apsethicsbowl20026-collabapsethicsbowl20026-collab/open-computer-skills/skills/desktop-text/SKILL.mddesktop-text
Skill2 starsChanged 31 days agoMITView on GitHub
For text-only models or low-vision budgets. No pixels needed.
In this repository6 other files it gives its agents.
- SKILL.mdSkill
- click-groundSkill
- form-fillSkill
- safe-bashSkill
- see-verifySkill
- stop-guardSkill
The file
Files
desktop-text
For text-only models or low-vision budgets. No pixels needed.
Loop
desktop_snapshot→ get windows + elements liket_12.desktop_act(element="t_12", operation="click").- Operations:
click,double_click,right_click,type_into(+text),press_key(+text),scroll(+direction). - Re-snapshot after every 2 acts.
When to prefer over screenshot mode
- Model has no vision, or screenshots cost too many tokens.
- Dense desktop with many small controls (text ids are more precise).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.