Agent skill

Scienceworld Tool Fetcher

by zjunlp in zjunlp/SkillNet

This skill locates and picks up a specified tool or instrument from the environment.

MITAuto-check passed

Install Scienceworld Tool Fetcher

skills CLI
$ npx skills add zjunlp/SkillNet --skill scienceworld-tool-fetcher -a claude-code

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

GitHub CLI
$ gh skill install zjunlp/SkillNet scienceworld-tool-fetcher --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/zjunlp/SkillNet.git skills-src && mkdir -p .claude/skills && cp -r skills-src/experiments/src/skills/scienceworld/scienceworld-tool-fetcher .claude/skills/scienceworld-tool-fetcher && 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
scienceworld-tool-fetcher
GitHub stars
1.4k
Token cost
~584 tokens
SKILL.md length
290 words
Files
3 (incl. references)
Skills in repo
122
Repo updated
First seen
Licence
MIT

At a glance

This skill locates and picks up a specified tool or instrument from the environment.

  • Works in 4 steps: Identify the Target Tool → Locate the Tool via Exploration → Execute the Pick-up → …
  • SKILL.md covers 1. Identify the Target Tool, 2. Locate the Tool via…, 3. Execute the Pick-up and 4. Post-Action Verification…, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Scienceworld Tool Fetcher is an agent skill from zjunlp/SkillNet. This skill locates and picks up a specified tool or instrument from the environment. It should be triggered when a task requires a specific tool (e.g., thermometer, stopwatch) for measurement or manipulation. The skill identifies the tool's location via observation and executes a pick-up action, moving the tool to inventory.

Its SKILL.md is about 580 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/environment_actions.md` and `references/trajectory_analysis.md`).

The repository describes itself as: Create, Evaluate, and Connect AI Skills. The licence is MIT.

Example prompts

  • “/scienceworld-tool-fetcher”

Workflow steps

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

  1. Identify the Target Tool
  2. Locate the Tool via Exploration
  3. Execute the Pick-up
  4. Post-Action Verification (Optional)

What it can do on your machine

Read from SKILL.md and the folder at commit c527136. 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

Scienceworld Tool Fetcher loads about 584 tokens when it runs, and up to ~1.5k if it reads all its reference files. Until then it costs about 88 tokens; SKILL.md has 290 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~88
When it runs · the whole SKILL.md, loaded when a task matches
~584
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.5k

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 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 zjunlp/SkillNet at commit c527136, republished under its MIT licence (© zjunlp). 290 words, ~584 tokens.

Download SKILL.mdSave it as .claude/skills/scienceworld-tool-fetcher/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
scienceworld-tool-fetcher
description
This skill locates and picks up a specified tool or instrument from the environment. It should be triggered when a task requires a specific tool (e.g., thermometer, stopwatch) for measurement or manipulation. The skill identifies the tool's location via observation and executes a pick-up action, moving the tool to inventory.

Instructions

Primary Goal: Locate a specified tool and move it to your inventory.

1. Identify the Target Tool

  • The required tool will be specified in the user's task or request (e.g., "thermometer", "stopwatch", "lighter").
  • Confirm the exact name of the tool object.

2. Locate the Tool via Exploration

  • If you are not in the correct room, use teleport to [ROOM_NAME] to go to the most likely location (e.g., kitchen, workshop).
  • Use look around to survey the current room.
  • Scan the observation for the target tool name. It may be:
    • Listed directly in the room description (e.g., "a thermometer").
    • Inside an open container (e.g., "a fridge. In the fridge is: chocolate, a wood cup...").
  • If the tool is not immediately visible, examine likely containers using look at [CONTAINER] (e.g., look at counter, look at cupboard).

3. Execute the Pick-up

  • Once the tool is located, execute the action: pick up [TOOL_NAME].
  • Example: pick up thermometer.
  • Verify the action was successful by checking the observation for confirmation (e.g., "You move the thermometer to the inventory.").

4. Post-Action Verification (Optional)

  • If required by the broader task, you may perform a secondary action to signal readiness, such as focus on [TOOL_NAME] in inventory.

Key Constraints & Notes

  • Containers are Open: All containers are pre-opened. Do not use open or close actions.
  • Direct Action: Proceed directly to pick up. Do not attempt to move the tool to an intermediate location first.
  • Tool Not Found: If the tool is not in the initial room, systematically teleport to other relevant rooms and repeat the look around search pattern.
  • Single Tool: This skill fetches one specified tool. For multiple tools, trigger the skill sequentially.

Output: The target tool will be in your inventory, ready for use in subsequent task steps.

© zjunlp, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in experiments/src/skills/scienceworld/scienceworld-tool-fetcher of zjunlp/SkillNet.

  • SKILL.md
  • references/environment_actions.md
  • references/trajectory_analysis.md

Open the folder on GitHubat commit c527136

Compare with similar skills

Scienceworld Tool Fetcher 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.

Scienceworld Tool Fetcher compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Scienceworld Tool Fetcher this skillzjunlp/SkillNet1.4k—~584Automated safety check: PassMIT
Flutter Cherry Pickflutter/flutter179k—~1.8kAutomated safety check: PassBSD-3-Clause
Observability And Instrumentationsickn33/agentic-awesome-skills47k1 repos~2.9kAutomated safety check: PassMIT
Logic Locatesickn33/agentic-awesome-skills47k1 repos~977Automated safety check: PassMIT
Appinsights Instrumentationgithub/awesome-copilot40k1 repos~616Automated safety check: PassMIT
Skill Locationsremotion-dev/remotion63k—~182Automated safety check: PassCustom licence

Similar skills

  • Flutter Cherry Pick

    flutter/flutter

    How to land a formal cherry-pick of a merged PR for the flutter/flutter repo stable or beta channel.

    179k GitHub stars~1.8k tokensUpdated today
    MobileAuto-check passed
  • Observability And Instrumentation

    sickn33/agentic-awesome-skills

    Instruments code so production behavior is visible and diagnosable.

    47k GitHub starsUsed in 1 repo~2.9k tokens
    DevOps & CloudAuto-check passed
  • Logic Locate

    sickn33/agentic-awesome-skills

    Locate the root cause of a CONFIRMED failure via backward-then-forward semi-formal tracing.

    47k GitHub starsUsed in 1 repo~977 tokens
    DevelopmentAuto-check passed
  • Appinsights Instrumentation

    github/awesome-copilot

    Official

    Instrument a webapp to send useful telemetry data to Azure App Insights

    40k GitHub starsUsed in 1 repo~616 tokens
    DevOps & CloudAuto-check passed
  • Skill Locations

    remotion-dev/remotion

    Official

    Document Remotion skill placement. An agent skill from remotion-dev/remotion.

    63k GitHub stars~182 tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Automatically add PostHog analytics instrumentation to code.

    11k GitHub stars~420 tokensUpdated 29 days ago
    Frontend & DesignAuto-check passed

More from zjunlp/SkillNet

All 122 skills in this repo
  • Skillnet

    zjunlp/SkillNet

    Search, download, create, evaluate, analyze and route reusable agent skills with SkillNet.

    1.4k GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • This skill searches for a specific receptacle (e.g., garbage can, cabinet) by systematically exploring the environment, checking multiple locations until found.

    1.4k GitHub stars~709 tokensUpdated yesterday
    Auto-check passed
  • Prepares a household appliance (microwave, oven, toaster, fridge) for use by ensuring it is in the correct open/closed state.

    1.4k GitHub stars~611 tokensUpdated yesterday
    Auto-check passed
  • Operates a device or appliance (like a desklamp, microwave, or fridge) to interact with another object.

    1.4k GitHub stars~916 tokensUpdated yesterday
    Auto-check passed
  • Performs an initial scan of the ALFWorld environment to identify all visible objects and receptacles.

    1.4k GitHub stars~786 tokensUpdated yesterday
    Auto-check passed
  • Uses a heating appliance (microwave, stoveburner, oven) to apply heat to a specified object.

    1.4k GitHub stars~744 tokensUpdated yesterday
    Auto-check passed

Questions about Scienceworld Tool Fetcher

What does Scienceworld Tool Fetcher do?

This skill locates and picks up a specified tool or instrument from the environment. Scienceworld Tool Fetcher is an agent skill from zjunlp/SkillNet. This skill locates and picks up a specified tool or instrument from the environment.

How do I install Scienceworld Tool Fetcher in Claude Code?

Run `npx skills add zjunlp/SkillNet --skill scienceworld-tool-fetcher -a claude-code`. Or copy the skill folder (experiments/src/skills/scienceworld/scienceworld-tool-fetcher in zjunlp/SkillNet) into .claude/skills/scienceworld-tool-fetcher in your project. Claude Code loads it when a task matches its description.

How do I install Scienceworld Tool Fetcher in Codex?

Run `npx skills add zjunlp/SkillNet --skill scienceworld-tool-fetcher -a codex`. Or copy the skill folder (experiments/src/skills/scienceworld/scienceworld-tool-fetcher in zjunlp/SkillNet) into .agents/skills/scienceworld-tool-fetcher in your project. Codex loads it when a task matches its description.

Can I use Scienceworld Tool Fetcher 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 zjunlp/SkillNet --skill scienceworld-tool-fetcher -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scienceworld-tool-fetcher, .gemini/skills/scienceworld-tool-fetcher, .github/skills/scienceworld-tool-fetcher and .opencode/skills/scienceworld-tool-fetcher in your project.

What does Scienceworld Tool Fetcher need to run?

SKILL.md names no scripts, command-line tools or credentials: Scienceworld Tool Fetcher is instructions for the agent only.

Does Scienceworld Tool Fetcher 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 Scienceworld Tool Fetcher 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 Scienceworld Tool Fetcher use?

Scienceworld Tool Fetcher is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Scienceworld Tool Fetcher use?

About 584 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 872 tokens, read only when the agent opens those files.

What are the alternatives to Scienceworld Tool Fetcher?

Skills that share tags, products or a category with Scienceworld Tool Fetcher: Flutter Cherry Pick (flutter/flutter, 179k stars), Observability And Instrumentation (sickn33/agentic-awesome-skills, 47k stars), Logic Locate (sickn33/agentic-awesome-skills, 47k stars) and Appinsights Instrumentation (github/awesome-copilot, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Scienceworld Tool Fetcher?

zjunlp (a GitHub organization) maintains it in zjunlp/SkillNet, which has 1,397 GitHub stars. The repository holds 122 skills in this directory. The repository was last updated on October 9, 2026.

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