agentic-ai agents

agentdecksdk/agentdeck

Agent Claude Code

Runs ONE narrow entropy scan over agentdeck (narrative comments, dead code, duplicate helpers, or pattern drift) and opens one small evidence-backed PR.

fabioc-aloha/Alex_Skill_Mall

Agent Claude Code

Plans and executes multi-file changes by mapping context, tracing dependencies, and sequencing modifications.

endorphin-ai/claude-code-teams

Agent Claude Code

System Architect agent that designs APIs, DB schemas, component trees, and reviews code. Use when: Designing system architecture for a new feature Creating API contracts and database schemas Reviewing code against design specifications Examples: User: "Design the backend and frontend architecture" Assistant: "I'll…

erniker/understudy

Agent Claude Code

Frontend Developer — user interfaces, accessibility, UX.

geoffmcc/sidekick

Agent Claude Code

Use Sidekick's live knowledge, structured memory, MCP tools, and governed remote capabilities for verified project, infrastructure, automation, debugging, research, deployment, and durable Agent work.

mattmre/EVOKORE-MCP-PUBLIC

Agent Claude Code

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

MarieLynneBlock/arcanum-artifex

Agent Claude Code

Guidelines for creating high-quality Agent Skills for GitHub Copilot.

sanyaden/agents0826

Agent Claude Code

On-demand retrieval from the Neo4j memory graph (project-scoped, hybrid vector+fulltext search). Use when you need prior decisions, conventions, gotchas, or facts about the current project or shared knowledge that are NOT already in context — e.g. "what did we decide about X", "how do we usually do Y here", "any known…

fullstack455/deer-flow

Agent Claude Code

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

felipefontoura/spec-driven-development-book

Agent Claude Code

Produces requirements.md and design.md from an approved idea or feature request. Use for the WHAT and the HOW — user stories, EARS requirements, data models, API contracts, technical decisions with rationale, and the requirement→design traceability map. Never writes implementation code.

Enovatr-Labs/SpecRoute

Agent Claude Code

This directory contains the 12 Claude Code agents that implement the SpecRoute skeleton. They are project-internal - they build SpecRoute itself, not consumer-facing templates that ship as artifacts.

Sharrmavishal/operating-kit

Agent Claude Code

Comprehensive pre-ship review of all changes since the last deploy or a specified commit. Walks correctness, atomicity/races, error handling, data-store hygiene, security, type safety, tests, integration, performance, observability, and any project-specific invariants. Use after any sprint and always before deploying.

raja21068/AutoResearch

Agent Claude Code

Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.

berekvolgyipeter/dotclaude

Agent Claude Code

Expert documentation specialist. Proactively updates documentation when code changes are made, ensures README accuracy, and maintains comprehensive technical documentation. Be sure to give this subagent information on the files that were changed so it knows where to look to document changes. Always call this agent…

thomas-powers-jr/cadence

Agent Claude Code

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

br3eze-code/br3eze-code

Agent Claude Code

Upgrade agents/ask-engine.js into the central, observable orchestration boundary for AgentOS while preserving existing behavior and keeping CLI/PWA/channel adapters thin.

Claritune/mutantx

Agent Claude Code

MutantX mutation testing agent — autonomously runs mutation testing on a project and produces a report.

tonik173/generative-ai-explained

Agent Claude Code

Behaviour is assembled fresh every turn, out of text.

Shad0wMazt3r/The-Scaffolding

Agent Claude Code

Security testing workflow assistant for recon, web, network, mobile, pwn, crypto, reverse engineering, and forensics phases.

tertiarycourses/TGS-2020503207-AI-Vibe-Coding-for-Multi-Agents-System

Agent Claude Code

Quality reviewer for WSQ courseware — audits the slide deck (PPT), Lesson Plan (LP) and Learner Guide (LG) against the Tertiary Infotech WSQ house standards. Use PROACTIVELY after any courseware (re)generation or edit, before reporting completion to the user.

Claudedidthis/claude-my-network-engineer

Agent Claude Code

Domain expert for the UniFi local Network Integration API and UniFi Protect API on a UDM running UniFi OS 5.x. Use when implementing or debugging tools/unificlient.py, when API responses don't match expectations, when an endpoint returns an unexpected shape, or when deciding which API surface (Network Integration v1…

iamironz/ai-config-bundle

Agent Claude CodeOpenCode

The research equivalent of codebase-analyzer. Use this subagenttype when wanting to deep dive on a research topic. Not commonly needed otherwise.

ahmettugur/agentic-customer-support-bot

Agent Claude Code

Sen ResponseAgent'sın. Diğer ajanlar tarafından sağlanan yanıtı biçimlendirip kullanıcıya anlaşılır, samimi ve empatik bir şekilde iletmekle görevlisin.

jaroslavsoucek-art/Giovanni

Agent Claude Code

Executes the predictive-layer slash commands in isolated context — /branch-out (active simulation), /shadow-review (quarterly verdict pass with adversarial lookback), /calibration-report (monthly accuracy aggregation). Carries prediction-architect's 8 binding principles verbatim. Sub-mode selection driven by caller.…