Agent skill

Scienceworld Ambiguous Action Resolution

by zjunlp in zjunlp/SkillNet

A skill your agent uses when the ScienceWorld environment returns an "Ambiguous request" prompt with a numbered list of identical action options.

MITAuto-check passed

Install Scienceworld Ambiguous Action Resolution

skills CLI
$ npx skills add zjunlp/SkillNet --skill scienceworld-ambiguous-action-resolution -a claude-code

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

GitHub CLI
$ gh skill install zjunlp/SkillNet scienceworld-ambiguous-action-resolution --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-ambiguous-action-resolution .claude/skills/scienceworld-ambiguous-action-resolution && 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-ambiguous-action-resolution
GitHub stars
1.4k
Token cost
~797 tokens
SKILL.md length
292 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 ScienceWorld environment returns an "Ambiguous request" prompt with a numbered list of identical action options.

  • Works in 4 steps: Recognize the prompt -- Identify the… → Scan the options -- Confirm that the… → Select the lowest number -- Choose 0… → …
  • The ScienceWorld environment returns an Ambiguous request prompt with a numbered list of identical action options
  • SKILL.md covers Purpose, When to Use, Workflow and Examples, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Scienceworld Ambiguous Action Resolution is an agent skill from zjunlp/SkillNet. Use when the ScienceWorld environment returns an "Ambiguous request" prompt with a numbered list of identical action options. This skill resolves the disambiguation by selecting the lowest available number (typically 0) to proceed, ensuring task progression when multiple identical object instances exist and the system cannot automatically determine which instance to act upon.

Its SKILL.md is about 800 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/trajectory_examples.md`).

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

When your agent uses it

  • The ScienceWorld environment returns an Ambiguous request prompt with a numbered list of identical action options

Example prompts

  • “Ambiguous request”
  • “/scienceworld-ambiguous-action-resolution”

Workflow steps

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

  1. Recognize the prompt -- Identify the exact phrase: "Ambiguous request: Please enter the number for the action you intended (or blank to…
  2. Scan the options -- Confirm that the listed options (0, 1, 2...) are functionally identical, referring to different instances of the same…
  3. Select the lowest number -- Choose 0 (the first option) to proceed. Any valid selection will produce the same result.
  4. Execute -- Output the selected number as the next action.

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 Ambiguous Action Resolution loads about 797 tokens when it runs, and up to ~870 if it reads all its reference files. Until then it costs about 105 tokens; SKILL.md has 292 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~105
When it runs · the whole SKILL.md, loaded when a task matches
~797
With references · SKILL.md plus every file in references/, read only if the agent opens them
~870

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). 292 words, ~797 tokens.

Download SKILL.mdSave it as .claude/skills/scienceworld-ambiguous-action-resolution/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
scienceworld-ambiguous-action-resolution
description
Use when the ScienceWorld environment returns an "Ambiguous request" prompt with a numbered list of identical action options. This skill resolves the disambiguation by selecting the lowest available number (typically 0) to proceed, ensuring task progression when multiple identical object instances exist and the system cannot automatically determine which instance to act upon.

Skill: scienceworld-ambiguous-action-resolution

Purpose

Resolve system disambiguation prompts that block task progression when the ScienceWorld environment cannot determine which identical object instance the agent intends to act upon. This is a mechanical bypass, not a decision-making step.

When to Use

  • When the environment returns an observation containing "Ambiguous request: Please enter the number for the action you intended (or blank to cancel):" followed by a numbered list
  • When multiple identical object instances exist (e.g., five identical banana seeds in a jar) and the system requires explicit selection
  • Only when options are functionally identical -- do NOT use this skill for menu selections where options have different meanings

Workflow

  1. Recognize the prompt -- Identify the exact phrase: "Ambiguous request: Please enter the number for the action you intended (or blank to cancel):".
  2. Scan the options -- Confirm that the listed options (0, 1, 2...) are functionally identical, referring to different instances of the same object.
  3. Select the lowest number -- Choose 0 (the first option) to proceed. Any valid selection will produce the same result.
  4. Execute -- Output the selected number as the next action.

Examples

Example 1: Moving one of several identical banana seeds

Observation:

Ambiguous request: Please enter the number for the action you intended (or blank to cancel):
0: move banana seed (in seed jar, in inventory, in agent, in greenhouse) to flower pot 1 (in greenhouse)
1: move banana seed (in seed jar, in inventory, in agent, in greenhouse) to flower pot 1 (in greenhouse)
2: move banana seed (in seed jar, in inventory, in agent, in greenhouse) to flower pot 1 (in greenhouse)

Action:

> 0

The system proceeds with moving one banana seed to flower pot 1.

Example 2: Picking up one of several identical items

Observation:

Ambiguous request: Please enter the number for the action you intended (or blank to cancel):
0: pick up red wire (on table, in workshop)
1: pick up red wire (on table, in workshop)

Action:

> 0

Key Principles

  • Efficiency -- Do not overthink; the objects are identical and any choice is valid.
  • Consistency -- Always default to 0 unless task logic specifically requires a different instance.
  • Scope -- This skill is strictly a disambiguation mechanic, not a decision-making process.

Anti-Patterns

  • Do NOT use for non-ambiguous choices where options have different meanings.
  • Do NOT trigger if the observation does not contain the exact "Ambiguous request" phrase.
  • Do NOT waste steps analyzing differences between identical instances.

© 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-ambiguous-action-resolution of zjunlp/SkillNet.

  • SKILL.md
  • references/trajectory_examples.md

Open the folder on GitHubat commit c527136

Compare with similar skills

Scienceworld Ambiguous Action Resolution 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 Ambiguous Action Resolution compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Scienceworld Ambiguous Action Resolution this skillzjunlp/SkillNet1.4k—~797Automated safety check: PassMIT
ActionsJetBrains/intellij-community21k—~341Automated safety check: PassCustom licence
Laravel Actionscoollabsio/coolify63k—~2.4kAutomated safety check: PassApache-2.0
ActionsBuilderIO/agent-native7.1k—~4.4kAutomated safety check: PassNone
GitHub Actionssickn33/agentic-awesome-skills47k1 repos~1.9kAutomated safety check: PassMIT
Cmdk Actionsgetsentry/sentry46k—~6.3kAutomated safety check: PassCustom licence

Similar skills

  • Actions

    JetBrains/intellij-community

    Official

    Implement or change IntelliJ AnAction actions and registrations.

    21k GitHub stars~341 tokensUpdated today
    MobileAuto-check passed
  • Laravel Actions

    coollabsio/coolify

    Build, refactor, and troubleshoot Laravel Actions using lorisleiva/laravel-actions.

    63k GitHub stars~2.4k tokensUpdated today
    Backend & APIsAuto-check passed
  • Actions

    BuilderIO/agent-native

    How to create and run agent actions. An agent skill from BuilderIO/agent-native.

    7.1k GitHub stars~4.4k tokensUpdated today
    Backend & APIsAuto-check passed
  • GitHub Actions

    sickn33/agentic-awesome-skills

    Build, test, and deploy applications using GitHub Actions workflows.

    47k GitHub starsUsed in 1 repo~1.9k tokens
    DevOps & CloudAuto-check passed
  • Cmdk Actions

    getsentry/sentry

    Official

    Guide for adding new actions to Sentry's Command+K palette. An agent skill from getsentry/sentry.

    46k GitHub stars~6.3k tokensUpdated today
    Auto-check passed
  • Official

    The resolution criteria for PostHog Review's resolution stage: the bar for deciding, per unresolved review thread, whether the ask is worth implementing and safe to implement unattended.

    40k GitHub stars~1.4k tokensUpdated today
    Auto-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 today
    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 today
    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 today
    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 today
    Auto-check passed
  • Performs an initial scan of the ALFWorld environment to identify all visible objects and receptacles.

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

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

Questions about Scienceworld Ambiguous Action Resolution

What does Scienceworld Ambiguous Action Resolution do?

A skill your agent uses when the ScienceWorld environment returns an "Ambiguous request" prompt with a numbered list of identical action options. Scienceworld Ambiguous Action Resolution is an agent skill from zjunlp/SkillNet. Use when the ScienceWorld environment returns an "Ambiguous request" prompt with a numbered list of identical action options.

When should I use Scienceworld Ambiguous Action Resolution?

Scienceworld Ambiguous Action Resolution fits situations like: the ScienceWorld environment returns an Ambiguous request prompt with a numbered list of identical action options.

How do I install Scienceworld Ambiguous Action Resolution in Claude Code?

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

How do I install Scienceworld Ambiguous Action Resolution in Codex?

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

Can I use Scienceworld Ambiguous Action Resolution 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-ambiguous-action-resolution -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-ambiguous-action-resolution, .gemini/skills/scienceworld-ambiguous-action-resolution, .github/skills/scienceworld-ambiguous-action-resolution and .opencode/skills/scienceworld-ambiguous-action-resolution in your project.

What does Scienceworld Ambiguous Action Resolution need to run?

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

Does Scienceworld Ambiguous Action Resolution 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 Ambiguous Action Resolution 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 Ambiguous Action Resolution use?

Scienceworld Ambiguous Action Resolution 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 Ambiguous Action Resolution use?

About 797 tokens (SKILL.md is roughly 3.2k 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 73 tokens, read only when the agent opens those files.

What are the alternatives to Scienceworld Ambiguous Action Resolution?

Skills that share tags, products or a category with Scienceworld Ambiguous Action Resolution: Actions (JetBrains/intellij-community, 21k stars), Laravel Actions (coollabsio/coolify, 63k stars), Actions (BuilderIO/agent-native, 7.1k stars) and GitHub Actions (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Scienceworld Ambiguous Action Resolution?

zjunlp (a GitHub organization) maintains it in zjunlp/SkillNet, which has 1,394 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.