Agent skill

Scienceworld Object Selector

by zjunlp in zjunlp/SkillNet

A skill your agent uses when the agent needs to choose a specific object from multiple candidates in the environment based on task criteria such as object type (non-living thing, electrical…

MITAuto-check passed

Install Scienceworld Object Selector

skills CLI
$ npx skills add zjunlp/SkillNet --skill scienceworld-object-selector -a claude-code

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

GitHub CLI
$ gh skill install zjunlp/SkillNet scienceworld-object-selector --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-object-selector .claude/skills/scienceworld-object-selector && 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-object-selector
GitHub stars
1.4k
Token cost
~744 tokens
SKILL.md length
276 words
Files
2 (incl. references)
Skills in repo
122
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the agent needs to choose a specific object from multiple candidates in the environment based on task criteria such as object type (non-living thing, electrical…

  • Works in 5 steps: Survey the environment -- Use look… → Evaluate candidates -- For each visible… → Select the best match -- Choose the… → …
  • Electrical component
  • SKILL.md covers Purpose, When to Use, Workflow and Examples, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Scienceworld Object Selector is an agent skill from zjunlp/SkillNet. Use when the agent needs to choose a specific object from multiple candidates in the environment based on task criteria such as object type (non-living thing, electrical component, container), properties, or category. This skill surveys visible objects with "look around", evaluates each against the task requirements, selects the most suitable candidate, and signals intent with "focus on [OBJECT]".

Its SKILL.md is about 740 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/object_properties.md`).

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

When your agent uses it

  • Electrical component

Example prompts

  • “look around”
  • “focus on [OBJECT]”
  • “/scienceworld-object-selector”

Workflow steps

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

  1. Survey the environment -- Use look around to list all visible objects in the current location.
  2. Evaluate candidates -- For each visible object, determine if it matches the task criteria. Exclude target containers (e.g., destination…
  3. Select the best match -- Choose the first suitable, portable object unless the task specifies a preference (e.g., "largest", "closest").
  4. Signal intent -- Execute focus on [OBJECT] to confirm selection.
  5. Execute the task action -- Proceed with the required action (e.g., pick up, move, use).

What it can do on your machine

Read from SKILL.md and the folder at commit 3fcebf8. 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 Object Selector loads about 744 tokens when it runs, and up to ~1.1k if it reads all its reference files. Until then it costs about 107 tokens; SKILL.md has 276 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~107
When it runs · the whole SKILL.md, loaded when a task matches
~744
With references · SKILL.md plus every file in references/, read only if the agent opens them
~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 zjunlp/SkillNet at commit 3fcebf8, republished under its MIT licence (© zjunlp). 276 words, ~744 tokens.

Download SKILL.mdSave it as .claude/skills/scienceworld-object-selector/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
scienceworld-object-selector
description
Use when the agent needs to choose a specific object from multiple candidates in the environment based on task criteria such as object type (non-living thing, electrical component, container), properties, or category. This skill surveys visible objects with "look around", evaluates each against the task requirements, selects the most suitable candidate, and signals intent with "focus on [OBJECT]".

Skill: scienceworld-object-selector

Purpose

Identify and select the correct object from visible candidates in the ScienceWorld environment based on task-defined criteria (e.g., "non-living thing", "electrical component", "container"), then signal intent with a focus on action.

When to Use

  • When a task requires choosing a specific type of object from multiple visible options
  • When the agent must classify objects by property (living/non-living, material type, function) to select one
  • When the task instructs finding and interacting with a particular category of object

Workflow

  1. Survey the environment -- Use look around to list all visible objects in the current location.
  2. Evaluate candidates -- For each visible object, determine if it matches the task criteria. Exclude target containers (e.g., destination boxes) and fixed furniture from candidates.
  3. Select the best match -- Choose the first suitable, portable object unless the task specifies a preference (e.g., "largest", "closest").
  4. Signal intent -- Execute focus on [OBJECT] to confirm selection.
  5. Execute the task action -- Proceed with the required action (e.g., pick up, move, use).

Examples

Example 1: Find a non-living thing and move it

Task: "Find a non-living thing. First, focus on the thing. Then, move it to the purple box."

> look around
You see: purple box, table, battery, black wire, blue light bulb, red light bulb, red wire, switch, violet light bulb, yellow wire, ultra low temperature freezer.

Evaluation: Purple box is the destination. Table and freezer are fixed furniture. Remaining items (battery, wires, bulbs, switch) are all non-living and portable.

> focus on black wire
You focus on the black wire.

> move black wire to purple box
You move the black wire to the purple box.
Example 2: Find an electrical component

Task: "Find an electrical component and place it on the workbench."

> look around
You see: workbench, chair, battery, glass cup, red wire, notebook.

> focus on battery
You focus on the battery.

> move battery to workbench
You move the battery to the workbench.

Key Principles

  • Exclude destinations -- Never select the target container or destination as the candidate object.
  • Verify if uncertain -- Use examine [OBJECT] for more detail about an object's properties before selecting.
  • Task alignment -- The selection should enable the next action in the task sequence.

© 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 1 other file (references) in experiments/src/skills/scienceworld/scienceworld-object-selector of zjunlp/SkillNet.

  • SKILL.md
  • references/object_properties.md

Open the folder on GitHubat commit 3fcebf8

Compare with similar skills

Scienceworld Object Selector 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 Object Selector compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Scienceworld Object Selector this skillzjunlp/SkillNet1.4k—~744Automated safety check: PassMIT
Has Selectorthedaviddias/Front-End-Checklist74k—~547Automated safety check: PassMIT
Object Altthedaviddias/Front-End-Checklist74k—~429Automated safety check: PassMIT
Add Selectorsimstudioai/sim30k—~1.7kAutomated safety check: PassApache-2.0
Validate Selectorsimstudioai/sim30k—~1.2kAutomated safety check: PassApache-2.0
Object Storagesickn33/agentic-awesome-skills47k2 repos~2.6kAutomated safety check: PassMIT

Similar skills

  • Has Selector

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing stylesheets or components that use JavaScript to toggle classes on parent elements based on child state, form input values, or content presence — :has() may…

    74k GitHub stars~547 tokensUpdated 2 days ago
    Frontend & DesignAuto-check passed
  • Object Alt

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Provide alternative text for objects.

    74k GitHub stars~429 tokensUpdated 2 days ago
    Frontend & DesignAuto-check passed
  • Add Selector

    simstudioai/sim

    Add or update a Sim dynamic selector using the shared manifest, server attachment, and selectors.execute path.

    30k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Validate Selector

    simstudioai/sim

    Audit a Sim dynamic selector across its declaration, browser-safe manifest, server attachment, provider primitive, and selectors.execute security boundary.

    30k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Object Storage

    sickn33/agentic-awesome-skills

    Configure object storage with S3, GCS, and MinIO. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 2 repos~2.6k tokens
    Backend & APIsAuto-check passed
  • Neon Object Storage

    sickn33/agentic-awesome-skills

    S3-compatible object storage that branches with your Neon project, so files and the database stay in sync across every branch.

    47k GitHub starsUsed in 1 repo~2.9k tokens
    Backend & APIsAuto-check: notes

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
  • Performs an initial scan of the ALFWorld environment to identify all visible objects and receptacles.

    1.4k GitHub starsUsed in 1 repo~786 tokens
    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
  • 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 Object Selector

What does Scienceworld Object Selector do?

A skill your agent uses when the agent needs to choose a specific object from multiple candidates in the environment based on task criteria such as object type (non-living thing, electrical…. Scienceworld Object Selector is an agent skill from zjunlp/SkillNet. Use when the agent needs to choose a specific object from multiple candidates in the environment based on task criteria such as object type (non-living thing, electrical component, container), properties, or category.

When should I use Scienceworld Object Selector?

Scienceworld Object Selector fits situations like: electrical component.

How do I install Scienceworld Object Selector in Claude Code?

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

How do I install Scienceworld Object Selector in Codex?

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

Can I use Scienceworld Object Selector 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-object-selector -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-object-selector, .gemini/skills/scienceworld-object-selector, .github/skills/scienceworld-object-selector and .opencode/skills/scienceworld-object-selector in your project.

What does Scienceworld Object Selector need to run?

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

Does Scienceworld Object Selector 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 Object Selector 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 Object Selector use?

Scienceworld Object Selector 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 Object Selector use?

About 744 tokens (SKILL.md is roughly 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 382 tokens, read only when the agent opens those files.

What are the alternatives to Scienceworld Object Selector?

Skills that share tags, products or a category with Scienceworld Object Selector: Has Selector (thedaviddias/Front-End-Checklist, 74k stars), Object Alt (thedaviddias/Front-End-Checklist, 74k stars), Add Selector (simstudioai/sim, 30k stars) and Validate Selector (simstudioai/sim, 30k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Scienceworld Object Selector?

zjunlp (a GitHub organization) maintains it in zjunlp/SkillNet, which has 1,393 GitHub stars. The repository holds 122 skills in this directory. The repository was last updated on October 7, 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.