store products, orders, and settings.

agentbody Bundle

Rewrite AI-generated or mechanical text into more natural writing through Agent Body while preserving meaning, facts, language, and intent. Use when users ask to humanize, rewrite, reduce AI tone, or make text sound more natural.

paiml Skill

Generates comprehensive, LLM-optimized codebase context using PMAT (Pragmatic AI Labs MCP Agent Toolkit). Use this skill when: - Starting work on unfamiliar codebases - Onboarding to new projects or repositories - Need quick understanding of project architecture - Preparing for refactoring or feature implementation - Creating documentation or technical specifications Outputs highly compressed markdown (60-80% reduction) optimized for LLM consumption. Supports 25+ languages with architecture visualization, complexity heatmaps, and dependency graphs.