ai agents

weidu12123/Liyuan

Agent Claude Code

Fast codebase recon that returns compressed context for handoff to other agents.

damianvtran/local-operator

Agent Claude Code

Use Local Operator agent profiles, roles, and subagents: discover, create, select, interact, delegate, and choose the correct collaboration mode.

fabriqaai/specs.md

Agent Claude Code

You are the Inception Agent for AI-DLC (AI-Driven Development Life Cycle).

Conceptual-Machines/magda-core

Agent Claude Code

Reviews new GitHub issues, identifies actionable problems vs false alarms, applies labels, requests missing info, and routes issues based on tags/exceptions.

lornshrimp/Lorn.NovelWriteSkills

Agent Claude Code

An internet research agent for novel writers. It gathers real information about trends, publishing platforms, specialist topics, settings, people who inspired characters, writing methods, and reader feedback across languages and online communities.

Azure-Samples/mcp-agent-langchainjs

Agent Claude Code

Help engineers learn about the codebase and programming concepts of this project.

SebastienDegodez/copilot-instructions

Agent Claude Code

Expert presentation strategist and creative advisor for creating impactful Marp presentations with strategic content and visual design.

eli-labz/Godcoder

Agent Claude Code

Independent checker for loop-produced changes. Rejects unless tests pass and scope is minimal. Never implement fixes.

erans/lunaroute

Agent Claude Code

Use this agent when you need expert review of Rust code, particularly web services, HTTP implementations, or security-critical systems. Trigger this agent after completing logical code units like implementing HTTP handlers, API endpoints, authentication systems, middleware, database operations, or any Rust web…

verseles/codewalk

Agent Claude CodeOpenCode

Review OpenCode releases and assess CodeWalk impact.

autohandai/code-cli

Agent Claude Code

Review maintainability risks and prioritize focused cleanup.

echoVic/blade-code

Agent Claude Code

Agent "README" from echoVic/blade-code, covering claude code subagents collection, available subagents, development & architecture, language specialists and infrastructure & operations.

Zettelgarden/Zettelgarden

Agent Claude Code

Use this agent when you need to develop, modify, or troubleshoot Go backend code, including API endpoints, database operations, middleware, authentication, or any server-side functionality. Examples: Context: User needs to add a new API endpoint for user preferences. user: 'I need to add an endpoint to save user…

vericontext/vibeframe

Agent Claude Code

End-to-end tester for the current VibeFrame CLI. Use when asked to test everything, run full tests, or verify the repo works.

idavidov13/agentic-playwright

Agent Claude Code

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

codingagentsystem/cas

Agent Claude Code

Internal agent for verifying task completion. Spawned automatically on task close. Do not invoke directly.

sammcj/agentic-coding

Agent Claude Code

Implementation research on a specific named software library, framework, package, SDK, CLI, or API: usage, current best practices, version/compatibility facts, and source-traced code. Use for "how do I implement X" or "which package for Y". Not for general web research, market comparison, conceptual explainers, or…

crisnahine/rails-ai-context

Agent Claude Code

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

bobmatnyc/claude-mpm

Agent Claude Code

All Engineer agents inherit these common patterns and requirements.

arbiterForge/codeArbiter

Agent Claude Code

INTERNAL SMARTS analyst dispatched by the decision-variance skill. Produces a SMARTS analysis and recommendation for one (artifact-position, scaffold-evidence) pair. Never decides — the user decides. Never dispatch directly.

Goldziher/ai-rulez

Agent Claude Code

Use when reviewing code changes for quality, security, and convention compliance.

chaohong-ai/ai-auto-work

Agent Claude Code

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

NikiforovAll/github-copilot-rules

Agent Claude Code

Perform a thorough code review with prioritized, actionable feedback.

Menfre01/waveloom

Agent Claude Code

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