Total 50,674 skills, AI & Machine Learning has 8494 skills
Showing 12 of 8494 skills
Senior Architect for @google/genai v1.35.0+. Specialist in Structured Intelligence, Context Caching, and Agentic Orchestration in 2026.
Researches topics and trends for blog content with parallel multi-agent execution. USE WHEN orchestrator invokes research phase OR user says 'research topic', 'find trends', 'gather information for blog'.
Implementing safety filters, content moderation, and guardrails for AI system inputs and outputs
Use this agent for audits, debugging nasty bugs, deep research, getting second opinions on approaches, reviewing commits for correctness, or analyzing complex problems. Invoke when you need advanced reasoning about difficult issues. Use PROACTIVELY when encountering complex bugs, architectural decisions, or when a thorough review would prevent future issues.
LangGraph workflow patterns including basic graphs, conditional routing, parallel execution, and subgraphs. Use when designing graph structure or workflow flow.
Analyze Claude Code session transcripts to improve existing skills or create new ones. Use when you want to review a past session to identify what worked, what didn't, and how to enhance skill documentation. Extracts session data and provides structured analysis prompts. Triggers on "improve skill", "analyze session", "review session", "skill improvement", "create skill from session", "skill not working", "skill missed", "skill didn't trigger", "enhance skill", "refine skill", "skill feedback", "session transcript", "what went wrong", "skill optimization", "better triggers".
Guidance for working with the Beltic KYA (Know Your Agent) ecosystem - a credential-based trust framework for AI agents. Use when: (1) Working in any Beltic repository (beltic-spec, beltic-cli, beltic-sdk, fact-python, kya-platform, wizard, nasa), (2) Implementing agent credential signing/verification, (3) Using @belticlabs/kya SDK or beltic-sdk Python, (4) Understanding agent safety certification, (5) Working with verifiable credentials for AI. Triggers on: Beltic CLI commands, agent credentials, HTTP message signatures (RFC 9421), safety scores, KYB tier verification, trust chain validation.
Create new skills for the bench-skills repo following all conventions. Use when the user says "create a new skill", "add a skill", "new slash command", or wants to extend bench-skills with additional capabilities.
Collaborative multi-agent planning with iterative deliberation. Use when creating complex plans that benefit from multiple specialist perspectives, cross-review, and consensus-building through discussion rounds.
Guidelines for writing Agent Skills. TRIGGERS: create a skill, new skill, write a skill, skill template, skill structure, review skill, skill PR, skill compliance, agentskills spec, SKILL.md format, skill frontmatter, skill best practices
Conduct in-depth research on topics and automatically generate knowledge relationship graph PDFs. After receiving a research topic, it automatically performs web research, information collection, knowledge organization, and finally generates a professional visualized relationship graph. Suitable for scenarios such as "research...and diagram", "in-depth analysis...and visualization", "generate knowledge graph", etc.
Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt needs better clarity, specificity, or structure; or when generating prompt variations for different use cases. Covers quality assessment, targeted improvements, and automatic optimization across techniques like CoT, few-shot learning, role-play, and 50+ more.