modelscope

Execute AgentJet reinforcement learning experiments using experiment blueprints in classic (non-swarm) mode. Handles full lifecycle: launch experiment in tmux, monitor progress, analyze errors, collect results, and write finish flag. Use when the user wants to run AgentJet training experiments without the swarm distributed framework.

Execute AgentJet reinforcement learning experiments using experiment blueprints in swarm mode. Handles full lifecycle: generate blueprint if needed, launch experiment in tmux, monitor progress, analyze errors, collect results, and write finish flag. Use when the user wants to run or debug AgentJet training experiments.

Install AgentJet swarm server using Conda. Handles Python 3.10 environment creation, dependency installation with the verl training backbone, flash-attn compilation, and optional PyPI mirror for China users.

Install and run the AgentJet Swarm Server in a Docker container with NVIDIA GPU support. Use when the user wants to deploy a swarm server on a GPU machine via Docker, including GPU driver setup, Docker mirror configuration, model weight mounting, and server startup.

Download per-step time-series metric data (reward, entropy, response length, etc.) from a SwanLab cloud run URL as a pandas.DataFrame. Use when the user provides a SwanLab URL and wants to fetch or analyze training curves.

Install AgentJet client for connecting to a swarm server. Use when the user only needs to run the AgentJet client (not a swarm server) and does not need to run models locally, e.g. on a laptop. Installs basic requirements via `pip install -e .`.

Map VERL training configuration to AgentJet configuration. Find VERL config in verl_default.yaml, check for existing mappings in config_auto_convertion_verl.jsonc, add new mappings to ajet_default.yaml and the conversion schema, and optionally add parameters to AgentJetJob.

Convert skills in non-standard formats to the standard Agent Skills `SKILL.md` format. Validates YAML frontmatter (name, description, license, compatibility, metadata, allowed-tools), directory structure (SKILL.md, scripts/, references/, assets/), and best practices. Use when the user asks to normalize, validate, or fix a skill.

Access ms-agent's advanced AI capabilities via MCP tools: deep research with async submit/check/get pattern, web search (arxiv/exa/serpapi), LSP code validation (TypeScript/Python/Java), concurrent-safe file editing, and agent delegation for complex multi-step tasks. Use when the user asks to research a topic, search the web, validate code, edit files precisely, or delegate a complex task to a specialized agent. Requires ms-agent (pip install ms-agent).

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Translates natural language requests into evalscope CLI commands. Core capabilities: (1) Model accuracy evaluation (eval) — runs 156+ benchmarks (Math, Coding, Chinese, Multimodal, Agent, etc.) against local checkpoints or OpenAI-compatible / Anthropic API endpoints; (2) Performance stress testing (perf) — measures TTFT, TPOT, throughput, and latency under configurable concurrency gradients or SLA auto-tuning; (3) Benchmark discovery — lists and filters benchmarks by capability tag, retrieves full metadata and sample examples; (4) Result visualization — launches a Web dashboard to compare and explore evaluation outputs. Trigger this skill whenever the user mentions: evaluate / benchmark / score a model, throughput / latency / QPS / stress test, find benchmarks by tag or capability, or view / compare evaluation results.

Local file search using sirchmunk API. Use when you need to search for files or content by asking natural language questions.

Ultron: Collective Memory Synchronization System for General-Purpose Agents