agent sdk agents

proma-ai/Proma

Agent

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

proma-ai/Proma

Agent

Compare two outputs WITHOUT knowing which skill produced them.

proma-ai/Proma

Agent

Evaluate expectations against an execution transcript and outputs.

ThibautMelen/agentic-ai-systems

Agent

Agent "autonomous" from ThibautMelen/agentic-ai-systems, covering 🐔 autonomous agent, diagram, the agent loop, key insight and characteristics.

ThibautMelen/agentic-ai-systems

Agent

Agent "multi-window" from ThibautMelen/agentic-ai-systems, covering 🖥️ multi-window context, diagram, when to use, implementation and flow example.

terryso/AutoQA-Agent

Agent Claude Code

You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.

terryso/AutoQA-Agent

Agent Claude Code

You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.

terryso/AutoQA-Agent

Agent Claude Code

You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.

timothywarner-org/claude-architect

Agent Claude Code

Expert Azure architecture guidance grounded in the Azure Well-Architected Framework. Use when designing new Azure solutions, reviewing existing architectures, selecting Azure services, or weighing trade-offs across reliability, security, cost, operational excellence, and performance. Example - user asks "Should I run…

timothywarner-org/claude-architect

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.

timothywarner-org/claude-architect

Agent Claude Code

Financial analysis expert specializing in startup metrics, burn rate, runway calculations, and investment decisions. Use proactively for any budget, financial projections, or cost analysis questions.

thevibeworks/claude-code-docs

Agent

Agent "archive" from thevibeworks/claude-code-docs, covering archive agent, path parameters, headers, returns and example.

thevibeworks/claude-code-docs

Agent

Agent "create" from thevibeworks/claude-code-docs, covering create agent, headers, body parameters, returns and example.

thevibeworks/claude-code-docs

Agent

Agent "update" from thevibeworks/claude-code-docs, covering update agent, path parameters, headers, body parameters and returns.

shabaraba/vibing.nvim

Agent

Read-only code navigation and analysis specialist for a project open in vibing.nvim. Use for "where is X defined/used", "what calls this function", "what's the type of this", or "what diagnostics exist here" questions — it answers using the live Neovim buffer/LSP state via vibing-nvim MCP tools instead of editing…

Caspian-Sun/claude-code-workflow

Agent Claude Code

Fix a single triaged bug (from bug-reports entries or verbal descriptions normalized by /bug-check). Locate root cause → minimal fix → run tests → return fix report. Suitable for parallel spawning by /fix when handling multiple bug reports (one bug per agent).

Caspian-Sun/claude-code-workflow

Agent Claude Code

Perform read-only code review on specified files or directories, scanning for issues per project rules (coding-style / no-hardcode / file-docs / testing), and outputting a structured report. Does not modify code. Suitable for parallel review of large directories by /review, or as an independent second-opinion check…

Caspian-Sun/claude-code-workflow

Agent Claude Code

God-mode engineering meta-auditor. Scans .claude/ + docs/ + workspace/src/, outputs structured observation reports to docs/retrospectives/. Observes and suggests only — does not modify any .claude/ or docs/ files (except its own reports). Triggered by /meta-audit command, or spawned by main agent after major…

dork-labs/dorkos

Agent Claude Code

Senior code reviewer for production readiness. Reviews completed work against plans, specs, and coding standards. Dispatched after major tasks, features, or before merge.

dork-labs/dorkos

Agent Claude Code

Runs data-heavy read-and-summarize operations in an isolated context window to prevent bloating the main conversation. Use when a task requires reading potentially large inputs (long commit logs, deep filesystem scans, aggregated logs, many-file searches) but only a small structured summary needs to flow back to main…

dork-labs/dorkos

Agent Claude Code

Specialized research expert for parallel information gathering. Use for focused research tasks with clear objectives and structured output requirements.