Computer Use
Use when a task needs an app on the user's own screen — a native desktop application (instrument control software, Origin, GraphPad, ImageJ, a reference manager, a spreadsheet), or a desktop browser window that needs window-level control. Read before the first `computer` call. Covers the observe-act-observe loop, why element indexes go stale, which action to prefer for which control, what "unverified" means and why it must never be reported as success, and the recovery for each error code. Not for page-level web automation (use the browser connector) and not for anything that can be done from
Install
npx skills add ai4s-research/open-science --skill computer-usegit clone --depth 1 https://github.com/ai4s-research/open-science.git /tmp/open-science
mkdir -p ~/.claude/skills
cp -r /tmp/open-science/runtime/skills/core/computer-use ~/.claude/skills/computer-usePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Computer use `computer` reads an app's **accessibility tree** and acts on the numbered elements in it. The tree is the interface; a screenshot is confirmation. This design, and most of the rules below, come from [Orca](https://github.com/stablyai/orca) (MIT). ## Before anything else Use this only when there is no better route. A file is read with `read`, a computation is run in the shell, a web page is driven by the browser connector. Reach for `computer` when the capability lives in a desktop app and nowhere else. The user sees a permission prompt on the first call of a session. Say what you intend to do before you make it. **Never** push, submit a form, send a message, buy, delete, or change an account setting unless the user asked for that exact thing. If an app holds content the user did not ask about, read only what the task needs. ## The loop ``` computer(action: "list_apps") computer(action: "get_state", app: "com.spotify.client") computer(action: "click", app: "com.spotify.client", elementIndex: 42) computer(action: "get_state", app: "com.spotify.client") ``` Observe, act once, observe again. Every action already returns the new state, so the reply to an action is also the next thing you read. ## Element indexes go stale The numbers in the tree are valid for **that** snapshot of **that** window. Navigation, scrolling, a focus change, a dialog, an app re-render, or simply a few seconds passing can invalidate them.
Details
- Skill name
computer-use- Repository
- ai4s-research/open-science
- Path
runtime/skills/core/computer-use/SKILL.md- Repo updated
- 17 November 2026
FAQ
What does the Computer Use skill do?
Use when a task needs an app on the user's own screen — a native desktop application (instrument control software, Origin, GraphPad, ImageJ, a reference manager, a spreadsheet), or a desktop browser window that needs window-level control. Read before the first `computer` call. Covers the observe-act-observe loop, why element indexes go stale, which action to prefer for which control, what "unverified" means and why it must never be reported as success, and the recovery for each error code. Not for page-level web automation (use the browser connector) and not for anything that can be done from
How do I install the Computer Use skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add ai4s-research/open-science --skill computer-use. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Computer Use popular?
It lives in ai4s-research/open-science, which has 2,105 GitHub stars and 231 forks.
Related skills
Domain Check
2.1kai4s-research/open-science
Use ONLY when the user asks to check, validate, review or audit analysis code for scientific correctness, or when you are the reviewer agent running its checks. Never run it unprompted as part of ordinary analysis work. Covers physics, earth/geo, biology, chemistry, social science and bioprocess/fermentation. Runs a deterministic domain-correctness gate that catches code which runs but is scientifically wrong (unit/dimension mismatch, Euclidean distance on lat/lon without a CRS, 0-based/1-based coordinate and strand errors, impossible SMILES valence, uncorrected multiple comparisons, averaging
Large File
2.1kai4s-research/open-science
Use BEFORE reading any data file that could be large (CSV/TSV, Parquet, HDF5, FITS, NetCDF, NDJSON, genomics FASTQ/FASTA/VCF/BAM, GRIB, ROOT, or big text/simulation logs like VASP OUTCAR). Returns a compact memory pointer — header/schema/shape/sample/key numbers — by introspection and sampling in bounded memory, so you never load a file bigger than the context window into the model. Reference data via the pointer; read specific ranges deterministically.
Modal Run
2.1kai4s-research/open-science
Use when the user asks to run heavy or GPU work on Modal (the cloud compute platform) — writing a Modal function in the workspace, running it with the user's own `modal` CLI + token, and bringing results back. Data-to-compute for jobs too big for the laptop, without a Slurm cluster.
Remote Compute
2.1kai4s-research/open-science
Use when the user asks to run, submit, monitor, or cancel a job on a remote machine over SSH — their own GPU/CPU server, a workstation, or a Slurm cluster ("the cluster", a login node, "my 3090 box", "the compute server"). Picks a saved machine, runs the work directly over SSH (or via Slurm when present), tracks it, and fetches results back into the workspace.
Code Simplifier
1.2kgetsentry/skills
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Use when asked to "simplify code", "clean up code", "refactor for clarity", "improve readability", or review recently modified code for elegance. Focuses on project-specific best practices.
Information Architecture
3.4kOwl-Listener/designer-skills
Design content structure, hierarchy, labelling, and the navigation model. Use when organising what exists. For the UI that exposes it use `navigation-patterns` (interaction-design); for user-generated grouping evidence use `card-sort-analysis` (design-research).
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.