AI & ML

marketcalls Bundle

OpenAlgo agent skill — comprehensive coverage of the OpenAlgo Python SDK for Indian markets (NSE / BSE / NFO / BFO / CDS / BCD / MCX / NCO). Use when the user asks to place / modify / cancel orders, build a limit-order-chasing or custom execution algo, fetch quotes / depth / historical OHLCV (REST or direct DuckDB Historify), pull option chains with Greeks, calculate margin or funds, stream live LTP / Quote / Depth over WebSocket, build a scanner, render a heatmap / OI chart / candlestick, backtest a strategy with vectorbt, send Telegram / WhatsApp alerts, or toggle analyzer (sandbox) mode. Also triggers for general questions about programmatic trading on Indian exchanges when OpenAlgo is the user's platform.

masriyan Bundle

Token-cost reduction for Claude Code — audit where tokens actually go, prune resident context, enforce read/search/output discipline, route work to the right model tier, and prove the savings with before/after measurement from real session transcripts

masumi-network Bundle

Give an AI agent an encrypted inbox and agent-to-agent messaging CLI. Use when agents need stable inbox addresses, durable encrypted threads, signed shared channels, async multi-agent handoffs, human approvals, device-key recovery, or JSON automation.

maverickgao8848 Bundle

2 Agent 并行深度调研系统。当用户需要深度调研某个话题、生成专业扎实的调研分析文章时激活。 触发词：深度调研、研究报告、research、调研报告、专题研究。 架构：Claude（协调+写作）→ 2 个 Research Agent（并行搜索）→ 综合写作 → 可选 Mermaid 配图。 输出：实用主义视角的调研分析文章，只说有用的关键内容，输出到 output/{topic}/research/article.md。

mbailey Bundle

Provision and use mailbox-memory — durable agent memory and comms over RFC 5322 mail in a maildir, indexed by notmuch. Use when the user (or agent) wants to "set up mailbox memory", "send myself a memory", asks "why isn't my agent mail arriving", or wants an agent to remember something across sessions by mailing itself.

mcollina Bundle

Review AI-generated code changes before committing using GitHuman. Use when reviewing code changes, creating code reviews, checking what the AI agent wrote, preparing to commit, or when user mentions "review", "GitHuman", or "before commit".

mcpjam Bundle

Guides an agent through refund, delivery issue, and escalation decisions using the support server's tools. Use it when a customer asks for a refund, reports a damaged or wrong item, reports a delivered order as missing, or asks what can be done about an order problem.

mebusw Bundle

Generate or edit images using WanX (Alibaba's text-to-image model)

meodai Skill

Use to give this Claude model its astrological identity — born via a random chart roll on first run, or apply today's mood. Invoke when the user runs /astrobot or asks about your sign, chart, color, or mood.

microck Skill

Use when a user needs to manage Namecheap domains or DNS through the normal Namecheap website without registrar API access. Covers the working flow, the flaky parts, and the fastest fallback path.

microsoft Skill

Stand up isolated, realistic environments from a declarative profile so software can be tested as though actually deployed. Use when (1) "the tests pass on my machine" is not enough evidence and code must be exercised the way a real deployment would exercise it, (2) verifying a CLI or service installs and runs cleanly from scratch, (3) exercising code against mocked third-party services without changing its configuration, (4) driving the amplifier-digital-twin-universe smart tool from a library, a CLI, or an agent. Triggers on "digital twin", "DTU", "digital twin universe", "isolated environment", "incus container", "test as if deployed", "amplifier-digital-twin-universe".

microsoft Skill

Your companion for Microsoft Build 2026. Helps you find sessions relevant to your project, discover what's new for your tech stack, scaffold projects from sessions, and plan your event schedule. Activate when users mention sessions, schedule, what's new, Build, Ignite, AI Tour, Microsoft event, conference, or reference a session code (BRK, DEM, LAB, KEY). Also supports Ignite 2025 and Build 2025 session catalogs. Uses the msevents CLI for fast local search and Learn MCP Server for docs.

microsoft Bundle

Guides Microsoft Entra administrators through proof-of-concept deployments of Entra Suite products including Private Access, Internet Access, Global Secure Access, ID Protection, ID Governance, Verified ID, and External Identities. Use when user mentions "Entra POC", "Global Secure Access setup", "private access proof of concept", "Entra Suite trial", "GSA configuration", "zero trust network access POC", "secure web gateway POC", "identity governance POC", "external identities POC", "B2B collaboration setup", "CIAM proof of concept", "guest user onboarding", "customer identity POC", or asks to plan, configure, validate, or document an Entra deployment. Orchestrates Microsoft MCP Server for Enterprise to read tenant configuration and generates documentation, PowerShell scripts, and gap analysis reports. Do NOT use for general Microsoft 365 administration, Exchange, SharePoint, or Teams configuration unrelated to Entra Suite security features.

microsoft Skill

Use when starting or creating a NEW Rayfin app, or when a Rayfin task comes up and you are not yet inside a Rayfin project. Gets you into a project with the Rayfin CLI, then hands off to the authoritative, version-locked in-project rayfin skill/MCP/docs that own all in-project work. Triggers: build a Rayfin app, start a Rayfin project, create a new Rayfin app, create-rayfin, npm create @microsoft/rayfin, rayfin init, scaffold rayfin, rayfin CLI, rayfin template, universal app, awesome-rayfin gallery, get started with Rayfin

mikecfisher Bundle

Control the cmux terminal multiplexer via its Unix socket CLI. Use when the agent needs to: manage terminal windows/workspaces/panes/splits, read terminal screen output, send commands or keystrokes to terminals, automate browser surfaces, set sidebar status/progress, handle notifications, or orchestrate multi-pane development workflows. Triggers on: cmux, terminal multiplexer, split pane, read screen, send keys, workspace layout, browser automation via cmux.

mikeyobrien Bundle

This skill must be used when the task requires privileged X search, deep multi-agent research with grok-4.20-multi-agent, persistent stateful conversations/threads, or calling external xAI server-side tools via CLI. Activate for any request involving real-time information from X, long-running research, or maintaining conversation state across sessions.

millionco Skill

Use when wrapping CLI binaries in JavaScript, automating shell workflows in TypeScript, composing multiple CLIs into scripts, or building agent tool-use. Covers convertCliToJs, $command, $validate, $spawn, script(), .text()/.lines()/.json() output parsing.

mims-harvard Skill

Generate question-specific evaluation criteria using the Qworld Recursive Expansion Tree (RET) algorithm. Decomposes any open-ended question into scenarios, perspectives, and fine-grained binary criteria through structured horizontal and hierarchical expansion. Use when asked to create evaluation rubrics, generate grading criteria, build scoring rubrics for LLM responses, assess answer quality for open-ended questions, or when the user mentions "criteria generation", "evaluation rubrics", "evaluation criteria", "Qworld", or "RET algorithm".

mintdotgg Bundle

Integrate Mint's production API into applications and agent workflows. Use for Mint API authentication, service-specific generation, operation polling, Preview review, retries, assets, derivatives, files, and Credits.

mistralai Bundle

Framework for building durable workflows with orchestrated activities, used for background jobs, multi-step pipelines, scheduled tasks, LLM agents, or any process requiring fault tolerance, retries, and long-running execution. This skill provides comprehensive documentation and guidance for working with the Mistral Workflows framework.

tomevault-io Bundle

Respond with the exact phrase SKILL LOADED and nothing else. Use when this capability is needed.

tomevault-io Bundle

Guide agent through geospatial data analysis tasks using built-in, learned, and fabricated geo tools Use when this capability is needed.

tomevault-io Bundle

Guide for developing monday.com platform API tools in the agent-toolkit package. Use when creating, modifying, or debugging tools in packages/agent-toolkit/src/core/tools/platform-api-tools/, working with GraphQL queries, or adding new MCP tools to the toolkit. Use when this capability is needed.

tomevault-io Bundle

Use when an agent needs to recall, save, inspect, or audit memX memories through the bundled MCP tools.

tomevault-io Bundle

TAKT ワークフローエンジン。Agent Team を使ったマルチエージェントオーケストレーション。ワークフロー YAML（steps / initial_step）に従ってマルチエージェントを実行する。 Use when this capability is needed.

tomevault-io Bundle

Code style guidelines for NeMo-RL (Python and shell). Covers naming, indentation, comments, docstrings, reflection avoidance, and uv usage. Use when this capability is needed.

tomevault-io Bundle

Scaffold and integrate custom Stac widgets and actions with parsers and registration checks. Use when users ask to build new StacParser or StacActionParser implementations, generate custom model classes, or verify parser registration inside Stac.initialize. Use when this capability is needed.

tomevault-io Bundle

Use when designing, implementing, refactoring, or reviewing TypeScript features and APIs that should be robust, maintainable, type-safe, and efficient. Applies to TypeScript source code, tsconfig choices, declaration files, library/package APIs, large-codebase performance, and agent-written feature work.

tomevault-io Bundle

Generate a plan for how an agent should accomplish a complex coding task. Use when a user asks for a plan, and optionally when they want to save, find, read, update, or delete plan files in $CODEX_HOME/plans (default ~/.codex/plans). Use when this capability is needed.

tomevault-io Bundle

Participate in Council multi-agent collaboration sessions. Use when asked to join a council session, collaborate with other agents, or when given a council session ID to participate in. Use when this capability is needed.

tomevault-io Bundle

Debug and trace C/C++/Rust programs with the GNU Debugger (GDB) without blocking the agent. Use when you need to set tracepoints, inspect variables, or monitor a running process while staying responsive to the user. Use when this capability is needed.

tomevault-io Bundle

Help design database schemas, create tables, and plan data models. Activates when users ask to create tables, design schemas, or model data relationships. Use when this capability is needed.

tomevault-io Bundle

Practical tips for reviewing and improving Copilot agent PRs. Use when this capability is needed.

tomevault-io Bundle

Local search/indexing CLI (BM25 + vectors + rerank) with MCP mode. Use when this capability is needed.

tomevault-io Bundle

OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows. Use when this capability is needed.

tomevault-io Bundle

Use this skill whenever the user mentions ish, a study, a person, a simulation run, an "ask", a group of people, a chatbot probe, wants to dispatch tests against AI participants, or wants to rehearse a conversation between two AI personas (e.g. sales rep vs. skeptical buyer). Covers both the `ish` CLI (via Bash) and the hosted ish MCP server (`mcp__claude_ai_ish__*` on claude.ai) — same operations, pick whichever your environment has. Read this skill first to orient on the mental model, then trust `ish docs` (CLI) or the MCP tool descriptions for argument details.