scienceworld-object-selector SKILL.md skillA
scienceworld-object-selector from zjunlp/skillnet is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add zjunlp/skillnet/scienceworld-object-selector@git:20260316.e08426ePins git:20260316.e08426e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- zjunlp/skillnet
- Path
experiments/src/skills/scienceworld/scienceworld-object-selector/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260316.e08426e, committed Mar 16, 2026
- First version recorded
- Mar 7, 2026
- Size
- 2,974 bytes
- Repository stars
- 1,449
- License
- MIT
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]".
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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. …
Read the whole file at its exact version.
How to install
mdr add zjunlp/skillnet/scienceworld-object-selector@sha256:7a7abdb5fd1f4e9cThe line at the top of this page pins the label git:20260316.e08426e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_76megnvwcvdlsnnd)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Mar 7, 2026 and Mar 16, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260316.e08426e latest | 2026-03-16 | e08426e | 2,974 B | A | view · diff |
| git:20260307.388baa3 | 2026-03-07 | 388baa3 | 2,033 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2974 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
zjunlp/skillnet · 1,449 stars · license MIT · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_76megnvwcvdlsnnd GET https://markdownregistry.com/api/v1/resolve?ref=zjunlp/skillnet/scienceworld-object-selector GET https://markdownregistry.com/api/v1/blob/7a7abdb5fd1f4e9c2d6a32271f6cbdf4430569c72f4318c6ae2f77e9b2c57a3e
Your AI assistant 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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.