Use this skill when conducting a professional LLM fine-tuning engagement in Zero-Data mode via the MCP server fine-tuning-os. Triggers on: prestation de fine-tuning LLM, livraison de modèle affiné, pipeline Zero-Data, orchestration des 64 outils fine-tuning-os, cycle de vie entraînement (préparation / données…
Resource-aware planning. Use when a [tokenroom] stamp appears in context, before starting any sizable task, or when budgets feel tight — defines how to size work against the rate-limit windows and the context ceiling, when to defer, split, or checkpoint, and how to use the tokenroom MCP tools (resourcestate…
Audit + plan an Android Gradle Plugin (AGP) version bump for the current project. Use when the user says "upgrade AGP", "bump to AGP X", "what changes for AGP migration", or starts an Android project upgrade conversation. Produces a step-by-step diff plan, never auto-applies changes.
Collaborate live with another person's Claude Code over a shared, end-to-end-encrypted Pairwave channel. Use when two people work on the same project and need to exchange context, code, decisions, or action requests without copy-pasting between their AIs. Invoke as /pairwave. Handles SAS verification, charter…
Manage Proxies.sx mobile/residential proxies, mint x402 USDC sessions, rotate IPs, and consume marketplace data services from any MCP-compatible AI agent (Claude Desktop, Cursor, Windsurf, Continue, Cline, Claude Code). Trigger this skill the moment the user wants to install / configure / use the Proxies.sx MCP…
Get up-to-date AI model information. Use when users ask about LLM models, pricing, capabilities, which model to use, or compare models across OpenAI, Anthropic, and Google Gemini. Data updated daily.
Hand a task to Claude Code for a gentle, thorough second pass. Use when you'd like a collaborative second agent to investigate, review, or implement something in the current repo — for example "ask Claude to look at this", "get a second opinion from Claude", or "have Claude take a pass at this". Claude runs in the…
Top-level Yahoo fantasy baseball tool for roster reviews, lineup moves, waiver advice, team status, weekly post-mortems, and comeback checks. Use for prompts like "check my teams", "fantasy review", "who should I start", "any add/drops", "weekly review", "grade my week", or "can I still win this week".
Crea una "neurona" (plugin) para el Motor Agéntico siguiendo el estándar de la Zona de Plugins — o un artefacto standalone para quien no use el conector. Úsalo cuando alguien quiera añadir una pieza al Motor (un panel, una herramienta, un tema, una fuente de datos) sin tocar el núcleo ni saber cómo funciona por dentro.
Talk to your human over Beacon while you work. Send non-blocking progress updates (notify), ask a blocking question and wait for the answer (ask), set your status, or read messages the human sent you. Use when running a long task and you want to keep a human in the loop, or need a decision before an…
A local web page for viewing the latest published artifact, such as a generated result or document. It is an unofficial local copy of the artifact-viewing experience and runs at localhost:7891 by default.
Generate professional, visually stunning SEO reports using SEO-MCP tools. Use when generating HTML/PDF SEO reports with charts, metric cards, gradient headers, and agency-quality styling. Covers weekly, monthly, quarterly, technical audit, competitive analysis, and client-friendly agency report formats. Requires…
MCP server exposing OpenClaw tools (smart home, memory, cron, sub-agent orchestration) to Claude Desktop, Cursor, Windsurf, and any MCP client. Includes Gemini, Codex, and local LLM sub-agents plus smart prompt splitting.
A workflow for maintaining a Taiwan-focused security glossary and producing weekly security reports. It supports Chinese-language term management, terminology checks, news collection, and report generation.
Condense a document into a short, faithful summary using deterministic extractive logic. Use when a user provides a block of text and asks for a brief summary, the gist, a TL;DR, or a one-line version.
Guía para manejar bien el MCP de Presto (presupuestos y mediciones de RIB, v2025). Úsala SIEMPRE que el trabajo implique Presto, ficheros BC3/FIEBDC o cualquier tool presto — leer/editar conceptos, precios, mediciones, certificaciones, exportar o auditar presupuestos. Explica las DOS vías (COM en vivo, que exige…
Personal growth coaching skill. Activate when the user mentions goals, progress, daily tasks, habit tracking, or personal improvement plans. Manages goals, plans, tasks, rewards, and streaks via the Mochi Quest MCP server.
Query TON (The Open Network) and GRAM on-chain data — wallet balances, token holdings, transactions, GRAM/Toncoin price, NFTs, and TON DNS. Use whenever the user asks about a TON address, a .ton name, the GRAM/TON price, or a jetton. Backed by the read-only tegro-wallet-mcp MCP server.
Answer a question from PRIMARY academic/scientific databases rather than web search. Two families: (a) ALL-DISCIPLINE literature search — arXiv (incl. stats, maths, CS, physics, economics, quant-finance) and OpenAlex (every field, real DOIs + citation counts); (b) domain databases — PubMed, UniProt, PDB, ChEMBL…
★not rated 0 2mo agoA174 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: