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

Watchdog

by cua-lite in cua-lite/cua-lite

Hold / release GPUs by running a standard SGLang inference server on them (lab convention — occupy a card with a real serving job that fills ~all of its memory AND is driven at stable near-full…

No licenceAuto-check passedAI & LLM Engineering

Install Watchdog

skills CLI
$ npx skills add cua-lite/cua-lite --skill watchdog -a claude-code

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

GitHub CLI
$ gh skill install cua-lite/cua-lite watchdog --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/cua-lite/cua-lite.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/watchdog .claude/skills/watchdog && 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
watchdog
GitHub stars
107
Token cost
~1.9k tokens
SKILL.md length
681 words
Files
2
Skills in repo
5
Repo updated
First seen
Licence
None found

At a glance

Hold / release GPUs by running a standard SGLang inference server on them (lab convention — occupy a card with a real serving job that fills ~all of its memory AND is driven at stable near-full…

  • AI & LLM Engineering work in your project
  • SKILL.md covers Arguments, Config (defaults; tune inline), hold and release, plus 1 more section
  • Runs Python scripts from its folder; calls python

What it does

Watchdog is an agent skill from cua-lite/cua-lite. Hold / release GPUs by running a standard SGLang inference server on them (lab convention — occupy a card with a real serving job that fills ~all of its memory AND is driven at stable near-full utilization), instead of a dedicated GPU-squatter script.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `driver.py`).

It sits in AI & LLM Engineering. It works with SGLang and NVIDIA AI Platform. The repository describes itself as: CUA-Lite: An Open Platform for Computer-Use Agents.

When your agent uses it

  • AI & LLM Engineering work in your project

Example prompts

  • “/watchdog”

Requirements

  • Python 3
  • Docker

What it can do on your machine

Read from SKILL.md and the folder at commit 65a61c4. 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

    Ships script files (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    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

Watchdog loads about 1.9k tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 681 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 681 words (~1,948 tokens).

“Hold target GPUs by launching a normal SGLang inference server on each one (sized so its static memory pool fills ~all of the card's VRAM) plus a small load client that drives it continuously (so GPU utilization stays stably near-full)…”

— opening of SKILL.md by cua-lite
name
watchdog

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in .claude/skills/watchdog of cua-lite/cua-lite.

  • SKILL.md
  • driver.py

Open the folder on GitHubat commit 65a61c4

Compare with similar skills

Watchdog 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.

Watchdog compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Watchdog this skillcua-lite/cua-lite107—~1.9kAutomated safety check: PassNone
Dstack Prototypingdstackai/dstack2.3k—~1.6kAutomated safety check: PassMPL-2.0
Graphsignalgraphsignal/graphsignal257—~6.2kAutomated safety check: PassApache-2.0
LLM Torch Profiler Trace AnalysisBBuf/AI-Infra-Auto-Driven-SKILLS925—~2.8kAutomated safety check: PassNone
Sglang Diffusion Modelopt Quantsgl-project/sglang37k2 repos~5kAutomated safety check: PassApache-2.0
SGLang Structured ServingOrchestra-Research/AI-Research-SKILLs13k2 repos~2.9kAutomated safety check: PassMIT

Similar skills

  • Dstack Prototyping

    dstackai/dstack

    Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven.

    2.3k GitHub stars~1.6k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Graphsignal

    graphsignal/graphsignal

    Profile AI inference workloads (vLLM, SGLang, TensorRT-LLM, PyTorch, any GPU application) with the Graphsignal profiler and read the results from its local /signals JSON endpoint.

    257 GitHub stars~6.2k tokensUpdated 11 days ago
    AI & LLM EngineeringAuto-check passed

  • LLM Torch Profiler Trace Analysis

    BBuf/AI-Infra-Auto-Driven-SKILLS

    Analyzes Torch Profiler traces from SGLang, vLLM and TensorRT-LLM servers into kernel attribution, overlap and fusion tables.

    925 GitHub stars~2.8k tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check passed

  • Sglang Diffusion Modelopt Quant

    sgl-project/sglang

    A skill your agent uses when quantizing a diffusion DiT with NVIDIA ModelOpt and making the resulting FP8 or NVFP4 checkpoint loadable, verifiable, and benchmarkable in SGLang Diffusion.

    37k GitHub starsUsed in 2 repos~5k tokens
    AI & LLM EngineeringAuto-check passed

  • SGLang Structured Serving

    Orchestra-Research/AI-Research-SKILLs

    Covers serving LLMs with SGLang, whose RadixAttention reuses cached prefixes, and constraining output to JSON, regex or grammar for agent and tool-calling workloads.

    13k GitHub starsUsed in 2 repos~2.9k tokens
    AI & LLM EngineeringAuto-check passed

  • Model PR History Knowledge

    BBuf/AI-Infra-Auto-Driven-SKILLS

    A skill your agent uses when an SGLang, vLLM, TensorRT-LLM, or TokenSpeed serving/model optimization task needs prior model-family PR evidence.

    925 GitHub stars~1.5k tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check passed

More from cua-lite/cua-lite

  • Ckpt

    cua-lite/cua-lite

    Manage training checkpoints — export from the slime container to the host .ckpts/ directory with a runinfo.txt for full reproducibility.

    107 GitHub stars~800 tokensUpdated 14 days ago
    Auto-check passed

  • Cleanup

    cua-lite/cua-lite

    Direct-mode cleanup of local docker containers, training processes, and GPU memory.

    107 GitHub stars~1.7k tokensUpdated 14 days ago
    Auto-check passed

  • Long Run

    cua-lite/cua-lite

    Run a long-running command or task in background and monitor it with minimal-thinking polls.

    107 GitHub stars~1.1k tokensUpdated 14 days ago
    Auto-check passed

  • Audit

    cua-lite/cua-lite

    Audit codebase for inconsistencies, redundant code, stale references, and (if staged changes exist) newly introduced bugs.

    107 GitHub stars~418 tokensUpdated 14 days ago
    Auto-check passed

Works with

Categories

Questions about Watchdog

What does Watchdog do?

Hold / release GPUs by running a standard SGLang inference server on them (lab convention — occupy a card with a real serving job that fills ~all of its memory AND is driven at stable near-full…. Watchdog is an agent skill from cua-lite/cua-lite. Hold / release GPUs by running a standard SGLang inference server on them (lab convention — occupy a card with a real serving job that fills ~all of its memory AND is driven at stable near-full utilization), instead of a dedicated GPU-squatter script.

When should I use Watchdog?

Watchdog fits situations like: AI & LLM Engineering work in your project.

How do I install Watchdog in Claude Code?

Run `npx skills add cua-lite/cua-lite --skill watchdog -a claude-code`. Or copy the skill folder (.claude/skills/watchdog in cua-lite/cua-lite) into .claude/skills/watchdog in your project. Claude Code loads it when a task matches its description.

How do I install Watchdog in Codex?

Run `npx skills add cua-lite/cua-lite --skill watchdog -a codex`. Or copy the skill folder (.claude/skills/watchdog in cua-lite/cua-lite) into .agents/skills/watchdog in your project. Codex loads it when a task matches its description.

Can I use Watchdog 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 cua-lite/cua-lite --skill watchdog -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/watchdog, .gemini/skills/watchdog, .github/skills/watchdog and .opencode/skills/watchdog in your project.

What does Watchdog need to run?

Going by SKILL.md and its folder, Watchdog needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3; Docker.

Does Watchdog 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 Watchdog 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 Watchdog use?

No licence was found for Watchdog or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Watchdog use?

About 1.9k tokens (SKILL.md is roughly 7.8k 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 Watchdog?

Skills that share tags, products or a category with Watchdog: Dstack Prototyping (dstackai/dstack, 2.3k stars), Graphsignal (graphsignal/graphsignal, 257 stars), LLM Torch Profiler Trace Analysis (BBuf/AI-Infra-Auto-Driven-SKILLS, 925 stars) and Sglang Diffusion Modelopt Quant (sgl-project/sglang, 37k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Watchdog?

cua-lite (a GitHub organization) maintains it in cua-lite/cua-lite, which has 107 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 25, 2026.

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