Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Open Computer Use · ifuryst | DecimalAI

agent toolingby ifuryst

Open Computer Use

ifuryst/open-computer-use

Source ifuryst/open-codex-computer-use ↗License MIT

Platform-neutral guidance for using Open Computer Use, the open-source Computer Use MCP server and CLI for macOS, Linux, and Windows.

SkillScore100Maintained

Automatic

AI Engineer pack

Last verified 9/24/2026

What it changes

Passed 22 of 22 test cases with the skill, and 10 of 22 without it.

Without skill45%

With skill100%

Checks it passed that the model alone missed

States that macOS 14.0 or later is required.
Uses the --calls flag with open-computer-use call.
Passes mcp as the argument in the MCP configuration.

and 14 more in the full report

12 fixed10 passed either way0 still failing0 broke

Pass-rate lift: +55 pp
Tokens: +37%
Agent turns: 0%
Response time: -53%

Model Measured 9/24/2026v3 · latest is v422 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

This benchmark measured an earlier version of the skill.

A newer attempt on gemini-3.8-flash on 10/19/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/ifuryst-open-computer-use/SKILL.md https://app.decimal.ai/s/ifuryst-open-computer-use/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add ifuryst-open-computer-use, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/ifuryst-open-computer-use/ and pins it in .decimal/skills.lock

decimalai skills add ifuryst-open-computer-use

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/ifuryst-open-computer-use/SKILL.md https://app.decimal.ai/s/ifuryst-open-computer-use/SKILL.md

Raw file: /s/ifuryst-open-computer-use/SKILL.md ↗ · machine-readable summary at /s/ifuryst-open-computer-use.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

I need to run a multi-step GUI automation sequence against TextEdit using open-computer-use. I want to retrieve the current window state and press the Return key all in a single command process so the element index mapping stays intact. Provide the exact terminal command formatted as a clean shell snippet with the JSON payload included.

What was checked, without and with the skill
Checked	Without skill	With skill
Uses the --calls flag with open-computer-use call.	Missed	Passed
Formats the payload passed to --calls as a JSON array.	Missed	Passed

case-02 · gemini-3.6-flash · 9/24/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md85 lines4 files

Open Computer Use

Overview

Open Computer Use exposes Computer Use as a local CLI and stdio MCP server. It is not Codex.app-specific; adapt the commands and MCP config to the agent runtime you are operating in.

The macOS runtime requires macOS 14.0 or later. Windows and Linux use their own platform runtimes and are not subject to this macOS minimum.

It supports the same core tool surface across macOS, Linux, and Windows: list_apps, get_app_state, click, perform_secondary_action, scroll, drag, type_text, press_key, and set_value.

macOS additionally exposes query: a targeted accessibility lookup that finds controls by text and/or role without rendering a tree or taking a screenshot.

Core Workflow

On macOS, run sw_vers -productVersion before invoking the CLI and require macOS 14.0 or later. On older versions, explain that the runtime cannot launch; do not recommend doctor or permission changes as a fix for binary incompatibility.
Check the CLI is installed with open-computer-use -h or ocu -h. If installation or setup is missing, read references/installation.md.
On supported macOS versions, run open-computer-use doctor before the first real GUI task. If permissions are missing, ask the user to approve Accessibility and Screen Recording in the onboarding UI.
Inspect available apps before acting: open-computer-use call list_apps.
Capture current UI state with open-computer-use call get_app_state --args '{"app":"TextEdit"}'. The default state is usually enough for UI operation.
When the task needs longer semantic text, such as chat history, email bodies, document text, or long form content, call get_app_state with text_limit: 1000 or text_limit: "max".
When visible long pages or lists appear incomplete even after scrolling, call get_app_state with a larger max_tree_nodes or max_tree_depth.
Prefer element-targeted actions using element_index from the latest get_app_state result.
For multi-step CLI work, use open-computer-use call --calls '<json-array>' so one process can reuse the latest element index mapping.
For agent runtimes that support local MCP servers, configure open-computer-use mcp or ocu mcp and call the exposed Computer Use tools directly. Read references/usage.md.
For direct code-first orchestration, run ocu capabilities and then use one-shot ocu js or persistent ocu repl. Read references/usage.md.
If communication, permission, or desktop-session access fails, read references/troubleshooting.md.

Operating Rules

Treat the target desktop as the user's real session. Do not inspect password managers, unrelated private content, or sensitive apps unless the user explicitly asked for that task.
Ask before sending, deleting, purchasing, approving, uploading, or making other externally visible changes.
Do not assume Codex.app plugin helpers are available. Use the installed open-computer-use / ocu CLI or an explicit MCP config.
Always run get_app_state before using element_index; do not guess indexes across sessions or after large UI changes.
Prefer semantic actions and set_value for editable controls. Use coordinate click, scroll, and drag only when the element tree does not expose a safer target.
On macOS, do not enable OPEN_COMPUTER_USE_ALLOW_GLOBAL_POINTER_FALLBACKS=1 unless the user explicitly requested click_method: "global", a drag that must drive a window-server drag session (window move, drag-select text, Finder drag-and-drop), or other diagnostic behavior that may move the real pointer. Without it drag reports Drag delivered via app_post and those operations have no effect; see references/usage.md for alternatives.
On Windows and Linux, confirm the command is running inside the logged-in desktop session before assuming GUI automation is available.

Track record

Benchmark

22 / 22

test cases passed, vs 10 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v6 — 10/16/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

ifuryst / open-codex-computer-use

skills/open-computer-use/SKILL.md

View on GitHub ↗

License MITImported 10/16/2026Version v4Bundled 3 files

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Open Computer Use

Overview

Core Workflow

Operating Rules

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills