Kkclaw
kk43994/kkclaw
给你的 AI Agent 一个桌面身体 — Setup Wizard、14情绪球体、语音克隆、歌词窗、Doctor 自检、跨平台支持（Windows + macOS）
mlx-serve benchmarking methodology — bench.sh/llmprobe usage, comparison-trap rules (same-methodology cells only, spec-decode variance, thermal lies, engine naming), perf-claim etiquette.
Install Bench
$ npx skills add ddalcu/mlx-serve --skill bench -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ddalcu/mlx-serve bench --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ddalcu/mlx-serve.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/bench .claude/skills/bench && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "bench" agent skill from https://github.com/ddalcu/mlx-serve/tree/main/.claude/skills/bench into .claude/skills/bench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bench", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ddalcu/mlx-serve/tree/main/.claude/skills/benchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ddalcu/mlx-serve --skill bench -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ddalcu/mlx-serve bench --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ddalcu/mlx-serve.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/bench .agents/skills/bench && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "bench" agent skill from https://github.com/ddalcu/mlx-serve/tree/main/.claude/skills/bench into .agents/skills/bench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bench", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ddalcu/mlx-serve --skill bench -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ddalcu/mlx-serve bench --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ddalcu/mlx-serve.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/bench .cursor/skills/bench && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "bench" agent skill from https://github.com/ddalcu/mlx-serve/tree/main/.claude/skills/bench into .cursor/skills/bench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bench", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ddalcu/mlx-serve.git --path .claude/skills/bench--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ddalcu/mlx-serve --skill bench -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ddalcu/mlx-serve bench --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ddalcu/mlx-serve.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/bench .gemini/skills/bench && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "bench" agent skill from https://github.com/ddalcu/mlx-serve/tree/main/.claude/skills/bench into .gemini/skills/bench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bench", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ddalcu/mlx-serve benchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ddalcu/mlx-serve --skill bench -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ddalcu/mlx-serve.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/bench .github/skills/bench && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "bench" agent skill from https://github.com/ddalcu/mlx-serve/tree/main/.claude/skills/bench into .github/skills/bench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bench", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ddalcu/mlx-serve --skill bench -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ddalcu/mlx-serve bench --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ddalcu/mlx-serve.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/bench .opencode/skills/bench && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "bench" agent skill from https://github.com/ddalcu/mlx-serve/tree/main/.claude/skills/bench into .opencode/skills/bench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bench", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
bench- GitHub stars
- 1.8k
- Used in
- 1 other repo
- Token cost
- ~1.1k tokens
- SKILL.md length
- 580 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
mlx-serve benchmarking methodology — bench.sh/llmprobe usage, comparison-trap rules (same-methodology cells only, spec-decode variance, thermal lies, engine naming), perf-claim etiquette.
- Media & Creative work in your project
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Bench is an agent skill from ddalcu/mlx-serve. mlx-serve benchmarking methodology — bench.sh/llmprobe usage, comparison-trap rules (same-methodology cells only, spec-decode variance, thermal lies, engine naming), perf-claim etiquette. Use before running benchmarks or making any performance claim.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Media & Creative. It works with macOS. The repository describes itself as: Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.
When your agent uses it
- Media & Creative work in your project
Example prompts
- “/bench”
What it can do on your machine
Read from SKILL.md and the folder at commit 2ebcbdb. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Bench loads about 1.1k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 580 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 580 words (~1,067 tokens).
“llmprobe is the measurement layer. tests/bench.sh boots mlx-serve (one model at a time: boot, probe, kill, settle) and llmprobe takes every number via --bench-only. We do not hand-roll timing loops — llmprobe discards a warmup per scenario, reports median-of-3 as…”
- name
- bench
Files
Just SKILL.md in .claude/skills/bench of ddalcu/mlx-serve.
Open the folder on GitHubat commit 2ebcbdb
Used in 1 other repository
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in ddalcu/mlx-serve, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Bench next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Bench this skillddalcu/mlx-serve | 1.8k | 1 repos | ~1.1k | Automated safety check: Pass | Custom licence | |
| Kkclawkk43994/kkclaw | 174 | — | ~576 | Automated safety check: Pass | MIT | |
| Voxtype Installpchalasani/claude-code-tools | 2k | — | ~857 | Automated safety check: Notes | MIT | |
| Vlog Auto Editznyupup/ai-video-editing-skill | 144 | — | ~6.8k | Automated safety check: Pass | MIT | |
| Sayitcallebtc/sayit | 159 | — | ~2.9k | Automated safety check: Pass | MIT | |
| Gpt Imagenikships/droidproxy | 122 | — | ~2.5k | Automated safety check: Pass | MIT |
Similar skills
Voxtype Install
pchalasani/claude-code-tools
Guide the user through installing, configuring, and launching voxtype — local on-device voice dictation (speech-to-text that types wherever the cursor is).
Vlog Auto Edit
znyupup/ai-video-editing-skill
AI Agent自动剪辑旅行Vlog的完整工作流。从原始素材到成品视频，系统级只需ffmpeg，其余在Python venv内完成。by nyx研究所 (GitHub @znyupup · B站/小红书 @nyx研究所)
Sayit
callebtc/sayit
Live, low-latency spoken narration for hands-free agent sessions through the sayit TTS command.
Gpt Image
nikships/droidproxy
Generate or edit images via GPT Image 2.5 Flare or Sunburst through DroidProxy Codex OAuth (no OPENAIAPIKEY).
Agentvibes
paulpreibisch/AgentVibes
🎤 AgentVibes Voice Management - Manage your text-to-speech voices across multiple providers (Piper TTS, Piper, macOS Say).
More from ddalcu/mlx-serve
Mlx Serve
ddalcu/mlx-serve
Hook an app, game or script up to the local mlx-serve server for LLM chat, embeddings, image, speech, music, sound effect, video and 3D generation, and Laya/Kev/Clef typed decisions.
Release
ddalcu/mlx-serve
mlx-serve pre-release validation checklist, CalVer versioning, release steps, and CHANGELOG style.
PR Charts
ddalcu/mlx-serve
Turn llmprobe reports into the charts a perf PR embeds (one line per arm across context size, every point labelled, machine and model in the caption) and host them so the PR body renders them.
Related
Works with
Categories
Questions about Bench
What does Bench do?
mlx-serve benchmarking methodology — bench.sh/llmprobe usage, comparison-trap rules (same-methodology cells only, spec-decode variance, thermal lies, engine naming), perf-claim etiquette. Bench is an agent skill from ddalcu/mlx-serve.sh/llmprobe usage, comparison-trap rules (same-methodology cells only, spec-decode variance, thermal lies, engine naming), perf-claim etiquette.
When should I use Bench?
Bench fits situations like: media & Creative work in your project.
How do I install Bench in Claude Code?
Run `npx skills add ddalcu/mlx-serve --skill bench -a claude-code`. Or copy the skill folder (.claude/skills/bench in ddalcu/mlx-serve) into .claude/skills/bench in your project. Claude Code loads it when a task matches its description.
How do I install Bench in Codex?
Run `npx skills add ddalcu/mlx-serve --skill bench -a codex`. Or copy the skill folder (.claude/skills/bench in ddalcu/mlx-serve) into .agents/skills/bench in your project. Codex loads it when a task matches its description.
Can I use Bench in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ddalcu/mlx-serve --skill bench -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bench, .gemini/skills/bench, .github/skills/bench and .opencode/skills/bench in your project.
What does Bench need to run?
SKILL.md names no scripts, command-line tools or credentials: Bench is instructions for the agent only.
Does Bench access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Bench safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Bench use?
Bench has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Bench use?
About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Bench?
Skills that share tags, products or a category with Bench: Kkclaw (kk43994/kkclaw, 174 stars), Voxtype Install (pchalasani/claude-code-tools, 2k stars), Vlog Auto Edit (znyupup/ai-video-editing-skill, 144 stars) and Sayit (callebtc/sayit, 159 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Bench?
ddalcu (a GitHub user) maintains it in ddalcu/mlx-serve, which has 1,782 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 7, 2026.
Source: ddalcu/mlx-serve on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.