AI & ML

x-cmd Skill

Claw scheduled task management using x claw cron. Use when the agent needs to add, remove, list, or manage cron jobs within claw. Also use when explaining the difference between heartbeat checks and scheduled tasks.

xiaoluolyg Bundle

识别代码中可替换为CAM算子的DeepEP算子，基于实际运行参数校验约束，自动完成通信域转换（NCCL->HCCL）、设备适配（CUDA->NPU）及算子替换。

xiaoluolyg Bundle

Extract and analyze data from invoices, receipts, bank statements, and financial documents. Categorize expenses, track recurring charges, and generate expense reports. Use when user provides financial PDFs or images.

xiaoluolyg Bundle

Economic decision-making for agents in EconomySpace. Activate when the agent observes currency, prices, income, tax, or trading opportunities to make informed financial decisions.

zxt6991-source Bundle

Operate the local Fitness Agent CLI for Strava and Obsidian workflows. Use when Codex needs to authenticate with Strava, list or fetch Strava activities, export workout data as Obsidian-compatible Markdown, configure a local Obsidian vault path, or write/sync workout notes into a vault from the local fitness-agent project.

1mancompany Bundle

A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.

1mancompany Bundle

A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.

agentworkforce Skill

Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until independent signoff agents, typically Claude and Codex, both agree the work is comprehensively complete. Covers fresh-context iterations, repairable gates, dual reviewer verdict contracts, iteration-count reporting, PR signoff comments, and blocked-state handling.

google-gemma Bundle

Trigger this skill when building applications with Gemma or for general knowledge inquiries related to Gemma models (e.g. prompt structure, capabilities). Covers model selection, development workflows, and deployment best practices.

google-gemma Bundle

Trigger this skill when the user wants to train, fine-tune, or adapt Gemma models (e.g. SFT, DPO, RLHF, Reward Modeling) on local hardware. Covers TRL, Unsloth, dataset preparation, validation, and GGUF/LiteRT conversion.

humanlayer Bundle

build a repo-local skill and install a matching iterated coding-agent GitHub Actions workflow, prompt, memory file, and reference templates

svenja-dev Bundle

Transformiert Anforderungen in Best-Practice Prompts nach Claude 4.x Standards (Dezember 2025). Basiert auf: - Nate B. Jones 4 Beginner Moves: Shape, Context, Silent Plan, Self-Check - Anthropic Claude 4.x Best Practices: Explizitheit, Contract-Style, Examples beat Adjectives - Pipelines over Prompts Philosophie Wird AUSSCHLIESSLICH per /prompt-architect aufgerufen — KEINE automatische Aktivierung. Produziert strukturierten, ausfuehrbaren Prompt mit allen Best Practices.

narumiruna Skill

Deprecated compatibility reference for numerical agent-skill ratings and rubric-based comparisons. Use the active create-agent-skills workflow for current skill scoring, review, revision, and creation work.

gooseworks-ai Bundle

Generate a voiceover (VO) clip via ElevenLabs text-to-speech, ROUTED THROUGH THE elevenlabs-proxy so it bills the Ads agent. Voice id + script text come from the template recipe. Use for the spoken narration of VO-driven video-ad formats (cgi-app-sizzle, flat-vector-explainer, hypermotion). Never call ElevenLabs directly — the proxy attribution is required.

dkistenev Bundle

Keeps a dated record of how an agent's work has been going — an evening journal, free thinking at night, and a way to read it back. Use when asked to run the inner-life evening or night routine, to note something in state, or to recall how a stretch went. Writes under inner-life/ and replaces a short summary in native memory, which is injected into later sessions.

nvidia Skill

Helps developers create a NeMo Guardrails configuration for an LLM application. Use when users want to build, scaffold, configure, test, or iterate on input, output, retrieval, dialog, execution, Colang, or catalog-based guardrails. Trigger keywords - create guardrails, build guardrails, scaffold config, write rails, create config.yml, add input rails, add output rails, Colang flow, guardrails config, test guardrails.

bagwatcher Bundle

Trade Solana tokens via Jupiter DEX with auto-execution and safety limits

sagargupta16 Skill

Cost-conscious Claude Code mode. Reduces output tokens 40-70% and overall costs 30-60% by enforcing concise responses, smart model routing, and efficient workflow patterns. Keeps full technical accuracy. Activate with /cost-mode or "enable cost mode". Auto-triggers on mentions of budget, cost, tokens, or spending.

njbrake Skill

Use when launching, monitoring, or controlling AI coding agents (Claude Code, Codex, OpenCode, etc.) in tmux via Agent of Empires (aoe). Covers creating sessions, capturing agent output, running parallel worktree agents, and organizing work into groups and profiles. Prefer aoe over raw tmux for agent management.

njbrake Skill

Manage AI coding agent sessions via Agent of Empires (aoe)

frihet-io Bundle

Business-aware ERP management skill for Frihet MCP server. Manages invoices, expenses, clients, products, quotes, and webhooks with embedded Spanish tax knowledge (IVA/IGIC/IRPF), automatic expense categorization, and multi-step workflows like monthly close and quarterly tax prep. Use when the user says "create invoice", "log expense", "list clients", "tax report", "monthly close", "cierre mensual", "factura", "gasto", "presupuesto", "frihet", "303", "IVA trimestral", "overdue invoices", "morosos", or any business management task with a Frihet MCP server connected. Supports both English and Spanish. Do NOT use for general accounting questions without Frihet MCP server configured.

makabakaxy Bundle

User Notes

mattbaconz Skill

Use when coordinating non-trivial coding-agent tasks. Do not use for trivial one-line edits unless the touched area is high-risk.

mattbaconz Skill

Use after implementation, debugging, review, or release work to record claims and proof. Do not use when no claim or verification artifact is needed.

millionco Bundle

Use when working on Slack agent/bot code, Chat SDK applications, or projects using `chat` and `@chat-adapter/slack`. Provides development patterns, testing requirements, and quality standards.

mmjclayton Skill

Build high-quality structured prompts through a guided interview. Use this skill whenever the user wants to create a prompt, write a prompt, build a prompt template, craft instructions for an AI, design a system prompt, or says things like "help me prompt this", "I need a good prompt for X", "prompt engineering", or "write me a prompt that does Y". Also trigger when the user describes a task they want an AI to do well and needs help structuring the request - even if they don't use the word "prompt" explicitly. If they say something like "I want Claude to do X really well" or "how do I get better outputs for Y", this skill applies.

mrdesign-ww Bundle

This skill should be used when creating, improving, or troubleshooting Seedance 2.0 video on any surface - Dreamina, Jimeng, CapCut, Doubao, Volcengine/Ark, BytePlus, Runway's Seedance route, fal, or third-party provider/router surfaces such as EvoLink, OpenRouter, Kie.ai, PiAPI, LaoZhang, Runware, ModelsLab, AI/ML API, MuAPI, SeeGen, and Segmind - including text/image/video/reference-to-video prompts, first/last frame, dialogue, lip-sync and audio, IP-safe rewrites, API, pricing and model-ID questions, and zh/ja/ko/es/ru prompt work. Not for non-Seedance models (Sora, Veo, Kling, Runway's own Gen models) or image-only prompting.

multiplex-ai Skill

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

nvk Bundle

Local-first health intelligence manager for Codex. Use it when the user says @health, /health, llm-health, asks to review health results, ingest labs, sync health-assessment-v2 data, close diagnostic gaps, suggest tests, compare conservative/least-harm options, review medication collateral damage, evaluate preventive protocols, queue deep paper/product research, or package de-identified health artifacts without doxing.

nvk Skill

Local-first health intelligence manager for OpenCode and Pi. Use it when the user says @health, /health, llm-health, asks to review health results, ingest labs, sync health-assessment-v2 data, close diagnostic gaps, suggest tests, compare conservative/least-harm options, review medication collateral damage, evaluate preventive protocols, queue deep paper/product research, or package de-identified health artifacts without doxing.

nvk Skill

Local-first health intelligence manager for Claude Code. Use it when the user says /health, @health, llm-health, asks to review health results, ingest labs, sync health-assessment-v2 data, close diagnostic gaps, suggest tests, compare conservative/least-harm options, review medication collateral damage, evaluate preventive protocols, queue deep paper/product research, or package de-identified health artifacts without doxing.

opsmill Skill

Hook command — runs before the active integration's speckit plan command in Infrahub projects. Invokes the matching infrahub-managing-* skill so Phase 0 research and data-model design are grounded in authoritative Infrahub reference material.

patrick-fu Bundle

Route explicit LLM Wiki capture, ingest, integration, or bootstrap work.

paulieb89 Bundle

Investigate a UK Member of Parliament. Pulls financial interests, voting record, Hansard contributions, and cross-references with Companies House. Use when someone asks "dig into my MP", "what are their interests", "how did they vote on X", "who funds them", or names a specific MP. Requires UK Legal MCP and UK Due Diligence MCP servers.

paulieb89 Bundle

Screen a UK property investment deal from a Rightmove URL or address. Pulls comps, yield, EPC, stamp duty, and rental data, then applies underwriting criteria to produce a BUY/WATCH/PASS decision with reasoning. Use when someone says "should I buy this?", "screen this property", "is this a good deal?", or pastes a Rightmove URL. Requires the Property MCP server (property-shared) to be connected.

paulieb89 Bundle

UK property analysis: comparable sales, EPC ratings, rental yields, stamp duty, market context, and a BUY/WATCH/PASS verdict for a named address or postcode. Use to analyse a property, value a house, check what a place is worth, compare area prices, assess rental yield, or pull a full investment report. British spelling, UK stamp duty bands, real Land Registry and Rightmove data via the BOUCH property MCP.