Convert approved plans into intent-based beads with self-assessment gate. Each bead is a work package for a sub-agent that loads surgical context to implement. No source code in beads.

Browser automation in Cursor IDE using MCP protocol server `cursor-ide-browser`. Use when (1) Automating web interactions in Cursor IDE, (2) Navigating web pages, (3) Clicking buttons or links,...

This skill should be used ONLY when the user asks to update README.md, CLAUDE.md, AGENTS.md, or CONTRIBUTING.md. Trigger phrases include "update README", "update context files", "init context",...

Expert skill for AI model quantization and optimization. Covers 4-bit/8-bit quantization, GGUF conversion, memory optimization, and quality-performance tradeoffs for deploying LLMs in...

Execute approved beads using sub-agent model. Each bead is a work package - agent loads surgical context, designs, implements, and verifies. Continues until feature complete.

Use when user needs security incident response, operational incident management, evidence collection, forensic analysis, or coordinated response for outages and breaches.

Expert in SQLCipher encrypted database development with focus on encryption key management, key rotation, secure data handling, and cryptographic best practices

Guidance for 50+ specialized Wolf agent roles with responsibilities and collaboration patterns

Advanced information retrieval specialist combining systematic search strategies, multi-platform expertise, and precision filtering techniques. Excels at finding specific, high-quality information...

Vue 3 and Nuxt 3 for JARVIS AI Assistant UI development with security-first patterns

Create System Requirements (SYS) - Layer 6 artifact defining functional requirements and quality attributes

Structured review process for Remotion video implementations. Analyzes spec compliance, detects common timing/easing issues, validates asset quality, and provides prioritized revision lists. Use...

Systematic root cause analysis for bugs and unexpected behavior. Investigates, isolates, and either fixes simple issues directly or escalates to appropriate workflow.

Verify compliance with OWASP Top 10 2021 security standards. Use when

Look up current research information using Perplexity Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter. Automatically selects the best model based on query complexity. Search...

Behavioral archetypes for automatic agent adaptation based on work type

Build reliable third-party API integrations including OAuth, webhooks, rate limiting, error handling, and data sync. Use when integrating with external services (Slack, Stripe, Gmail, etc.),...

Build AI agents with Pydantic AI (Python) and Claude SDK (Node.js)

Generate and iteratively refine implementation plans from an initial spec/prompt. Takes a specification as input, generates an initial plan, then refines it through parallel multi-reviewer passes...

|