gui-automation
Skill1 starsChanged 9 months agoMITView on GitHub
Use when Codex is asked to automate local GUI workflows with SakuraProj using skpr-local/skpr-cli scripts, including probe-driven readiness and repeatable local task orchestration.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- trycua/cuatheir own version, first seen Oct 8, 2026
- marmutapp/superbased-claude-code-plugintheir own version, first seen Apr 12, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- trycua/cua★ 32ksame name
- marmutapp/superbased-claude-code-plugin★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- axum-single-page-uiSkill
- feishuSkill
- frontend-designSkill
- git-opsSkill
- macos-gui-automationSkill
- mermaidSkill
- npmSkill
- playrightSkill
- playwright-cliSkill
- pythonSkill
- python-uvSkill
- rust-coding-styleSkill
- youtrackSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Keep business logic in skpr-cli and runtime hosting in skprd.
- Very specific: line 16
Prefer skpr-local for local task orchestration.
- Very specific: line 17
Keep skpr-local thin: bootstrap daemon, readiness probe, delegate to skpr-cli.
- Distinctive: line 18
Do not re-implement client or daemon semantics inside automation wrappers.
- Distinctive: line 22
Use these patterns first, then adapt args:
- Distinctive: line 47
Keep wrapper logic minimal and reversible.
- Distinctive: line 48
Prefer deterministic commands and explicit endpoints for scripted runs.
- Distinctive: line 50
If a workflow needs heavy branching or state machines, move logic to dedicated scripts rather than inflating wrapper behavior.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
GUI Automation (SakuraProj)
Overview
Automate local GUI workflows by treating skpr-local as the default entrypoint.
Keep business logic in skpr-cli and runtime hosting in skprd; use this skill to
compose reliable local automation commands and scripts.
Default Architecture
- Prefer
skpr-localfor local task orchestration. - Keep
skpr-localthin: bootstrap daemon, readiness probe, delegate toskpr-cli. - Do not re-implement client or daemon semantics inside automation wrappers.
Command Patterns
Use these patterns first, then adapt args:
# Run a local interactive session
skpr-local -- display 0
# Run a local headless probe (CI-friendly smoke check)
skpr-local -- --backend headless probe
# Override daemon backend while preserving CLI pass-through
skpr-local --skprd-arg=--backend --skprd-arg=mock -- --backend headless probe
# Connect to a custom local endpoint
skpr-local --endpoint quic://127.0.0.1:48220 -- --backend headless probeWorkflow
- Pick task intent: interactive viewing, attach/open, or headless probe.
- Encode daemon-only options via
--skprd-arg. - Pass client behavior after
--unchanged toskpr-cli. - For automation, prefer
probechecks before longer GUI actions.
Guardrails
- Keep wrapper logic minimal and reversible.
- Prefer deterministic commands and explicit endpoints for scripted runs.
- For flaky startup environments, increase wrapper startup timeout/poll values.
- If a workflow needs heavy branching or state machines, move logic to dedicated scripts rather than inflating wrapper behavior.
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.