AI & Agents Agent Skills for Devin Desktop

Analyzes feedback logs to identify patterns and suggest improvements to review skills.

Review and analyze a skill against best practices for length, intent scope, and trigger patterns

Recursive Language Models (RLM) CLI - enables LLMs to recursively process large contexts by decomposing inputs and calling themselves over…

Run reproducible DeepSWE coding-agent benchmark evaluations through OpenRouter and mini-swe-agent.

Cost-safety discipline for paid AI / inference APIs: treat $-cost as a third complexity dimension alongside time and space.

Auto-generate project context for AI sessions.

Display a comprehensive runtime environment report covering detected provider, available tools, AIWG version, and installed frameworks

Safely remove plugin assets (skill/agent/rule/script/hook) with dependency detection and reference cleanup.

AUTO-INVOKE when user mentions SDLC, requirements, architecture, ADR, use case, user story, test plan, phase gate, inception, elaboration…

Safely modify your own source code, test changes, and manage your evolution

SONA self-optimizing neural architecture with ReasoningBank trajectory learning, EWC++ anti-forgetting, and reinforcement learning…

Initial CWF configuration to standardize environment/tool contracts before workflow execution: hook group selection, external tool…

Load top-performing Shinka programs into agent context using `shinka.utils.load_programs_to_df`, and emit a compact Markdown bundle for…

Use when a task requires exhaustive unabridged output, complete files, or strict prevention of placeholders and skipped code.

To create new CLI skills following Anthropic's official best practices with zero manual configuration.

Comprehensive guide for creating and managing skills in Claude Code with auto-activation system, following Anthropic's official best…

Simulator.Company digital-twin & actor-agent specialist — talk to an agent AS an agent and delegate work to it.

Skill package manager for AI Agents — install, manage, and publish Agent Skills.

Enhance a mega-code skill — defaults to the remote server flow; pass --hitl for the local human-in-the-loop A/B flow.

Agent that simulates Geoffrey Hinton — Godfather of Deep Learning, 2018 Turing Award winner, creator of backpropagation and Deep Belief Netw

Iteratively improve a Claude Code skill using the skill-reviewer agent until it meets quality standards.