Claude Skills

Detect quiet failures in LLM agents - tool skipping, gibberish outputs, infinite loops, and degraded quality. Use when agents appear to work but produce incorrect results.

Real-time data streaming with SSE, WebSockets, and ReadableStream. Use when implementing streaming responses, real-time data updates, Server-Sent Events, WebSocket setup, live notifications, push updates, or chat server backends.

Progressive Web App patterns with Workbox 7.x, service worker lifecycle, offline-first strategies, and installability. Use when building PWAs, service workers, or offline support.

Graph-first memory orchestration - knowledge graph (PRIMARY, always available) with optional mem0 cloud enhancement for semantic search. Use when designing memory orchestration or combining graph and mem0.

Visualize local knowledge graph as a Mermaid diagram with 8 entity types and 8 relation types from the decisions memory store.

Scene-by-scene narration scripts for videos. Use when writing voiceover scripts, adding timing markers, or creating CTA patterns for demos

Best practices for HeyGen - AI avatar video creation API. Use when creating AI avatar videos, generating talking head videos, or integrating HeyGen with Remotion.

GitHub release workflow with semantic versioning, changelogs, and release automation using gh CLI. Use when creating releases, tagging versions, or publishing changelogs.

Scene-by-scene narration scripts for videos. Use when writing voiceover scripts, adding timing markers, or creating CTA patterns for demos

Security patterns for LLM integrations including prompt injection defense and hallucination prevention. Use when implementing context separation, validating LLM outputs, or protecting against prompt injection attacks.

LangGraph human-in-the-loop patterns. Use when implementing approval workflows, manual review gates, user feedback integration, or interactive agent supervision.

Use when creating or improving golden datasets for AI evaluation. Defines quality criteria, curation workflows, and multi-agent analysis patterns for test data.

Distributed locking patterns with Redis and PostgreSQL for coordination across instances. Use when implementing exclusive access, preventing race conditions, or coordinating distributed resources.

Transitional intro cards between video scenes. Use when adding "Coming Up Next" cards, scene transitions, or visual breathing room in demos

Pre-production planning for tech demo videos. Use when planning scenes, structuring narrative flow, or applying AIDA framework to video content

Python asyncio patterns with TaskGroup, structured concurrency, and modern 3.11+ features. Use when implementing concurrent operations, async context managers, or high-performance async services.

SQLAlchemy 2.0 async patterns with AsyncSession, async_sessionmaker, and FastAPI integration. Use when implementing async database operations, connection pooling, or async ORM queries.

RICE, ICE, WSJF, MoSCoW and other prioritization frameworks for product backlogs. Use when scoring features, ranking initiatives, or deciding what to build next.

Query decomposition for multi-concept retrieval. Use when handling complex queries spanning multiple topics, implementing multi-hop retrieval, or improving coverage for compound questions.

Multi-PR development for large features. Stack dependent PRs, manage rebases, and get faster reviews on smaller changes. Use when creating stacked PRs.

Use when completing tasks, code reviews, or deployments to verify work with evidence. Collects test results, build outputs, coverage metrics, and exit codes to prove work is complete.

Use when assessing task complexity, before starting complex tasks, or when stuck after multiple attempts. Provides quality-gates scoring (1-5) and escalation workflows.

Safe database schema changes without downtime using expand-contract pattern and online schema changes. Use when deploying schema changes to production without service interruption.

[BUILD] Comprehensive verification with parallel test agents. Use when verifying implementations or validating changes.