computer-use is agent-read markdown (skill) from badmuriss/my-llm-kit: Inspect and operate local browser or desktop interfaces. Prefer Jev Ultrafast for supported browser-only goals when its required credentials are available; use Orca for desktop apps, unsupported browser interactions, screenshots, and accessibility-level control..
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
# Computer Use
Route each task to Jev Ultrafast or Orca. Jev is the preferred browser backend when it is
ready and the task fits its supported action space. Orca remains the general desktop and
browser accessibility backend; its full, version-matched guide is served by the `orca`
binary so it cannot drift from the commands that will run.
## Prefer Jev for supported browser goals
Reuse a working local Jev installation when available. For the portable kit path,
resolve this installed skill directory and run its bundled runner with `uv` (Python
3.12+). It installs the pinned upstream dependency in uv's cache, outside the consumer
project. No patched checkout or globally installed `jev-agent` is required:
```text
uv run <skill-dir>/scripts/jev_browser.py --check
uv run <skill-dir>/scripts/jev_browser.py --url 'https://example.com' --goal 'A narrow, authorized, verifiable browser outcome' --evidence-dir .visual-evidence/jev-task
```
`--check` is read-only and checks credentials plus the active Browser Harness connection;
it does not prove API access. `--probe` makes one small paid decision request without
…
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.
GET https://markdownregistry.com/api/v1/artifacts/art_6opbvn27xxgbgz3e
GET https://markdownregistry.com/api/v1/resolve?ref=badmuriss/my-llm-kit/computer-use
GET https://markdownregistry.com/api/v1/blob/368aff53e5210d5e17d8cd234a914f40ef7c2a4d84048a45f54cf84db89457d8
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.
badmuriss/my-llm-kit · skills/agent-graph/SKILL.md · Run durable task graphs when independent work needs ownership, integration checks and recovery. Use for graph…
badmuriss/my-llm-kit · skills/frontend-visual-validation/SKILL.md · Verify rendered UI changes with reproducible screenshots and vision review on their supported platforms.
badmuriss/my-llm-kit · skills/grill-me/SKILL.md · Adversarial interview about a plan until you reach shared understanding. use_when: "grill me", stress-test a plan or…
badmuriss/my-llm-kit · skills/grill-with-docs/SKILL.md · Grill a plan against the documented domain model, updating CONTEXT.md and ADRs inline. use_when: stress-test a plan…
badmuriss/my-llm-kit · skills/impl/SKILL.md · Implement a requested change or approved plan, verify its outcomes, and report concrete blockers. Use graph execution…
badmuriss/my-llm-kit · skills/ingest/SKILL.md · Extract content from documents when their format or layout prevents reliable direct reading. Verify reading order and…
badmuriss/my-llm-kit · skills/readme-pass/SKILL.md · Make a public repository README easier to understand and use. Apply when README structure or presentation is requested.
badmuriss/my-llm-kit · skills/remove-ai-marks/SKILL.md · Inspect and remove requested metadata or invisible marks from user-owned files. Use when provenance cleanup is…
badmuriss/my-llm-kit · skills/research/SKILL.md · Research external questions and compare evidence with source attribution. Use for research or fact-checking, not facts…
badmuriss/my-llm-kit · skills/rule-curator/SKILL.md · Audit an existing corpus of agent instructions for conflicts, duplication and unnecessary process. Use for a…
qwenlm/qwen-code · packages/core/src/skills/bundled/computer-use/SKILL.md · Control local desktop applications through Computer Use for tasks that require reading or operating app UI. Prefer…
thinkinaixyz/deepchat · plugins/cua/skills/computer-use/SKILL.md · Drive native desktop apps through DeepChat's built-in Computer Use tools. Use when the user asks to operate, inspect…
clacky-ai/openclacky · lib/clacky/default_extensions/computer-use/skills/computer-use/SKILL.md · Drive the macOS desktop when a task needs a native app, dialog, menu bar, file picker or anything the terminal and…
xuzhougeng/wisp-science · skills/computer-use/SKILL.md · Use Cua Driver through MCP to inspect and operate the user's native desktop apps on Windows, macOS, or Linux. Trigger…
autonomous-ai/autonomous-os · skills/computer-use/SKILL.md · Operate apps/websites on the paired Mac via Buddy: Calendar, Notes, forms, screenshots, files. Never use the headless…
razshy/wiggle · mnt-skills/examples/computer-use/SKILL.md · Read this skill before the first step of any request to do something in an app on the person's own computer (Notes…
vm0-ai/vm0-skills · computer-use/SKILL.md · Operate apps on a desktop host through Computer Use, whether surfaced as Okou Desktop or the still-supported legacy…
