llm agent agents

areal-project/AReaL

Agent Claude Code

RL algorithm expert. Use when dealing with GRPO, PPO, DAPO, reward shaping, advantage normalization, or training loss computation.

areal-project/AReaL

Agent Claude Code

Code verification agent. Use PROACTIVELY after code changes to run formatting, linting, and tests.

areal-project/AReaL

Agent Claude Code

Expert on cluster launching and resource scheduling (Slurm/Ray/Kubernetes). Use when user modifies launcher/scheduler code, configures cluster resources, or troubleshoots deployment issues.

Weizhena/Deep-Research-skills

Agent

Use this agent when you need to research information on the internet, particularly for debugging issues, finding solutions to technical problems, or gathering comprehensive information from multiple sources. This agent excels at finding relevant discussions. Use when you need creative search strategies, thorough…

Weizhena/Deep-Research-skills

Agent

Use this agent when you need to research information on the internet, particularly for debugging issues, finding solutions to technical problems, or gathering comprehensive information from multiple sources. This agent excels at finding relevant discussions. Use when you need creative search strategies, thorough…

TianGzlab/OmicsClaw

Agent

OmicsClaw uses one primary repository context with a Bench-specific supplement.

TianGzlab/OmicsClaw

Agent

Issues and PRDs for this repository live in GitHub Issues for zhou-1314/OmicsClaw. Use the gh CLI for issue operations.

TianGzlab/OmicsClaw

Agent

Engineering skills use five canonical triage roles. Each role maps directly to the corresponding GitHub label.

NeoTheCapt/RedteamAgent

Agent Claude Code

Lead red team operator. Drives pentest methodology, coordinates phases, dispatches subagents.

mintuz/skills

Agent

Expert code review specialist. Use PROACTIVELY after writing or modifying code, before commits, or when asked to review changes. Focuses on quality, security, performance, and maintainability.

mintuz/skills

Agent

Use this agent proactively to guide refactoring decisions during code improvement and reactively to assess refactoring opportunities after tests pass (TDD's third step). Invoke when tests are green, when considering abstractions, or when reviewing code quality.

mintuz/skills

Agent

Run tests and return concise pass/fail summary. Auto-detects test framework. Returns only essential info to minimize context usage.

ThreeFish-AI/negentropy

Agent

A tuning guide for converting PDFs to Markdown on Apple computers with M-series chips. It covers hardware detection, processing batches, parallel pages, memory use, and supported processing engines.

ThreeFish-AI/negentropy

Agent

A project index that points developers to important documents, modules, tests, scripts, and configuration files.

ThreeFish-AI/negentropy

Agent

A guide to choosing different software engines while converting PDF files into Markdown text. It uses document characteristics such as whether pages are scanned, whether they contain tables or formulas, and how many pages they have.

taipt1504/agent-skills

Agent

Stage 2 of two-stage review. Spec compliance already verified by Stage 1. Reviews security, performance, maintainability, readability, test quality. Severity-tagged output (P0/P1/P2/P3/P4) with MANDATORY rule ID citation per finding.

taipt1504/agent-skills

Agent

Decompose chosen solution into vertical slices with dependency graph + risk register. Consumes Align + Brainstorm artifacts. Output feeds Spec gate. Use after Brainstorm gate (high-stakes) or directly after Align (standard with obvious solution).

taipt1504/agent-skills

Agent

Behavioral spec generator — translates approved plans into concrete, testable contracts. Use when /spec is invoked after plan approval.

Brayszieqw/PaperMate

Agent

Agent "papermate-checkpoint" from Brayszieqw/PaperMate, covering 核心职责, 交互原则, checkpoint 类型, 1. plan approval（计划确认） and 📋 计划确认.

Brayszieqw/PaperMate

Agent

Use this agent when a task is ambiguous, multi-stage, or needs a lightweight execution plan before work begins. It decides route shape, owner, papermates path, and parallel boundaries without doing the work itself. Examples: Context: The user asks for a repo analysis first and implementation later. user…

Brayszieqw/PaperMate

Agent

An agent that creates and manages Git snapshots before and after code changes.