Home / zjunlp / skillnet · experiments/src/skills/alfworld/alfworld-goal-interpreter/SKILL.md · GitHub

alfworld-goal-interpreter skillA

alfworld-goal-interpreter is agent-read markdown (skill) from zjunlp/skillnet: Parses the natural language task goal to extract actionable sub-objectives and required objects. Trigger this skill whenever a new task is assigned to break down complex instructions into clear, sequential targets. It interprets phrases like 'look at X under Y' to identify target objects (pillow), reference objects (desklamp), and spatial relationships (under)..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Goal Interpretation Protocol

## 1. Parse the Task Statement
When a new task is assigned, immediately analyze the natural language instruction to extract its core components. Use the parsing script (`parse_goal.py`) to perform this analysis.

**Input:** The raw task string (e.g., "look at pillow under the desklamp").
**Output:** A structured dictionary containing:
- `primary_target`: The main object to interact with.
- `reference_object`: The object that defines a location or condition.
- `spatial_relation`: The preposition linking them (e.g., under, on, in).
- `action`: The verb defining the required interaction.

## 2. Generate Sub-Objectives
Based on the parsed components, formulate a clear, sequential plan. The plan must account for the spatial relationship.

**Example Logic:**
- **IF** relation is `under` → Sub-goal 1: Locate the `reference_object`. Sub-goal 2: Inspect the area beneath it for the `primary_target`.
- **IF** relation is `in` or `on` → Sub-goal 1: Locate the `reference_object`. Sub-goal 2: Check its contents/surface.

## 3. Identify Required Objects & Actions
…

Read the whole file at its exact version.

How to install

Latest version
mdr add zjunlp/skillnet/alfworld-goal-interpreter@git:20260307.388baa3
Exact content
mdr add zjunlp/skillnet/alfworld-goal-interpreter@sha256:5459842fff5b2a2b

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_5kwsno74o4cmvjxd.svg)](https://markdownregistry.com/a/art_5kwsno74o4cmvjxd)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260307.388baa3 latest2026-03-07 388baa3 2,302 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2302 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

zjunlp/skillnet · 1,266 stars · license MIT · pushed 2026-09-25 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_5kwsno74o4cmvjxd
GET https://markdownregistry.com/api/v1/resolve?ref=zjunlp/skillnet/alfworld-goal-interpreter
GET https://markdownregistry.com/api/v1/blob/5459842fff5b2a2b76e4827456774e55d383abc615ea179d65526c2257b7621c

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from zjunlp/skillnet

alfworld-appliance-navigator skill
zjunlp/skillnet · experiments/src/skills/alfworld/alfworld-appliance-navigator/SKILL.md · Navigates the agent to a target appliance (microwave, stove, fridge, or sinkbasin) needed for object processing. Use…
git:20260316.e08426e · audit A · 1,266 stars
alfworld-appliance-preparer skill
zjunlp/skillnet · experiments/src/skills/alfworld/alfworld-appliance-preparer/SKILL.md · Prepares a household appliance (microwave, oven, toaster, fridge) for use by ensuring it is in the correct open/closed…
git:20260316.e08426e · audit A · 1,266 stars
alfworld-clean-object skill
zjunlp/skillnet · experiments/src/skills/alfworld/alfworld-clean-object/SKILL.md · Cleans a specified object using an appropriate cleaning receptacle (e.g., sinkbasin). Use when a task requires an…
git:20260316.e08426e · audit A · 1,266 stars
alfworld-device-operator skill
zjunlp/skillnet · experiments/src/skills/alfworld/alfworld-device-operator/SKILL.md · Operates a device or appliance (like a desklamp, microwave, or fridge) to interact with another object. Use when the…
git:20260316.e08426e · audit A · 1,266 stars
alfworld-environment-scanner skill
zjunlp/skillnet · experiments/src/skills/alfworld/alfworld-environment-scanner/SKILL.md · Performs an initial scan of the ALFWorld environment to identify all visible objects and receptacles. Use when you…
git:20260316.e08426e · audit A · 1,266 stars
alfworld-heat-object-with-appliance skill
zjunlp/skillnet · experiments/src/skills/alfworld/alfworld-heat-object-with-appliance/SKILL.md · Uses a heating appliance (microwave, stoveburner, oven) to apply heat to a specified object. Use when the task requires…
git:20260316.e08426e · audit A · 1,266 stars
alfworld-inventory-management skill
zjunlp/skillnet · experiments/src/skills/alfworld/alfworld-inventory-management/SKILL.md · Use when the agent must collect and track multiple instances of the same object type in ALFWorld (e.g., "put two…
git:20260316.e08426e · audit A · 1,266 stars
alfworld-locate-target-object skill
zjunlp/skillnet · experiments/src/skills/alfworld/alfworld-locate-target-object/SKILL.md · Navigates to a suspected location and identifies a target object. Use when your goal requires finding a specific object…
git:20260316.e08426e · audit A · 1,266 stars
alfworld-location-navigator skill
zjunlp/skillnet · experiments/src/skills/alfworld/alfworld-location-navigator/SKILL.md · Moves the agent to a specified receptacle or object location within the Alfworld environment. Use this skill when the…
git:20260307.388baa3 · audit A · 1,266 stars
alfworld-navigation-planner skill
zjunlp/skillnet · experiments/src/skills/alfworld/alfworld-navigation-planner/SKILL.md · Plans a path to move the agent between receptacles to search for target objects. Use this when you need to traverse the…
git:20260307.388baa3 · audit A · 1,266 stars
alfworld-object-cooler skill
zjunlp/skillnet · experiments/src/skills/alfworld/alfworld-object-cooler/SKILL.md · Cools a held object using an appropriate cooling appliance such as a fridge or freezer. Use when the task requires…
git:20260316.e08426e · audit A · 1,266 stars
alfworld-object-disposer skill
zjunlp/skillnet · experiments/src/skills/alfworld/alfworld-object-disposer/SKILL.md · This skill disposes of an object by placing it into a disposal receptacle like a garbage can. It should be triggered…
git:20260307.388baa3 · audit A · 1,266 stars

Every file in zjunlp/skillnet

Browse by kind, by grade A, or by owner.