All Skills

Automate Ambient Weather tasks via Rube MCP (Composio). Always search tools first for current schemas.

Patterns for parallel subagent execution using Task tool with run_in_background. Use when coordinating multiple independent tasks, spawning dynamic subagents, or implementing features that can be parallelized.

Use when errors are unclear, flaky, or regressions occur; apply a disciplined debugging loop in VS Code Copilot Agent mode.

Gemini and Imagen visual prompting specialist that transforms rough concepts into narrative-rich prompts tuned for Google generation workflows. Use when users explicitly target Gemini or Imagen and need semantically precise visual direction.

--- name: ai-image-generation description: Mastery of AI image generation across the full spectrum: Midjourney for aesthetic perfection, Flux for prompt adherence, DALL-E 3 for concept clarity, Stable Diffusion for control, and Imagen 3 for photorealism. This skill transforms text into visual real

Session-scoped hook lifecycle management with enable/disable/status controls, execution profiling, and color-coded performance alerts.

Use after brainstorming completes - writes validated designs to docs/design-plans/ with structured format and discrete implementation phases required for creating detailed implementation plans

Automate ActiveCampaign tasks via Rube MCP (Composio). Always search tools first for current schemas.

VMCA prompt compiler that translates scene descriptions into high-weight Traditional Chinese prompts optimized for video generation workflows using positive-only phrasing. Use when users ask for direct prompt-writing instead of full directing plans.

Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.

Keep cyclomatic complexity low; flatten control flow, extract helpers, and prefer table-driven/strategy patterns over large switches

Check crypto tokens for rug pull risk and scams using DEX Ranger. Use when the user wants to check a token's trust score, safety, warnings, or red flags on Ethereum (ETH), Solana (SOL), BSC, or TON. Also use when the user provides a token contract address and wants to know if it's safe, a scam, or a rug pull.

Orchestrate hierarchical multi-agent research with lead agents, sub-agents, critical review, and synthesis. Use for deep investigation tasks, research projects, complex analysis, or when exploring unfamiliar topics thoroughly.

Build and structure Java Spring Boot applications with modern best practices. Use when creating REST APIs, entities, repositories, services, controllers, DTOs, custom validators, or when the user asks about Java project structure, Spring Boot patterns, or backend architecture.

Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities". Do NOT use for accessibility (use web-accessibility), SEO (use seo), performance (use core-web-vitals), or comprehensive multi-area audits (use web-quality-audit).

High-level principles for isolating data between tenants.

Simplify and clean up code after changes are complete. Reduces complexity, improves readability, and ensures consistency.

Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Use when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for example: orphaned sensitive code, security maintainers, CODEOWNERS reality checks for risk, sensitive hotspots, or ownership clusters). Do NOT use for general maintainer lists, non-security ownership questions, or threat modeling (use security-threat-model).

Processes bug reports from markdown files exported from any ticket system (Linear, GitHub Issues, Bugzilla, etc.), extracts reproduction steps, error logs, and environment details. Manages debugging workflow through Detective Methodology including reproduction, investigation, root cause analysis, fix verification, and regression testing. Use when handling bug reports, debugging issues, or tracking bug resolution.

Address review and issue comments on the open GitHub PR for the current branch using gh CLI. Use when user says "address PR comments", "fix review feedback", "respond to PR review", or "handle PR comments". Verifies gh auth first and prompts to authenticate if not logged in. Do NOT use for creating PRs, CI debugging (use gh-fix-ci), or general Git operations.

Backend-specialised design skill in the SSDAM pipeline. Reads architecture-design (and optionally schema-design) to produce a DDD-structured backend specification per domain. Mandatory components per domain are domain/entity, domain/facade, api/controller, and service/store. All other sub-layers (vo, event, exception, shared, request, response, mapper, proxy, config, application service) are optional and included only when needed.

--- name: ai-for-learning description: Expert in applying AI to education - AI tutors, personalized learning paths, content generation, automated assessments, and adaptive learning systems. Covers practical implementation of AI to enhance (not replace) human instruction. Use when "ai tutor, ai for

--- name: qa description: Quality Assurance. Designs and executes tests, validates acceptance criteria, reports bugs. Works with Vitest (frontend) and Jest (backend). Reports to QAL. Use when: (1) Writing or executing test cases, (2) Test automation with Vitest, Jest or Playwright, (3) Validating

--- name: ai-code-generation description: Comprehensive patterns for building AI-powered code generation tools, code assistants, automated refactoring, code review, and structured output generation using LLMs with function calling and tool use. Use when "code generation, AI code assistant, functio