New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

PR Charts

by ddalcu in 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.

Custom licenceAuto-check passedMedia & Creative

Install PR Charts

skills CLI
$ npx skills add ddalcu/mlx-serve --skill pr-charts -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ddalcu/mlx-serve pr-charts --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ddalcu/mlx-serve.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/pr-charts .claude/skills/pr-charts && rm -rf skills-src

Use ~/.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/

Facts

Skill name
pr-charts
GitHub stars
1.8k
Token cost
~594 tokens
SKILL.md length
286 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
Custom licence

At a glance

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.

  • Works in 5 steps: Measure each arm with tests/bench.sh,… → Chart them. → Look at the PNGs before posting. A flat… → …
  • A PR makes a speed claim
  • Calls uv; reaches raw.githubusercontent.com
  • Asked for a chart of a bench run

What it does

PR Charts is an agent skill from 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. Use when a PR makes a speed claim, or when asked for a chart of a bench run.

Its SKILL.md is about 590 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, covering Pull requests. 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

  • A PR makes a speed claim
  • Asked for a chart of a bench run

Example prompts

  • “/pr-charts”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Measure each arm with tests/bench.sh, alternating. Run the ladder once per arm, then again in reverse order (A B B A), all in one session…
  2. Chart them.
  3. Look at the PNGs before posting. A flat line at zero, a missing arm, or two arms that match to the digit means a bad run, not a result…
  4. Host them. gh can't attach images. Commit the PNGs to a branch of your public fork, for example pr-charts with a directory per PR, and…
  5. One line of method under the charts: chip, macOS, model, flags, runs per arm, arm order.

What it can do on your machine

Read from SKILL.md and the folder at commit 20cec71. 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

    Shell commands in SKILL.md call:

    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • raw.githubusercontent.com

    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

PR Charts loads about 594 tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 286 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~594

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 286 words (~594 tokens).

“The chart goes above the table in "How I verified it". A reviewer sees in two seconds whether a win holds at every context size or only at one.”

— opening of SKILL.md by ddalcu, Custom licence
name
pr-charts

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/pr-charts of ddalcu/mlx-serve.

Open the folder on GitHubat commit 20cec71

Compare with similar skills

PR Charts 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.

PR Charts compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
PR Charts this skillddalcu/mlx-serve1.8k—~594Automated safety check: PassCustom licence
Perfupraullenchai/Rapid-MLX4k—~1.6kAutomated safety check: NotesCustom licence
Prepare PRchattymin/PokeTokenBar508—~1.8kAutomated safety check: PassMIT
Kkclawkk43994/kkclaw174—~576Automated safety check: PassMIT
cmux Screenshot and Recordingmanaflow-ai/cmux28k—~992Automated safety check: PassCustom licence
Voxtype Installpchalasani/claude-code-tools2k—~857Automated safety check: NotesMIT

Similar skills

  • Perfup

    raullenchai/Rapid-MLX

    Autonomous performance optimization: research, PoC, benchmark, implement, review, PR

    4k GitHub stars~1.6k tokensUpdated today
    AI & LLM EngineeringAuto-check: notes

  • Prepare PR

    chattymin/PokeTokenBar

    Prepare, create, or update a PokeTokenBar pull request with an English Conventional Commits title, the repository PR template, and mandatory images for visible UI changes.

    508 GitHub stars~1.8k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

  • 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）

    174 GitHub stars~576 tokensUpdated 5 mo ago
    Media & CreativeAuto-check passed

  • cmux Screenshot and Recording

    manaflow-ai/cmux

    Captures PNG or JPEG screenshots and MP4 or GIF clips of cmux windows from the command line, as visual evidence for pull requests and bug reports.

    28k GitHub stars~992 tokensUpdated today
    Testing & QAAuto-check passed

  • 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).

    2k GitHub stars~857 tokensUpdated yesterday
    Media & CreativeAuto-check: notes

  • PR Writer

    microsoft/SwiftStreamingMarkdown

    Official

    Prepare and publish SwiftStreamingMarkdown pull requests end-to-end: generate PR description, commit changes, create/push branch, and open a PR when needed.

    379 GitHub stars~2.9k tokensUpdated 15 days ago
    DevelopmentAuto-check passed

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.

    1.8k GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Release

    ddalcu/mlx-serve

    mlx-serve pre-release validation checklist, CalVer versioning, release steps, and CHANGELOG style.

    1.8k GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Bench

    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.

    1.8k GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed

Works with

Categories

Questions about PR Charts

What does PR Charts do?

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. PR Charts is an agent skill from 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.

When should I use PR Charts?

PR Charts fits situations like: A PR makes a speed claim; asked for a chart of a bench run.

How do I install PR Charts in Claude Code?

Run `npx skills add ddalcu/mlx-serve --skill pr-charts -a claude-code`. Or copy the skill folder (.claude/skills/pr-charts in ddalcu/mlx-serve) into .claude/skills/pr-charts in your project. Claude Code loads it when a task matches its description.

How do I install PR Charts in Codex?

Run `npx skills add ddalcu/mlx-serve --skill pr-charts -a codex`. Or copy the skill folder (.claude/skills/pr-charts in ddalcu/mlx-serve) into .agents/skills/pr-charts in your project. Codex loads it when a task matches its description.

Can I use PR Charts 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 pr-charts -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pr-charts, .gemini/skills/pr-charts, .github/skills/pr-charts and .opencode/skills/pr-charts in your project.

What does PR Charts need to run?

Going by SKILL.md and its folder, PR Charts needs the command-line tools its instructions call (uv).

Does PR Charts access the network?

SKILL.md names 1 domain. In commands or code: raw.githubusercontent.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is PR Charts 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 PR Charts use?

PR Charts 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 PR Charts use?

About 594 tokens (SKILL.md is roughly 2.4k 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 PR Charts?

Skills that share tags, products or a category with PR Charts: Perfup (raullenchai/Rapid-MLX, 4k stars), Prepare PR (chattymin/PokeTokenBar, 508 stars), Kkclaw (kk43994/kkclaw, 174 stars) and cmux Screenshot and Recording (manaflow-ai/cmux, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains PR Charts?

ddalcu (a GitHub user) maintains it in ddalcu/mlx-serve, which has 1,820 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 10, 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.