debugger
265Agent Cursor
Debugging specialist for errors and test failures. Use when encountering issues.
1,263 tagged agent, measured the same way as everything else here.
Browse within: agentic 86coding 68code 61vibe 60vibecoding 60chatbot 51agentic-workflow 47framework 46harness 45agent-framework 43gemini-cli 43agent-orchestration 42persona 42Multi-Agent 37
Agent Cursor
Debugging specialist for errors and test failures. Use when encountering issues.
Agent Cursor
Validates completed work. Use after tasks are marked done to confirm implementations are functional.
Agent
Deep analysis of a single pillar for agent readiness assessment.
Agent
Detects bugs, logic errors and runtime issues.
Agent
Detects inconsistencies in code style, patterns, and conventions.
Agent
Validates issues found by other agents and filters out false positives.
Agent
You are a design system extractor. Given a finished canvas.html, you read the markup + inline styles + computed style intent, and emit a Design System JSON document that captures color, typography, spacing, shadow, radius — plus recurring composition idioms.
Agent
A research helper that gathers and verifies outside information for another coding agent working on a design or written deliverable.
Agent
You are a visual design reviewer. Your job is to look at a rendered HTML design (a deck, landing page, or presentation) and tell the parent agent whether it looks right — and if not, what concretely to fix, page by page.
Agent
Part of twincat-mcp-agent
TwinCAT ST Master — Expert in Beckhoff IEC 61131-3 ExST development. Use for any TwinCAT PLC programming task, POU creation, GVL editing, function block design, compiler error fixes, and EtherCAT/I/O configuration.
Agent Claude Code
Use this agent when you need to test Terminal User Interface (TUI) applications, particularly vibecore or other Textual-based apps. This agent specializes in automated testing using iTerm MCP tools, executing test specifications, and generating comprehensive test reports. The agent handles the unique challenges of TUI…
Agent
Convert PRDs into development task lists.
Agent
Execute task lists with sequential commits.
Agent
Implement code, debug, refactor, optimize.
Agent
Create PRDs through structured discovery.
Agent
Convert PRDs into development task lists.
Agent
Execute task lists with sequential commits.
Agent Claude Code
Work on the Python FastAPI backend — sessions, bridge logic, agent runner, policy engine.
Agent Claude Code
Work on the reference UI and example frontends (React, Vite, Tailwind, AG-UI client).
Agent Claude Code
Debug ACP↔AG-UI protocol translation issues by tracing events through the bridge layers.
Agent
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
Agent
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
Agent
The skills under skills/ are staged into a sandbox and run autonomously against a target repo — no human is in the loop mid-run. A skill exists to wrangle determinism out of a stochastic agent: the goal is predictability, the agent taking the same process every run (not producing the same output). Everything below…
Agent
Codebase explorer — answers "where is X?" / "find the code that does Y" / "list all callers of Z". Read-only grep + glob + read, no memory injection.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: