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

Deploy Experiment

by GRIND-Lab-Core in GRIND-Lab-Core/night_owl_research_agent

Deploy and run experiments for ML/DL training (local, remote, or Modal GPU) AND spatial data science / GIScience experiments (local, data-driven).

No licenceAuto-check: notesData & Analytics

Install Deploy Experiment

skills CLI
$ npx skills add GRIND-Lab-Core/night_owl_research_agent --skill deploy-experiment -a claude-code

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

GitHub CLI
$ gh skill install GRIND-Lab-Core/night_owl_research_agent deploy-experiment --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/GRIND-Lab-Core/night_owl_research_agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/deploy-experiment .claude/skills/deploy-experiment && 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
deploy-experiment
GitHub stars
106
Used in
1 other repo
Token cost
~5k tokens
SKILL.md length
1,957 words
Files
1
Skills in repo
19
Repo updated
First seen
Licence
None found

At a glance

Deploy and run experiments for ML/DL training (local, remote, or Modal GPU) AND spatial data science / GIScience experiments (local, data-driven).

  • Works in 4 steps: Mandatory Local GPU Availability Check… → 1: Classify the Experiment → (Both Tracks): Verify & Record → …
  • User says run experiment
  • SKILL.md covers Inputs, Outputs (all under…, Step 0: Mandatory Local GPU… and Step 0.1: Classify the…, plus 7 more sections
  • Calls ssh, python and git; reaches wandb.ai; needs WANDB_API_KEY

What it does

Deploy Experiment is an agent skill from GRIND-Lab-Core/night_owl_research_agent. Deploy and run experiments for ML/DL training (local, remote, or Modal GPU) AND spatial data science / GIScience experiments (local, data-driven). Reads from output/refine-logs/EXPERIMENTPLAN.md and output/refine-logs/FINALPROPOSAL.md, writes to output/experiment/. Use when user says "run experiment", "deploy experiment", "execute experiment plan", or needs to launch training / spatial analysis jobs.

Its SKILL.md is about 5k 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 Data & Analytics, covering Geospatial analysis. The repository describes itself as: Fully automatic AI research agent for Geoscientists, Remote Sensing researchers, and GIScientists. Features harness engineering, GeoBenchmark (OLS/GWR/MGWR), journal templates…

When your agent uses it

  • User says run experiment
  • Deploy experiment
  • Execute experiment plan
  • Needs to launch training / spatial analysis jobs

Example prompts

  • “run experiment”
  • “deploy experiment”
  • “execute experiment plan”
  • “/deploy-experiment”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Bash(*), Read, Grep, Glob, Edit, Write, Agent

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Mandatory Local GPU Availability Check (pilot AND full experiments)
  2. 1: Classify the Experiment
  3. (Both Tracks): Verify & Record
  4. (Both Tracks): Write EXPERIMENT_RESULT.md

What it can do on your machine

Read from SKILL.md and the folder at commit 5f7a246. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(*)
    • Read
    • Grep
    • Glob
    • Edit
    • Write
    • Agent

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • ssh
    • python
    • git
    • rsync
    • conda
    • scp
    • pip

    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:

    • wandb.ai

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • WANDB_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deploy Experiment loads about 5k tokens when it runs. Until then it costs about 106 tokens; SKILL.md has 1,957 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~106
When it runs · the whole SKILL.md, loaded when a task matches
~5k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash(*), Read, Grep, Glob, Edit, Write, Agent

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 1,957 words (~4,963 tokens).

“Execute the experiment described in output/refine-logs/EXPERIMENT_PLAN.md (with context from output/refine-logs/FINAL_PROPOSAL.md) and write all results to output/experiment/.”

— opening of SKILL.md by GRIND-Lab-Core
name
deploy-experiment
allowed-tools
Bash(*), Read, Grep, Glob, Edit, Write, Agent
argument-hint
experiment-description-or-scope

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/deploy-experiment of GRIND-Lab-Core/night_owl_research_agent.

Open the folder on GitHubat commit 5f7a246

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 GRIND-Lab-Core/night_owl_research_agent, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Deploy Experiment 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.

Deploy Experiment compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deploy Experiment this skillGRIND-Lab-Core/night_owl_research_agent1061 repos~5kAutomated safety check: NotesNone
Antv L7antvis/L74.1k—~1.4kAutomated safety check: PassMIT
Geo SleuthOldcircle/geo-sleuth1.3k—~6.1kAutomated safety check: PassMIT
Portaljs Add Geodatopian/portaljs2.4k1 repos~1.7kAutomated safety check: PassMIT
Thematic Mapzzhonglei/GeoCode-Release187—~3.1kAutomated safety check: PassMIT
Rs Paper Pipelinethinson/RS-PaperClaw227—~319Automated safety check: PassMIT

Similar skills

  • Antv L7

    antvis/L7

    Comprehensive guide for AntV L7 geospatial visualization library.

    4.1k GitHub stars~1.4k tokensUpdated 29 days ago
    Data & AnalyticsAuto-check passed

  • Geo Sleuth

    Oldcircle/geo-sleuth

    Geolocate or chronolocate a photo with tool-verified reasoning (where was this taken / when was it taken / photo geolocation / geo-guessing).

    1.3k GitHub stars~6.1k tokensUpdated today
    Data & AnalyticsAuto-check passed

  • Portaljs Add Geo

    datopian/portaljs

    Auto-ingest a geospatial file (GeoJSON, Shapefile, GeoPackage, KML/KMZ, FlatGeobuf, CSV-with-geometry) into a PortalJS portal on the user's own machine, with no server.

    2.4k GitHub starsUsed in 1 repo~1.7k tokens
    Data & AnalyticsAuto-check passed

  • Thematic Map

    zzhonglei/GeoCode-Release

    Create well-designed maps that follow standard cartographic conventions.

    187 GitHub stars~3.1k tokensUpdated 3 days ago
    Data & AnalyticsAuto-check passed

  • Rs Paper Pipeline

    thinson/RS-PaperClaw

    A skill your agent uses when operating or maintaining the RS-PaperClaw pipeline that fetches remote-sensing arXiv papers, creates per-paper issues, builds daily digests, reconciles issue sets, and…

    227 GitHub stars~319 tokensUpdated today
    Data & AnalyticsAuto-check passed

  • Remote Sensing Research Radar

    limi124/remote-sensing-research-radar

    Track, retrieve, screen, and synthesize research frontiers for geospatial AI, remote sensing big data, and transferable computer vision methods.

    142 GitHub stars~1.3k tokensUpdated 5 mo ago
    Data & AnalyticsAuto-check passed

More from GRIND-Lab-Core/night_owl_research_agent

All 19 skills in this repo

  • Research Review

    GRIND-Lab-Core/night_owl_research_agent

    Get a deep critical review of research idea from GPT via Codex MCP.

    106 GitHub starsUsed in 6 repos~1.1k tokens
    Auto-check: notes

  • Experiment Design

    GRIND-Lab-Core/night_owl_research_agent

    Turn a refined GIScience / remote sensing / spatial data science proposal into a detailed, claim-driven experiment roadmap.

    106 GitHub stars~3.3k tokensUpdated 5 mo ago
    Auto-check: warnings

  • Experiment Design Pipeline

    GRIND-Lab-Core/night_owl_research_agent

    Run an end-to-end workflow that chains the skills refine-research and experiment-design.

    106 GitHub stars~2.1k tokensUpdated 5 mo ago
    Auto-check: warnings

  • Generate Idea

    GRIND-Lab-Core/night_owl_research_agent

    Generate and rank research ideas given a broad direction. An agent skill from GRIND-Lab-Core/night_owl_research_agent.

    106 GitHub stars~3.2k tokensUpdated 5 mo ago
    Auto-check: warnings

  • Data Download

    GRIND-Lab-Core/night_owl_research_agent

    Discover, evaluate, and download publicly available datasets from the internet.

    106 GitHub stars~8.1k tokensUpdated 5 mo ago
    Auto-check: warnings

  • Paper Writing Pipeline

    GRIND-Lab-Core/night_owl_research_agent

    Full paper writing pipeline. An agent skill from GRIND-Lab-Core/night_owl_research_agent.

    106 GitHub stars~5.5k tokensUpdated 5 mo ago
    Auto-check: warnings

Categories

Questions about Deploy Experiment

What does Deploy Experiment do?

Deploy and run experiments for ML/DL training (local, remote, or Modal GPU) AND spatial data science / GIScience experiments (local, data-driven). Deploy Experiment is an agent skill from GRIND-Lab-Core/night_owl_research_agent. Deploy and run experiments for ML/DL training (local, remote, or Modal GPU) AND spatial data science / GIScience experiments (local, data-driven).

When should I use Deploy Experiment?

Deploy Experiment fits situations like: user says run experiment; deploy experiment; execute experiment plan; needs to launch training / spatial analysis jobs.

How do I install Deploy Experiment in Claude Code?

Run `npx skills add GRIND-Lab-Core/night_owl_research_agent --skill deploy-experiment -a claude-code`. Or copy the skill folder (skills/deploy-experiment in GRIND-Lab-Core/night_owl_research_agent) into .claude/skills/deploy-experiment in your project. Claude Code loads it when a task matches its description.

How do I install Deploy Experiment in Codex?

Run `npx skills add GRIND-Lab-Core/night_owl_research_agent --skill deploy-experiment -a codex`. Or copy the skill folder (skills/deploy-experiment in GRIND-Lab-Core/night_owl_research_agent) into .agents/skills/deploy-experiment in your project. Codex loads it when a task matches its description.

Can I use Deploy Experiment 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 GRIND-Lab-Core/night_owl_research_agent --skill deploy-experiment -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deploy-experiment, .gemini/skills/deploy-experiment, .github/skills/deploy-experiment and .opencode/skills/deploy-experiment in your project.

What does Deploy Experiment need to run?

Going by SKILL.md and its folder, Deploy Experiment needs the command-line tools its instructions call (ssh, python, git, rsync, conda and scp) and credentials named WANDB_API_KEY. Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash(*), Read, Grep, Glob, Edit, Write, Agent.

Does Deploy Experiment access the network?

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

Is Deploy Experiment safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Deploy Experiment use?

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

How many tokens does Deploy Experiment use?

About 5k tokens (SKILL.md is roughly 20k 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 Deploy Experiment?

Skills that share tags, products or a category with Deploy Experiment: Antv L7 (antvis/L7, 4.1k stars), Geo Sleuth (Oldcircle/geo-sleuth, 1.3k stars), Portaljs Add Geo (datopian/portaljs, 2.4k stars) and Thematic Map (zzhonglei/GeoCode-Release, 187 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deploy Experiment?

GRIND-Lab-Core (a GitHub organization) maintains it in GRIND-Lab-Core/night_owl_research_agent, which has 106 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on May 6, 2026.

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