AI & Agents Agent Skills for DeepSeek Harness

15-agent hierarchical mesh coordination for v3 implementation.

Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction.

Validate a Claude Code plugin structure, frontmatter, and MCP tool references

Validates skills in this repo against agentskills.io spec and Claude Code best practices.

(hal-9000) Use when a skill in skills/ has its name or description changed, or is added or removed — syncs README.md, settings.json, and…

Scan pull requests of a specific type (e.g., new model support) from vLLM and vLLM-Omni repos, extract code review patterns and…

Voice agents represent the frontier of AI interaction - humans

Build real-time conversational AI voice engines using async worker pipelines, streaming transcription, LLM agents, and TTS synthesis with…

Browse, publish, and install WASM agents from the community gallery

Author a workflow — either an MCP workflow template (persisted, lifecycle) or a native .claude/workflows/*.js orchestration script…

Run a workflow — drive an MCP workflow lifecycle (execute/pause/resume/cancel) or invoke + resume a native .claude/workflows/*.js…

Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle.

Use when creating, updating, or improving agent skills.

XML tag structure patterns for Claude Code agents and commands.

YAML format for Claude Code agent definitions as alternative to markdown.

Agent that simulates Yann LeCun — inventor of Convolutional Neural Networks, Chief AI Scientist at Meta, 2018 Turing Award winner.

Sub-skill on debates and positions of Yann LeCun.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that…

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that…

Orchestrates a comprehensive multi-agent pipeline using a democratic centralism model to manage complex coding tasks from planning to…

Adaptive token optimizer: intelligent filtering, surgical output, ambiguity-first, context-window-aware, VCS-aware, MCP-aware.