Bench View — AI skill for Claude Code
Build and serve the custom-model-bench viewer; print the URL.
How to install Bench View
Installs to ~/.claude/skills/ant-open-skills-custom-model-bench-bench-view/SKILL.md
mkdir -p ~/.claude/skills/ant-open-skills-custom-model-bench-bench-view && curl -fsSL https://raw.githubusercontent.com/ant-open-skills/custom-model-bench/HEAD/commands/bench-view.md -o ~/.claude/skills/ant-open-skills-custom-model-bench-bench-view/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Bench View does
description: Build and serve the custom-model-bench viewer; print the URL.
Build the viewer data file and start the local web server so the user can see the latest comparison results.
All commands below run from the plugin's installed root via `${CLAUDE_PLUGIN_ROOT}` — that's where `package.json`, `viewer/`, and the `examples//runs/` directories live. The user's current working directory doesn't matter.
Steps:
- Dependency check. If
${CLAUDE_PLUGIN_ROOT}/node_modules/d
Alternatives in AI
- Zen MCP Server — The power of Claude Code + Gemini / OpenAI / Grok / OpenRouter / Ollama / Custom Model working as one 11.3k ★
- Open Researcher — 🔥 Visual AI research assistant that displays real-time thinking, provides split-view analysis, and automatic 634 ★
- Skillport — Bring Agent Skills to Any AI Agent and Coding Agent — via CLI or MCP 408 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Gptcc
GPT for Claude Code — use OpenAI GPT models inside the Claude Code CLI via documented extension points (ANTHRO
Pressroom
Hire, run, measure and retire a crew of AI agents for a custom print shop. Go, GraphQL, PostgreSQL and TypeScr
Erd UX Review
Review the rendered dbdocs ERD's UI/UX (overview + model-page "Related ERD") against a real dbt project — inst
Atrium
Zero-dependency, single-machine life dashboard — GitHub tasks, local AI agents, system health, email/calendar,
Ceo Info
Live preflight — resolve framework paths + writability, print effective settings, optional cheap model round-t
Crux
Taking the pi coding agent to Claude Code-level performance: 0.539 → 0.773 pass@1 on Terminal-Bench 2.1 with t
Related Agents
Icu Pathophysiology Basic
Use when an ICU clinical consult needs the animal-model and basic-science layer — the view of a bench scientis
Viz Frontend
Use when experiment data needs a custom dashboard, comparison surface, or trajectory viewer.
Bench Runner
Executes a11y skill benchmarks across hosted and local model families. Runs cloud/Codex/Ollama benchmark scrip