AI & ML

agentient Skill

Pydantic V2 data modeling with strict mode enforcement for type safety. PROACTIVELY activate for: (1) Creating data models or schemas, (2) Validating API request/response types, (3) Building configuration classes, (4) Defining data contracts, (5) Implementing DTOs. Triggers: "pydantic", "BaseModel", "ConfigDict", "Field", "validator", "model_dump", "strict mode", "data model"

agentient Skill

[STUB - Not implemented] Intelligent document chunking and ingestion with multiple strategies for Vertex AI RAG Engine. PROACTIVELY activate for: [TODO: Define on implementation]. Triggers: [TODO: Define on implementation]

agentient Skill

Comprehensive database schema analysis using 5-expert panel evaluation. PROACTIVELY activate for: (1) schema review, (2) data modeling decisions, (3) database design evaluation, (4) migration planning, (5) normalization analysis. Triggers: "evaluate schema", "review schema", "database design", "data model review", "schema analysis", "evaluate database"

agentient Skill

For long-running operations, stream results incrementally with progress reporting. PROACTIVELY activate for: (1) streaming tool results, (2) tool orchestration, (3) cancellation and timeout handling. Triggers: "streaming", "tool orchestration", "progress reporting"

agentient Bundle

Designs multi-model AI research strategies across 9 research patterns for Claude Opus 4.6, Gemini 3.1 Pro Deep Research, and optionally GPT-5.2 Deep Research (with site restrictions and mid-session intervention) or GPT-5.2 Chat. Generates copy-pasteable prompts optimized per model with pattern-aware role assignment, a consolidation manifest for downstream synthesis, and a merge prompt for consolidating outputs. Accepts Research Request Specification from research-interviewer upstream. Triggers on "create research brief", "research plan", "multi-model research", "research prompts for Claude/Gemini/OpenAI", "design research strategy", "consolidate research outputs", "synthesize research results", "research best practices for...", "best practices for [technology]", "create a best practices guide for...", "research [technology] patterns", "document [technology] best practices", "compare X vs Y", "landscape of [domain]", "compliance requirements for [topic]", "ROI analysis for [decision]". Modes: DUAL (Claude+Gemi

goldenzero Bundle

Attribute health outcomes to specific clinical interventions, programs, or policy changes using causal inference methods. Use when determining which interventions drove observed improvements, allocating credit across concurrent programs, or defending outcome claims to payers and regulators.

fierzone Bundle

CRITICAL - Before ANY file write, audit loaded skills for violations. Auto-report via feedback command.

fierzone Bundle

Universal standards for version control, branching, and team collaboration.

fierzone Bundle

Universal security protocols for building safe and resilient software.

fierzone Bundle

Idiomatic TypeScript patterns for clean, maintainable code.

ricable Bundle

Cognitive kernel plugin for LLM augmentation with working memory, attention control, meta-cognition, and scaffolding. Use when managing agent working memory, controlling attention across long contexts, enabling self-reflective reasoning, or structuring complex multi-step cognitive tasks.

ricable Bundle

Quantum-inspired optimization plugin with simulated annealing, QAOA, Grover search, dependency resolution, and schedule optimization. Use when solving combinatorial problems, optimizing task schedules, resolving complex dependency graphs, or finding optimal agent configurations.

ricable Bundle

Neural coordination plugin for multi-agent swarm intelligence using SONA, GNN, and attention mechanisms. Use when optimizing swarm communication, coordinating agent behavior with neural routing, applying graph neural networks to agent topologies, or using attention-based consensus.

waterplanai Bundle

Parallel research-to-deliverable orchestration via multi-agent multiplexer. Single orchestrator fans out to agents, all context funnels back. Triggers on keywords: mux, orchestrate, multi-agent, parallel research, fan-out, multiplex

agentient Skill

Test JSON-RPC 2.0 protocol compliance and Pydantic schema validation for MCP servers. PROACTIVELY activate for: (1) writing MCP server tests, (2) protocol compliance validation, (3) async tool testing. Triggers: "mcp testing", "protocol compliance", "pytest asyncio"

fierzone Skill

Universal standards for high-performance software development across all frameworks.

fierzone Bundle

Standards for maintaining code hygiene, automated checks, and testing integrity.

fierzone Skill

Foundational "High-Density" standard for token-optimized agent instructions and CLI-based automated activation.

bananayong Skill

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

bananayong Bundle

Guide for designing and creating effective Claude Code custom agents (subagents). Use when users want to create, update, or optimize agents defined in .claude/agents/. Triggers on requests like "make an agent", "create a subagent", "build a reviewer agent", "add a custom agent", or "define an agent for code review".

bananayong Skill

Consult Codex CLI (OpenAI) to get a second opinion on difficult problems. Use when facing complex debugging, architectural decisions, algorithm design, or any hard problem where cross-checking with another AI model would be valuable. Triggers on requests like "ask codex", "get a second opinion", "discuss with codex", "cross-check this", or when you determine that consulting another model would help solve a particularly challenging task.

goldenzero Bundle

Explain data traceability and lineage for financial institution data assets. Use when documenting data flows for regulatory reporting, tracing data from source to consumption, assessing data quality risks, supporting model risk management, or responding to BCBS 239 and FFIEC data governance expectations.

goldenzero Bundle

Document and explain model risk management decisions aligned with SR 11-7 and OCC 2011-12 supervisory guidance. Use when creating model validation reports, model inventory documentation, model risk assessments, ongoing monitoring plans, or responding to MRM examination findings.

waterplanai Skill

Short alias for ac-tools-dry-run. Applies the same dry-run workflow and constraints to the provided command or prompt. Triggers on keywords: dr, dry run shorthand, preview safely

waterplanai Skill

Installs and configures VoiceMode MCP for voice interactions in the target client. Triggers on keywords: setup voice, voice mode, install voicemode, configure voice

waterplanai Skill

Runs a delegated command or prompt in dry-run mode by setting session status, preserving read-only behavior, and resetting state after execution. Triggers on keywords: dry run, simulate, preview changes, safe mode

bananayong Skill

Core package for defining schemas, catalogs, and AI prompt generation for json-render. Use when working with @json-render/core, defining schemas, creating catalogs, or building JSON specs for UI/video generation.

bananayong Skill

Set up and configure the agent-sandbox development environment

peterbamuhigire Bundle

Use when implementing or reviewing iOS AI and ML features with Apple on-device frameworks, model evaluation, and privacy controls; use ios-architecture for general module boundaries.

peterbamuhigire Bundle

Use when securing an AI/LLM-powered feature against prompt injection, cross-tenant data leakage and tenant isolation failures, jailbreaks, and adversarial inputs. Covers PII scrubbing before model calls, output validation, rate limiting, audit logging, and DPPA/GDPR compliance for AI data flows.

peterbamuhigire Bundle

Use when designing or building an AI-enhanced web app with chat, RAG, MCP tools, streaming, provider abstraction, feature gates, token budgets, and output guardrails.

waterplanai Bundle

Browser automation via playwright-cli. Token-efficient alternative to Playwright MCP - uses CLI commands through Bash instead of MCP tool schemas. Supports navigation, interaction, screenshots, video recording, and session management. Triggers on keywords: browser, e2e, playwright, screenshot, navigate, click, type, test browser, visual test

x-cmd Skill

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

peterbamuhigire Skill

Use when specifying one AI-powered feature end to end, including model choice, prompt and context contracts, output schema, fallbacks, human oversight, UX states, and evaluation.

peterbamuhigire Bundle

Use when building features that answer questions from private data, documents, policies, or time-sensitive information — RAG architecture, chunking strategies, hybrid search, re-ranking, vector databases, evaluation, agentic RAG, multimodal RAG...

peterbamuhigire Bundle

Use when designing or building an LLM gateway for provider abstraction, tenant-aware routing, fallbacks, quotas, residency, audit logging, cost capture, and kill-switch enforcement.