run-bench

Name: run-bench
Author: tv-labs

Skill by tv-labs · updated yesterday · ★ 226

Score 73

Execute the benchmark harness under benchmarks/ and produce a markdown report comparing this build against the recorded baseline (and optionally against Luerl and PUC-Lua). Flag regressions over a configurable threshold. Use when the user asks for a benchmark run, after any executor or codegen change in Direction B, or when a Direction B plan's verification calls for it. STATUS: stub. Will be filled in when Direction B begins. The benchee harness is already in benchmarks/ (added in PR #143). run-bench is published by tv-labs on GitHub.

Install GitHub

Works withClaude CodeClaude apps Antigravity CLI

Maintenance

Last commit in the past day

Licence

Apache-2.0: permissive, fine for commercial use

Quality

Clear description, installs from GitHub, 226 stars, original repository

Security

Not checked yet. What we check

Install run-bench

Built from the published package, never by AI

git clone --depth 1 https://github.com/tv-labs/lua /tmp/lua && mkdir -p ~/.claude/skills && cp -r /tmp/lua/.agents/skills/run-bench ~/.claude/skills/run-bench

Run in your terminal. Claude Code loads skills from ~/.claude/skills automatically.

Step-by-step: install run-bench in Claude Code

git clone --depth 1 https://github.com/tv-labs/lua /tmp/lua && mkdir -p ~/.gemini/antigravity-cli/skills && cp -r /tmp/lua/.agents/skills/run-bench ~/.gemini/antigravity-cli/skills/run-bench

Antigravity CLI loads skills from ~/.gemini/antigravity-cli/skills, or .agents/skills for one project.

Step-by-step: install run-bench in Antigravity CLI

Skills can run scripts on your machine. Some need an API key: check the README.

Alternatives to run-bench

All alternatives →

channels-setupCopilotKit

Use when a developer wants to build their first CopilotKit Channels agent and get it answering in Slack or Microsoft Teams: "set up a channel", "connect my agent to Slack", "get my agent into Teams", or starting from nothing and wanting a working channel end to end. Covers the whole path: inspecting or scaffolding the project, building the AG-UI agent, creating and reconciling the managed Channel with the public CopilotKit CLI, running the long-running host, and proving a real provider mention gets a reply. The workflow is not in this file. Run `npx --yes copilotkit@latest onboard start` and follow the graph it prints.

AAA Skill 38k

office-export-pdfdeepseek-ai

Convert an Office document to a requested PDF with LibreOffice Kit.

AAA Skill 255k

openclaw-brandopenclaw

Apply OpenClaw visual identity to logos, typography, imagery, voice, documents, presentations, social graphics, and launch materials. Use when the task changes brand identity rather than ordinary product UI or public-page composition.

AAA Skill 9.5k

Format numbersTryGhost

Format numbers using the formatNumber function from Shade whenever someone edits a TSX file.

AAA Skill 56k

parse-documentsuperlinked

Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.

AAA Skill 3.4k

sort-redirectsdotnet

Sorts redirect entries in Open Publishing redirection JSON files alphabetically by path. Use after adding redirects or when the file becomes unsorted.

ACA Skill 4.8k

run-bench vs channels-setup run-bench vs office-export-pdf run-bench vs openclaw-brand

run-bench: common questions

How do I install run-bench?

Run the command above to copy the skill into ~/.claude/skills/. Claude Code picks it up automatically.

Is run-bench free?

The code is published under the Apache-2.0 licence. The service it connects to may have its own pricing.

Is run-bench safe to use?

It scores 73 of 100. Grades: maintenance A, licence A, quality B. The security check has not run for it yet. Review the code before you install. How grades work.

What are alternatives to run-bench?