Voice AI agent skills and MCP tools for Bland AI. Make phone calls, manage personas, knowledge bases, pathways, and more. Use when the user wants to build, test, or manage AI-powered phone agents.

Onboard a Vapi voice agent by calling +1 (443) 391 9140 and describing your business in 60-90 seconds. Generates YAML config, materializes files into your IDE, and (optionally) wires the agent to a Stripe payment-link + Telegram notifier with a cited.md audit trail. Cross-tool support for Claude Code, Cursor, Copilot, and Gemini CLI.

GraphQL Federation skill for creating correct federation subgraphs. Use when: (1) Creating new federation subgraphs, (2) Adding entities with @key directives, (3) Extending types across subgraphs, (4) Using federation directives (@shareable, @external, @override, @provides, @requires, @inaccessible, @interfaceObject, @authenticated, @requiresScopes), (5) Debugging composition errors, (6) Understanding federation rules and patterns. MANDATORY TRIGGERS: federation, subgraph, @key, entity, federated graph, supergraph, GraphQL composition, router schema

Use when working in the Rabbit Hole repository to start Docker services, run the backend and frontend, verify Aerospike and Airbyte wiring, and recover the demo stack quickly before a live demo.

Phalanx runs parallel-fork CVE remediation on a GitHub repository. Paste a repo URL, and the skill detects critical CVEs in the dependency tree, forks the dependency state N ways via Ghost, validates each hypothesis in isolated InsForge backends, cancels false positives mid-flight via Redis Pub/Sub, converts the Dockerfile to a Chainguard zero-CVE base, and publishes a signed evidence chain to cited.md. Use when the user asks to scan a repository for vulnerabilities, remediate a CVE autonomously, generate an SBOM with attestation, or produce a legally-defensible security remediation record. Also use for keywords like "CVE", "supply chain attack", "dependency audit", "zero-day remediation", "SBOM", "Sigstore", or "security remediation."

Evaluate, score, and systematically improve prompts in the codebase. Identifies weak prompts, generates test cases, scores outputs, and proposes optimized versions. Use when the user says "improve this prompt", "why is the AI doing X", "eval my prompts", or "optimize the agent".

Query a live San Francisco situational awareness system. Use this skill when the user asks about current SF conditions — aircraft overhead, active fire/police/EMS incidents, Muni transit, radio scanner activity, traffic events, or system health. Connects to the Monitoring the Situation REST API.

A full end-to-end Kaggle competition skill. Use this skill whenever a user mentions a Kaggle competition, ML contest, data science challenge, or competitive modeling event — even casually (e.g., "I joined a Kaggle competition", "help me with this ML challenge", "I want to climb the leaderboard"). This skill guides a solo competitor or team through every phase: competition intake, dataset access, exploratory data analysis, feature engineering, model development, ensembling, and final submission. Adapts to the user's proficiency level. Works in Claude Code, Claude.ai, and any coding agent that supports skills. Trigger this skill even when the user only mentions one phase (e.g., "help me with EDA for my Kaggle comp") — always load the full skill to understand context and jump in at the right phase.

Audit the overall code quality, architecture, and maintainability of a project or file and give an honest, unfiltered assessment. Use when the user asks "is this good?", "what do you think of this codebase?", or wants a holistic review before shipping.

Use when adding authentication to Vue.js 3 applications (login, logout, user sessions, protected routes) - integrates @auth0/auth0-vue SDK for SPAs with Vite or Vue CLI

Generate a structured implementation plan before writing any code. Produces a spec with requirements, data model, API surface, edge cases, and open questions. Use when starting a non-trivial feature, when the user says "plan this out", or before any implementation that touches more than 2 files.

Build and configure an AI-powered phone hotline for loan support using Bland AI, Auth0, and Senso. USE FOR: setting up AI phone agents for lending, creating voice-based loan support systems, integrating Auth0 passwordless OTP with Bland AI voice agents, connecting Senso knowledge bases to phone call workflows, building fintech customer service hotlines. NOT FOR: general web app development, non-voice chatbots, or projects unrelated to phone-based loan support.

Agentic meta-search for short-term rentals. Query Airbnb, VRBO, HomeAway, and direct-booked sites through one skill. Returns structured listings with per-platform pricing and split-stay itineraries when no single booking covers the date range. Redis-backed agent memory lets the skill personalize future searches.

Texas Hold'em poker intelligence — hand evaluation, pot odds, position strategy, and live player profiling for AI agents

Hackathon MVP for an entity intelligence cache — query → Redis semantic cache → Ghost (Postgres) entities → Tinyfish Search + mock retrieval → distillation → deltas → synthesis; optional Senso KB publish for cited.md pipeline.

Builds an autonomous iterative research loop that narrows a wide uncertainty/exposure range toward a user-defined target by issuing Google searches, extracting evidence from results, re-estimating the range from accumulated evidence, and repeating until converged. Use when the user wants to implement autonomous research that progressively reduces uncertainty toward a quantified goal — risk analysis, market sizing, due diligence, literature review, or any domain where a wide estimate must be narrowed with real evidence.

the best framework to build agent for claude code.

Use when adding authentication (login, logout, protected routes) to Fastify web applications - integrates @auth0/auth0-fastify for session-based auth. For stateless Fastify APIs use auth0-fastify-api instead.

Use this skill to scan URLs and inbox messages for scams targeting older adults, monitor an inbox autonomously, publish results to cited.md, and enforce x402-style payment rails for ElderShield.