gemini-cli-helper
Run Gemini CLI commands from Claude with correct Node version. Use when user asks to run Gemini CLI, test Gemini traces, or debug Gemini telemetry.
Run Gemini CLI commands from Claude with correct Node version. Use when user asks to run Gemini CLI, test Gemini traces, or debug Gemini telemetry.
🎯 TaskMaster Context Writer - 自動將 Agent 報告強制寫入 .claude/context/ 目錄
WCAG AA accessibility checklist and verification protocols for Somali dialect classifier dashboard. Covers keyboard navigation, screen readers, color contrast, ARIA labels, and accessibility testing procedures.
Run Claude Code in headless/programmatic mode for automation, CI/CD, and agent workflows. Use when user asks about headless mode, programmatic execution, scripting Claude, or automating Claude workflows.
Guide for creating effective skills with UV + justfile structure. This skill should be used when users want to create a new skill (or update an existing skill) that extends the agent's capabilities with specialized knowledge, workflows, or tool integrations. Skills include PEP 723 compliant Python scripts managed via justfile for consistent execution.
AI-augmented software engineering workflow based on Addy Osmani's methodology. Implements structured planning, chunked implementation, extensive context provision, strategic model selection, human oversight, granular commits, and continuous learning. Treats LLMs as pair programmers requiring clear direction rather than autonomous agents.
Create reusable agent skills for OpenCode with proper structure, frontmatter, and validation
Test, validate, and add new AI models to the eval suite. Use when user asks to add new models, test model access, check pricing, or update models.yml.
Low-resource NLP techniques specific to Somali language processing. Covers data scarcity strategies, cross-lingual transfer, morphological analysis, data augmentation for Somali, semi-supervised learning, and evaluation considerations for low-resource contexts. Auto-invokes when working on Somali NLP, low-resource language challenges, dialect classification, or language-specific modeling decisions.
Authoritative templates and scaffolding for creating agent system prompts (primary agents and subagents). This skill should be used when creating new agents, reviewing existing agent prompts for template compliance, verifying agent structure, or extracting knowledge into agent prompts. Contains YAML templates with section-by-section instructions and scaffolding scripts for generating skeleton files.
LLM guide for creating, publishing, and running Enact tools
Evaluates Claude skills against official best practices from Anthropic documentation. Use when reviewing skill quality, ensuring compliance with guidelines, or improving existing skills.
Design and implement long-term memory systems for AI agents using vector stores, knowledge graphs, and hybrid approaches. Includes benchmarks and decision frameworks. Use when building persistent agent memory, implementing RAG, designing knowledge bases, or when user mentions 'memory', 'RAG', 'vector store', 'knowledge graph', 'long-term memory', 'retrieval', or 'embeddings'.
Auto-activates when synthesizing outputs from multiple parallel sub-agents to create cohesive, integrated design with consistency checking and conflict resolution.
High-performance fuzzy matching library for filtering choices in prompts
Check and process messages from autonomous AILANG agents. Use when starting a session, after agent handoffs, or when checking for completion notifications.
Engage in critical thinking by questioning assumptions, exploring alternative perspectives, and uncovering latent topics in conversations. Use when discussions could benefit from deeper exploration, when identifying blind spots, or when broadening understanding through respectful challenge and curiosity-driven inquiry.