Agent Skills Hub

stop

Gracefully pause or close sessions: harvest context, archive work, verify features, and settle AtlasCoin bounties. Use when finishing for the day or wrapping up tasks.

cross-plugin-detective

Standardized detective skill integration for agent roles. Maps agents to code-analysis skills and enforces claudemem usage for memory-indexed code investigation.

subtask

Parallel task orchestration CLI for AI workers using isolated git workspaces.

using-superpowers

The foundational skill for the Superpowers methodology. Ensures agents correctly identify and invoke required development skills before starting any task or conversation.

dev

Development and maintenance of the PWAFire library: build PWA API modules, handle feature detection, manage testing, and contribute to codebase following strict sync/async patterns and error handling requirements.

agent-architecture

Implement production-grade AI agents with LangGraph, tool-calling guardrails, SSE streaming, and episodic memory. Includes anti-patterns, fix pairs, and stateful architecture patterns.

eval-harness

Official evaluation framework for AI agent sessions, implementing Evaluation-Driven Development (EDD) principles to ensure reliability.

roadmap-web-visualization

Visual web workspace for roadmap management, providing interactive kanban boards and graph-based dependency views for task planning and project progress tracking.

reverse-engineering-api

Reverse engineer web APIs by capturing browser traffic (HAR files) and generating production-ready Python API clients for automation and data extraction.

create-skill

Standardizes the process of creating and maintaining reusable Claude Code skills for packaging developer workflows and domain expertise.

tpmjs-tool-creator

Development guide for creating and publishing TPMJS tools using the blocks CLI, AI SDK v6, and npm registry patterns.

evaluating-code-models

Evaluate code generation models using BigCode Evaluation Harness. Benchmarks include HumanEval, MBPP, and MultiPL-E with pass@k metrics for multi-language coding models.