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

Skippy Prompt

by Mesh-LLM in Mesh-LLM/mesh-llm

A skill your agent uses when running or debugging interactive Skippy prompts against staged serving, including lab sync, native builds, stage startup, the HTTP prompt REPL, and process lifecycle.

Apache-2.0Auto-check passedDevelopment

Install Skippy Prompt

skills CLI
$ npx skills add Mesh-LLM/mesh-llm --skill skippy-prompt -a claude-code

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

GitHub CLI
$ gh skill install Mesh-LLM/mesh-llm skippy-prompt --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/Mesh-LLM/mesh-llm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/skippy-prompt .claude/skills/skippy-prompt && 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
skippy-prompt
GitHub stars
3.5k
Token cost
~1.1k tokens
SKILL.md length
489 words
Files
1
Skills in repo
25
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when running or debugging interactive Skippy prompts against staged serving, including lab sync, native builds, stage startup, the HTTP prompt REPL, and process lifecycle.

  • Works in 10 steps: Confirm repo state, branch, commit,… → Stop existing mesh/runtime processes on… → Rsync the current source tree to each… → …
  • Debugging interactive Skippy prompts against staged serving
  • SKILL.md covers Ownership Rules, Launch Workflow, Host Detection Commands and Commands
  • Calls just, cargo and jq

What it does

Skippy Prompt is an agent skill from Mesh-LLM/mesh-llm. Use this skill when running or debugging interactive Skippy prompts against staged serving, including lab sync, native builds, stage startup, the HTTP prompt REPL, and process lifecycle.

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 Development. It works with CUDA and Linux. The repository describes itself as: Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat. The licence is Apache-2.0.

When your agent uses it

  • Debugging interactive Skippy prompts against staged serving
  • Including lab sync
  • The HTTP prompt REPL
  • Process lifecycle

Example prompts

  • “/skippy-prompt”

Workflow steps

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

  1. Confirm repo state, branch, commit, model ref/path, hosts, desired layer
  2. Stop existing mesh/runtime processes on every selected host
  3. Rsync the current source tree to each remote host under
  4. Detect each host
  5. Choose the best backend per host
  6. Build on each host with repo-native just targets. Use just build on
  7. Materialize or locate model/package inputs on the launcher. If the source
  8. Start final stage first, then upstream stages, ending with local stage-0.
  9. Wait for readiness of every stage, then attach skippy prompt --endpoint
  10. Keep process handles or SSH sessions observable. Do not report success until

What it can do on your machine

Read from SKILL.md and the folder at commit 43ddd24. 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:

    • just
    • cargo
    • jq

    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

Skippy Prompt loads about 1.1k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 489 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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

The full file from Mesh-LLM/mesh-llm at commit 43ddd24, republished under its Apache-2.0 licence (© Mesh-LLM). 489 words, ~1,054 tokens.

Download SKILL.mdSave it as .claude/skills/skippy-prompt/SKILL.md (or your agent's skills folder).
name
skippy-prompt
description
Use this skill when running or debugging interactive Skippy prompts against staged serving, including lab sync, native builds, stage startup, the HTTP prompt REPL, and process lifecycle.
metadata.short-description
Run prompt-owned staged workflows

skippy-prompt

Use this skill for prompt-owned staged workflows. The skill is the launcher: Codex orchestrates sync, host-native builds, stage config generation, process startup, observation, prompt driving, and teardown.

Ownership Rules

  • The machine where the user asks to launch prompt is always stage-0.
  • Remote hosts are stage-1..N in the order provided by the user.
  • Bring down any running mesh-llm serving on the chosen nodes before starting prompt-owned stage servers.
  • Do not bring back standalone kv-server or ngram-pool.
  • Use $HOME/tmp for run roots, source syncs, logs, and bundles. Avoid /tmp unless the user explicitly asks for it.
  • Public OpenAI compatibility belongs in skippy-inference-api. The interactive client uses stage-0's OpenAI endpoint; raw protocol and cache checks belong in skippy-correctness.
  • Start stages with skippy serve --config <stage.json> --stage-transport binary. Use --worker-only on downstream stages. Stage 0 exposes the public API by default; attach with skippy prompt --endpoint or add --prompt to stage 0.

Launch Workflow

  1. Confirm repo state, branch, commit, model ref/path, hosts, desired layer ranges, context size, and prompt mode.
  2. Stop existing mesh/runtime processes on every selected host: mesh-llm stop first, then verify with ps; use pkill -f only if the scoped stop path fails.
  3. Rsync the current source tree to each remote host under $HOME/tmp/mesh-llm-prompt-src/<branch-or-sha>/, excluding build outputs and caches (target/, .git/, .deps/llama-build/, UI node_modules/).
  4. Detect each host: uname -s, uname -m, GPU inventory, compiler/runtime availability, and existing llama build cache.
  5. Choose the best backend per host:
    • macOS: Metal.
    • Linux NVIDIA with CUDA toolchain: CUDA. Use this for white.local unless CUDA is genuinely unavailable.
    • Linux AMD with ROCm toolchain: ROCm.
    • Vulkan-capable Linux without CUDA/ROCm: Vulkan.
    • CPU only as a last resort or explicit user request.
  6. Build on each host with repo-native just targets. Use just build on macOS and just release-runtime-build <backend> on Linux when UI rebuild is unnecessary. Do not hand-roll cargo/cmake build sequences.
  7. Materialize or locate model/package inputs on the launcher. If the source model only exists locally, rsync package/materialized stage inputs to remote hosts.
  8. Start final stage first, then upstream stages, ending with local stage-0. Use foreground TTY SSH for first repro/debug runs and tee logs under $HOME/tmp/skippy-prompt-runs/<run-id>/.
  9. Wait for readiness of every stage, then attach skippy prompt --endpoint from the launcher to the stage-0 OpenAI endpoint.
  10. Keep process handles or SSH sessions observable. Do not report success until stage servers are running and a prompt request has been attempted or the user explicitly only asked for startup.
Show full SKILL.md (80 more words)Show less

Host Detection Commands

Use these as probes, adapting for the host OS:

bash
uname -s
uname -m
command -v nvidia-smi && nvidia-smi -L
command -v nvcc && nvcc --version
command -v rocminfo && rocminfo
command -v vulkaninfo && vulkaninfo --summary
system_profiler SPDisplaysDataType

Backend selection is evidence-based. If a preferred backend fails, capture the failure and either fix the toolchain or clearly say why the fallback is being used.

Commands

Before using source-repo prompt commands, verify the crate exists here:

bash
cargo metadata --no-deps --format-version 1 | jq -r '.packages[].name' | sort

Expected prompt-owned binaries are:

text
skippy
skippy-correctness
skippy-package-builder
metrics-server

For remote long-running stages, use the remote-observable-process skill: allocate a TTY, use an interactive login shell, tee logs, and keep the session open while proving the topology.

© Mesh-LLM, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/skippy-prompt of Mesh-LLM/mesh-llm.

Open the folder on GitHubat commit 43ddd24

Compare with similar skills

Skippy Prompt 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.

Skippy Prompt compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skippy Prompt this skillMesh-LLM/mesh-llm3.5k—~1.1kAutomated safety check: PassApache-2.0
ONNX Runtime Source Buildmicrosoft/onnxruntime22k—~1.4kAutomated safety check: PassMIT
The Art of Debuggingstas00/the-art-of-debugging1.7k—~6.1kAutomated safety check: NotesCC-BY-SA-4.0
Install Miles Diffusionradixark/miles_diffusion109—~1.6kAutomated safety check: PassApache-2.0
Migrate Workflow Ec2 To Osdcpytorch/test-infra113—~2kAutomated safety check: PassCustom licence
Triton Sageattentionartokun/comfyui-mcp803—~5kAutomated safety check: PassMIT

Similar skills

  • ONNX Runtime Source Build

    microsoft/onnxruntime

    Official

    Builds ONNX Runtime from source with its build scripts, explaining the update, build and test phases, key flags and where the build output lands.

    22k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed

  • The Art of Debugging

    stas00/the-art-of-debugging

    Condensed debugging method and tool recipes for Unix, Python and PyTorch programs: crashes, hangs, segfaults, wrong output, CUDA OOM, NaN values and slowness.

    1.7k GitHub stars~6.1k tokensUpdated 4 days ago
    DevelopmentAuto-check: notes

  • Install Miles Diffusion

    radixark/miles_diffusion

    Fallback installer for milesdiffusion on a bare CUDA 12.9 Linux GPU box, reproducing the official radixark/milesdiffusion image's package versions and verifying them.

    109 GitHub stars~1.6k tokensUpdated yesterday
    DevOps & CloudAuto-check passed

  • Migrate Workflow Ec2 To Osdc

    pytorch/test-infra

    Step-by-step playbook for migrating a pytorch/pytorch .github/workflows/.yml from EC2 to OSDC (ARC) runners — covers both dial-up and 100% opt-in patterns, with the inputs that must be plumbed…

    113 GitHub stars~2k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Triton Sageattention

    artokun/comfyui-mcp

    Install Triton + SageAttention to accelerate ComfyUI (the sageattn attentionmode and inductor torch.compile used by WanVideoWrapper / many video graphs).

    803 GitHub stars~5k tokensUpdated 5 days ago
    AI & LLM EngineeringAuto-check passed

  • Xmake

    LuisaGroup/LuisaCompute

    XMake build configuration, options, commands, and patterns for LuisaCompute.

    1.1k GitHub stars~13k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from Mesh-LLM/mesh-llm

All 25 skills in this repo

  • Release Validation

    Mesh-LLM/mesh-llm

    A skill your agent uses when validating a MeshLLM release candidate or current HEAD against the last GitHub release, assembling the canonical feature/fix/modification inventory, testing locally…

    3.5k GitHub stars~2.6k tokensUpdated today
    Auto-check passed

  • Benchmark Tune

    Mesh-LLM/mesh-llm

    A skill your agent uses when running, debugging, interpreting, or documenting mesh-llm benchmark tune model-serving throughput trials, including choosing…

    3.5k GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Config Settings Management

    Mesh-LLM/mesh-llm

    A skill your agent uses when adding, renaming, removing, validating, or exposing mesh-llm config settings, including built-in settings, plugin config schemas, owner-control apply behavior, CLI…

    3.5k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Connect Agents

    Mesh-LLM/mesh-llm

    A skill your agent uses when connecting agent tools or OpenAI clients to mesh-llm — launching or configuring Goose, Claude Code, OpenCode, Pi, curl, or any OpenAI-compatible client against a local…

    3.5k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Hf Bf16 Gguf Conversion Jobs

    Mesh-LLM/mesh-llm

    A skill your agent uses when converting Hugging Face SafeTensors checkpoints into split BF16 GGUF model repos with skippy-quantize on Hugging Face Jobs or a local machine, then publishing the…

    3.5k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Hf Gguf Quant Jobs

    Mesh-LLM/mesh-llm

    A skill your agent uses when creating, monitoring, validating, or documenting low-memory Hugging Face Jobs or local runs that quantize split BF16/FP16 GGUF model repos into custom quant GGUF repos…

    3.5k GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Skippy Prompt

What does Skippy Prompt do?

A skill your agent uses when running or debugging interactive Skippy prompts against staged serving, including lab sync, native builds, stage startup, the HTTP prompt REPL, and process lifecycle. Skippy Prompt is an agent skill from Mesh-LLM/mesh-llm. Use this skill when running or debugging interactive Skippy prompts against staged serving, including lab sync, native builds, stage startup, the HTTP prompt REPL, and process lifecycle.

When should I use Skippy Prompt?

Skippy Prompt fits situations like: debugging interactive Skippy prompts against staged serving; including lab sync; the HTTP prompt REPL; process lifecycle.

How do I install Skippy Prompt in Claude Code?

Run `npx skills add Mesh-LLM/mesh-llm --skill skippy-prompt -a claude-code`. Or copy the skill folder (.agents/skills/skippy-prompt in Mesh-LLM/mesh-llm) into .claude/skills/skippy-prompt in your project. Claude Code loads it when a task matches its description.

How do I install Skippy Prompt in Codex?

Run `npx skills add Mesh-LLM/mesh-llm --skill skippy-prompt -a codex`. Or copy the skill folder (.agents/skills/skippy-prompt in Mesh-LLM/mesh-llm) into .agents/skills/skippy-prompt in your project. Codex loads it when a task matches its description.

Can I use Skippy Prompt 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 Mesh-LLM/mesh-llm --skill skippy-prompt -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skippy-prompt, .gemini/skills/skippy-prompt, .github/skills/skippy-prompt and .opencode/skills/skippy-prompt in your project.

What does Skippy Prompt need to run?

Going by SKILL.md and its folder, Skippy Prompt needs the command-line tools its instructions call (just, cargo and jq).

Does Skippy Prompt 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 Skippy Prompt 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 Skippy Prompt use?

Skippy Prompt is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Skippy Prompt use?

About 1.1k tokens (SKILL.md is roughly 4.2k 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 Skippy Prompt?

Skills that share tags, products or a category with Skippy Prompt: ONNX Runtime Source Build (microsoft/onnxruntime, 22k stars), The Art of Debugging (stas00/the-art-of-debugging, 1.7k stars), Install Miles Diffusion (radixark/miles_diffusion, 109 stars) and Migrate Workflow Ec2 To Osdc (pytorch/test-infra, 113 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skippy Prompt?

Mesh-LLM (a GitHub organization) maintains it in Mesh-LLM/mesh-llm, which has 3,489 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 10, 2026.

Source: Mesh-LLM/mesh-llm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.