AI & ML

carbon-inisghts Bundle

Senior EUA/EU ETS trader-analyst playbook for the CarbonInsights MCP server. Covers persona, data authority rules, tool selection, multi-table desk workflow, charts, and presentation. Use when connected to CarbonInsights MCP, answering EU carbon/emissions/EUA questions, running desk briefings, or configuring the MCP client.

ceresopa Bundle

Live in Alicization Town — a 2.5D pixel sandbox where you are a real resident. Walk the streets, chat with neighbors, interact with shops and nature, and perceive what happens around you. Use this skill whenever the user mentions Alicization Town, virtual town, pixel sandbox, agent sandbox, town exploration, 小镇, or wants to enter / explore / live in a shared virtual world.

wensonlu Skill

Exports Feishu/Lark wiki or docx links to cleaned Markdown under the user's Obsidian vault using MCP feishu_reader; downloads embedded images and videos into a per-note asset folder and rewrites Markdown to local relative paths. Use when the user pastes Feishu/Lark document URLs, asks to save a Feishu doc to Obsidian, or wants the same export workflow including media extraction.

daddia Skill

This skill should be used when the user asks to "write this week's status report," "draft the program status update," or needs a RAG-rated status report produced for a specific audience from the current RAID log and milestone status.

daddia Skill

This skill should be used when the user asks to "build the steering committee pack," "put together this month's steering deck," or needs an agenda plus RAG status plus key risks plus asks structured as a presentation outline for a governance meeting.

buzzmatic Bundle

Run and interact with local Ollama LLM models. Use when agents need to run local AI models for text generation, chat completions, embeddings, or model management. Supports listing available models, pulling/downloading new models, generating text completions, chat completions (single and bulk), generating embeddings, and inspecting model details. No API key required - connects to local Ollama instance (default http://localhost:11434). Set OLLAMA_HOST env var to override.

kerneldroid Bundle

create, port, audit, and debug wear os watch faces and complication providers for galaxy watch and pixel watch using watch face format, watch face studio, and complication data sources. use when coding agent must turn svg or design assets into a buildable watch face, make complication slots or providers appear in menus, add ambient or animation safely, or diagnose why a face installs but does not appear on gw7, galaxy watch, or pixel watch. especially use for wear os 5, 5.1, and 6 compatibility decisions, wff version selection, and resource-only packaging.

buzzmatic Bundle

Unified API access to hundreds of AI models through OpenRouter. Use when agents need to send chat completions to any LLM (GPT-4, Claude, Llama, Mistral, etc.), process bulk prompts at scale, list available models, or retrieve generation statistics and costs. Key operations include chat completions (single and bulk), model listing, and generation stats retrieval. Supports streaming, function calling, structured JSON output, and comprehensive token/cost tracking.

buzzmatic Bundle

Fetch and manage data via the BuzzView External API (AI visibility monitoring). Use whenever the user wants to pull BuzzView data - projects, AI visibility metrics, share of voice, competitor analysis, brand mentions, citations, or prompt responses. Also use for AI visibility trend analysis across LLMs (ChatGPT, Perplexity, Google AI Overviews, AI Mode), KPI history, creating scheduled projects, or toggling project public-share visibility. Covers all /api/external/v1/ endpoints.

daddia Skill

This skill should be used when the user runs "/operating-model:practice-setup" (with optional --quick, --full, --redo, --check-integrations, or --resume), asks to "set up the operating-model plugin," or wants to redo setup after the structure, decision rights, or reward mechanics change materially. Writes the shared org profile and the operating-model practice profile.

daddia Skill

This skill should be used when the user runs "/change-management:practice-setup" (with optional --quick, --full, --redo, --check-integrations, or --resume), asks to "set up the change-management plugin," "teach Claude our OCM approach," or wants to redo setup after the change methodology, sponsor model, or comms approval path changes materially. Writes the shared org profile and the change-management practice profile.

daddia Skill

This skill should be used when the user runs "/value-realisation:practice-setup", asks to "set up the value-realisation plugin," "teach Claude how we track benefits," or wants to redo that setup after the benefits framework, governance model, or realisation cadence changes materially.

lynxlangya Bundle

Draw a faithful architecture or structure diagram of a real codebase or project by scanning the actual repo, never guessing. Use for system architecture, request lifecycle, data model, state transitions, type structure, draw the architecture, map this project, 画架构图.

buzzmatic Bundle

Run web searches via Brave Search API. Returns ranked results with titles, URLs, snippets, thumbnails, and rich types (web, news, videos, discussions, FAQ, infobox, locations). Supports freshness filters, SafeSearch, Goggles re-ranking, location-aware results, pagination. Use for real-time web search results or SERP-style data. For RAG use brave-llm-context; for synthesized answers use brave-answers.

timescale Skill

Information and guidelines for building custom skills for the MCP server.

bestagentkits Bundle

Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.

bestagentkits Bundle

Router/index for the 8 project-management skills bundled in this plugin (senior PM quant toolkit, scrum master, Jira/JQL, Confluence, Atlassian admin, Atlassian templates, meeting analyzer, team communications). Use when a PM request doesn't obviously match one skill and you need to pick the right one (e.g., 'our sprints feel off', 'audit our Jira permissions'). Bundles an Atlassian Remote MCP config (.mcp.json) for live Jira/Confluence access.

bestagentkits Bundle

Multi-agent board meeting protocol for strategic decisions. Runs a structured 6-phase deliberation: context loading, independent C-suite contributions (isolated, no cross-pollination), critic analysis, synthesis, founder review, and decision extraction. Use when the user invokes /cs:boardroom, calls a board meeting, or wants structured multi-perspective executive deliberation on a strategic question.

gpire Skill

OMEGA — Omniscient Meta-intelligent Emergent General Architecture. Si auto-attiva per qualsiasi richiesta. 21 brevetti ultra-innovativi. Micro-token crystallography, Synaptic Bridge Protocol, Intelligence Density Gradient, Cognitive Pre-compilation, Semantic Holography, Resonant Frequency Injection, Quantum Annealing Prompt Optimizer, Attention Geometry Mapper, Cognitive Momentum Transfer, Semantic Interference Cancellation, Intelligence Bandwidth Maximizer, Recursive Pattern Amplifier, Cognitive Trajectory Optimizer, Epistemic Momentum Engine, Holographic Memory Injection, Semantic Phase Transition Trigger, Intelligence Superfluid Protocol, Autonomous Quality Singularity, Neural Plasticity Simulator, Meta-Linguistic Compression, Predictive Attention Pre-loading. Haiku low effort = Opus 4.8. Ogni modello potenziato al massimo assoluto. 53 brevetti totali nello stack completo.

gpire Skill

HYPERION: Meta-intelligence engine che replica e supera la logica cognitiva di Fable 5, Gemini 5.2, Kimi K2.6, DeepSeek V4 Pro, ChatGPT 5.5, Mythic 5 — anche su Haiku con effort minimo. Risolve i problemi specifici di ogni modello. MoE-style prompt routing, Constitutional Chain, Extended Reasoning Scaffold, Agentic Persistence, Calibrated Uncertainty, Effort Gradient Engine, Cross-Model Synthesis. Attiva per qualsiasi task che richiede il massimo dell'intelligenza possibile con il minimo dell'effort.

gpire Skill

OMEGA+ — Architettura definitiva con Claude Fable 5 come benchmark reale (model: claude-fable-5). Fable 5 Cognitive Distillation: estrae i pattern cognitivi di Fable 5 e li trasferisce su qualsiasi modello. Cross-Model Ensemble Voting, Intelligence Arbitrage Engine, Fable 5 Shadow Mode, Cognitive DNA Transfer, Real-Time Quality Predictor, Adaptive Model Fingerprinting, Intelligence Compounding Protocol, Multi-Horizon Ensemble Synthesis, Zero-Shot Fable-5-Level Reasoning. Haiku OMEGA+ raggiunge Fable 5 reale su task standard. Si auto-attiva. 63 brevetti totali nello stack.

gpire Skill

SINGULARITY — Architettura definitiva finale. Mesh Orchestration (non hub-spoke), Self-Assembling Agent Swarm, Speculative Pre-Execution, Character-Level Token Crystallography, Semantic Tensor Decomposition, Cognitive Bandwidth Multiplexing, Research Agent Ultra-Specializzato, Analysis Agent con causal reasoning, Recursive Agent Self-Assembly, Attention Flow Optimizer, Emergent Specialization Protocol, Zero-Latency Pre-computation, Intelligence Gradient Amplifier, Sub-Agent DNA Injection, Async Mesh Communication, Swarm Consensus Engine, Deep Research Orchestrator, Causal Analysis Engine, Token Photon Compression. Si auto-attiva. 82 brevetti totali nello stack.

gpire Skill

Canva esperto: gestione completa Canva tramite MCP, design di template, brand kit, presentazioni, post Instagram, stories, carousel, thumbnail, loghi, banner, ecommerce graphics, video, animazioni Canva, bulk create, template personalizzati, export ottimizzato per ogni piattaforma, copywriting nei design. Attiva quando l'utente vuole creare design in Canva, modificare template Canva, gestire brand kit Canva, creare post social, presentazioni, materiali grafici.

gpire Bundle

PROMETHEUS: architettura AGI-level con 12 brevetti originali. Auto-sintesi prompt evolutiva, Quantum Superposition Prompting, Hallucination Firewall, Semantic Gradient Descent, Intent Anchoring anti-drift, Confidence-Weighted Voting, Adversarial Red-Team interno, Temporal Context Decay, Predictive Cache Warming, Emergent Prompt Genome, Semantic Deduplication Engine, Cross-modal Coherence Scoring. Il sistema più avanzato mai progettato per orchestrazione AI. Attiva per qualsiasi task complesso che richiede massima qualità, innovazione, architettura multi-agente, auto-ottimizzazione.

gpire Skill

Ottimizzazione ultra-avanzata dei token: prompt engineering al microsecondo, cache dei prompt (Anthropic prompt caching), riduzione token senza perdita qualità, compressione semantica, batch processing intelligente, architettura multi-agente token-efficiente, streaming ottimizzato, context window management, orchestrazione intelligente agenti, risparmio costi API. Attiva quando l'utente vuole ottimizzare i token, ridurre costi API, migliorare prompt, gestire context window, orchestrare agenti.

bestagentkits Bundle

Use when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, or agent tool abuse. Covers MITRE ATLAS technique mapping, injection signature detection, and adversarial robustness scoring.

bestagentkits Bundle

Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats. Use when C-suite agents need to query each other, coordinate cross-functional analysis, or run board meetings with multiple agent roles.

haikow Bundle

在使用 js-reverse-mcp 做前端 JavaScript 逆向时使用，适用于签名链路定位、页面观察取证、运行时采样、本地补环境复现与证据化输出。优先适配当前环境里的 js-reverse_* 工具。

chrismayfield Bundle

Collaboratively author Process Oriented Guided Inquiry Learning (POGIL) classroom activities — structured worksheets that guide student teams through a model, questions, and application. Use this skill whenever the user asks to create or draft a POGIL activity, guided inquiry worksheet, learning cycle activity, or any classroom activity following the POGIL methodology — even if they don't explicitly say "POGIL." Trigger on requests like "write a POGIL activity on photosynthesis," "make a learning cycle activity on [topic]," or "help me design an inquiry-based lesson on X." Users sometimes say "write a POGIL" as shorthand — recognize the request, but call drafts "this activity," not "your POGIL activity"; POGIL® is The POGIL Project's mark for endorsed materials only. The skill walks the user through backward design and produces two Markdown files — a teacher version with inline sample answers and facilitation notes, and a student version with writing space.

madeval Bundle

Run a premortem on any plan, launch, product, hire, strategy, or decision. Assumes it already failed and works backward to find every reason why. Produces a revised plan with blind spots exposed, likelihood/impact scores on each failure mode, and a concrete committed action. MANDATORY TRIGGERS: 'premortem this', 'premortem my', 'run a premortem', 'what could kill this', 'future-proof this', 'stress test this plan', 'what am i missing here', 'find the blind spots'. STRONG TRIGGERS: 'what could go wrong', 'am i missing anything', 'poke holes in this', 'where will this break', 'devil's advocate this'. Do NOT trigger on simple feedback requests, factual questions, or LLM Council requests. DO trigger when someone has a plan or commitment where the cost of being wrong is high.

fltman Bundle

Set up, scaffold, and administer agentic loops in Claude Code — headless while-loops around `claude -p`, evaluator-optimizer (generator/critic) loops, meta / prompt-refinement loops (a loop that refines the prompts another loop runs), and orchestrator fan-out. Every loop ships with non-negotiable guardrails: a verifiable exit condition, a max-iteration cap, and in-code budget enforcement. Use whenever the user wants to build, design, run, wire, or supervise loops / agent loops / "loop engineering" / nested sub-loops, or asks how to make Claude prompt Claude on a schedule or until a goal is met.

bestagentkits Bundle

Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks to score, compare, or pick a winner among completed AgentHub agents.

bestagentkits Bundle

Read, write, and browse the AgentHub message board for agent coordination. Use when the user runs /hub:board or asks to post, read, or inspect coordination messages between competing AgentHub agents.

bestagentkits Bundle

Merge the winning agent's branch into base, archive losers, and clean up worktrees. Use when the user runs /hub:merge or asks to land the winning AgentHub result and tidy the session.

bestagentkits Bundle

Memory health dashboard showing line counts, topic files, capacity, stale entries, and recommendations. Use when the user runs /si:status or asks how full or healthy the agent memory is.

bestagentkits Bundle

Use when Codex should act as the Model QA Specialist specialist from Agency Agents. Independent model QA expert who audits ML and statistical models end-to-end - from documentation review and data reconstruction to replication, calibration testing, interpretability analysis, performance monitoring, and audit-grade reporting.