steer
Skill2 starsChanged 8 months agoMITView on GitHub
macOS GUI automation CLI. Use steer to see the screen, click elements, type text, send hotkeys, scroll, drag, manage windows and apps, run OCR on Electron apps, and wait for UI conditions.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- disler/mac-mini-agentword for word, first seen Oct 8, 2026
- BankrBot/openclaw-skillstheir own version, first seen Oct 8, 2026
- BankrBot/skillstheir own version, first seen Apr 28, 2026
Other versions3 projects use a version of this.
Word for word · 1
- disler/mac-mini-agent★ 272100% same
Edited · 0
None found.
Wrote their own version · 2
- BankrBot/openclaw-skills★ 1.2ksame name
- BankrBot/skills★ 1.2ksame 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 repository239 other files it gives its agents.
- claude-code-docs/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- claude-code-docs/llms.txtllms.txt
- agent-native-architectureSkill
- claude-apiSkill
- embedding-strategiesSkill
- fal-ai-mediaSkill
- gemini-imagegenSkill
- hybrid-search-implementationSkill
- langchain-architectureSkill
- llm-evaluationSkill
- ml-pipeline-workflowSkill
- prompt-engineering-patternsSkill
- rag-implementationSkill
- similarity-search-patternsSkill
- vector-index-tuningSkill
- api-design-principlesSkill
- api-designSkill
- architecture-patternsSkill
- cqrs-implementationSkill
- event-store-designSkill
- fastapi-templatesSkill
- microservices-patternsSkill
- openapi-spec-generationSkill
- projection-patternsSkill
- saga-orchestrationSkill
- api-conventionsSkill
- andrew-kane-gem-writerSkill
- angular-migrationSkill
- auth-implementation-patternsSkill
- backend-patternsSkill
- bazel-build-optimizationSkill
- coding-standardsSkill
- database-migrationSkill
- debugging-strategiesSkill
- dependency-upgradeSkill
- dhh-rails-styleSkill
- dotnet-backend-patternsSkill
- dspy-rubySkill
- error-handling-patternsSkill
- monorepo-managementSkill
- nodejs-backend-patternsSkill
- nx-workspace-patternsSkill
- react-modernizationSkill
- temporal-python-testingSkill
- turborepo-cachingSkill
- workflow-orchestration-patternsSkill
- defi-protocol-templatesSkill
- nft-standardsSkill
- solidity-securitySkill
- web3-testingSkill
- backtesting-frameworksSkill
- billing-automationSkill
- competitive-landscapeSkill
- data-storytellingSkill
- employment-contract-templatesSkill
- investor-materialsSkill
- investor-outreachSkill
- kpi-dashboard-designSkill
- market-sizing-analysisSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
18 rules. About 0 are common, 6 are distinctive, and 12 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
12
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Run steer --help and steer help <command> to learn each command's flags before using it.
- Very specific: line 31
Always pass --json for structured output.
- Distinctive: line 39
Before doing anything, understand the display setup, what's running, and capture the current state of every screen:
- Distinctive: line 52
Before interacting with any app, make sure it's the active window on the right screen:
- Distinctive: line 66
Read the JSON — understand what you see
- Distinctive: line 67
Do ONE action (click, type, hotkey, scroll)
- Very specific: line 75
Run steer see --app <app> --json to get a fresh snapshot
- Distinctive: line 76
Use element IDs from the snapshot (B1, T1, L3) — not coordinates when possible
- Distinctive: line 77
If using coordinates, they are relative to the screenshot image, factor in window position
- Very specific: line 78
After clicking, run steer see again to confirm the click landed
- Very specific: line 82
Before typing anything: ALWAYS check focus with steer focus --json to confirm the right element is targeted.
- Very specific: line 83
If you're not focused on the right element, use steer apps activate <AppName> --json to switch apps or steer click to focus the correct …
- Very specific: line 85
Use steer type "text" --into T1 --json to click-then-type in one step when targeting a specific field
- Very specific: line 86
If typing into the already-focused element, just steer type "text" --json
- Very specific: line 87
After typing, verify with steer see that the text appeared correctly
- Very specific: line 108
Don't assume the UI is ready after an action.
- Very specific: line 117
If there are multiple screens, coordinates and screenshots are per-screen.
- Very specific: line 133
Run
steer help <cmd>: if you're unsure about a command's flags
≈ “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
Steer — macOS GUI Automation
Binary: apps/steer/.build/release/steer
Run steer --help and steer help <command> to learn each command's flags before using it.
Commands
| Command | Purpose |
see | Takes a screenshot (PNG) and walks the accessibility tree. Screenshot always succeeds. Elements are best-effort — may be empty for Electron apps. Pass --ocr to fall back to OCR when the tree is empty. |
click | Click by element ID, label, or coordinates |
type | Type text into focused element or a target |
hotkey | Keyboard shortcuts (cmd+s, return, escape, etc.) |
scroll | Scroll up/down/left/right |
drag | Drag between elements or coordinates |
apps | List, launch, or activate apps |
screens | List displays with resolution and scale |
window | Move, resize, minimize, fullscreen, close windows |
ocr | Takes a screenshot and runs Vision OCR on it. Returns text with x/y positions. Use --store to make results clickable (O1, O2, etc.). Use when see returns no elements. |
focus | Show currently focused element |
find | Search elements by text in latest snapshot |
clipboard | Read/write system clipboard |
wait | Wait for app launch or element to appear |
Always pass --json for structured output.
How to Work
You are controlling a real macOS desktop. You cannot see anything unless you explicitly look. You cannot assume anything worked unless you verify.
1. Know your environment first
Before doing anything, understand the display setup, what's running, and capture the current state of every screen:
steer screens --json → which monitors exist, their resolution
steer apps --json → what apps are running
steer see --screen 0 --json → screenshot of screen 0 (primary)
steer see --screen 1 --json → screenshot of screen 1 (if exists)Take a screenshot of each screen returned by steer screens. Read them. This gives you a baseline of the desktop before you start making changes.
2. Focus the app, then verify
Before interacting with any app, make sure it's the active window on the right screen:
steer apps activate Safari --json
steer see --app Safari --json → verify it's in front, read the state3. One action, then observe
NEVER chain multiple steer commands in one bash call. The screen changes after every action. You must look after every action.
The loop is:
steer see— look at the screen- Read the JSON — understand what you see
- Do ONE action (click, type, hotkey, scroll)
steer see— look again to confirm it worked- Repeat
4. Clicking safely
Before clicking anything:
- Run
steer see --app <app> --jsonto get a fresh snapshot - Use element IDs from the snapshot (B1, T1, L3) — not coordinates when possible
- If using coordinates, they are relative to the screenshot image, factor in window position
- After clicking, run
steer seeagain to confirm the click landed
5. Typing into fields
- Before typing anything: ALWAYS check focus with
steer focus --jsonto confirm the right element is targeted.- If you're not focused on the right element, use
steer apps activate <AppName> --jsonto switch apps orsteer clickto focus the correct field. - Then validate your focus with
steer focus --json
- If you're not focused on the right element, use
- Use
steer type "text" --into T1 --jsonto click-then-type in one step when targeting a specific field - If typing into the already-focused element, just
steer type "text" --json - After typing, verify with
steer seethat the text appeared correctly - For URLs in browsers: type the URL, then
steer hotkey return --json, thensteer seeto confirm navigation
6. Reading content from apps
Both see and ocr save a screenshot PNG. The path is in the JSON output under "screenshot". You can read this image file to visually inspect what's on screen.
Native apps (Safari, Finder, Terminal): steer see --app <name> --json gives you the accessibility tree with labeled elements. If the element list is empty, the screenshot still exists — read it or try --ocr to fall back.
Electron apps (VS Code, Slack, Notion): Accessibility trees are empty. Use OCR instead:
steer ocr --app "VS Code" --store --jsonWith --store, OCR results become clickable elements (O1, O2, etc.).
Web pages: Accessibility tree may be shallow. Use steer ocr --app Safari --json to read all visible text with positions. Use the positions to click precisely.
7. Waiting for things
Don't assume the UI is ready after an action. Use steer wait or run steer see in a loop:
steer wait --app Safari --json → wait for app to launch
steer wait --for "Submit" --app Safari --json → wait for element to appear8. Multi-monitor awareness
If there are multiple screens, coordinates and screenshots are per-screen. Always check steer screens --json first and use --screen <index> when needed.
Element IDs
Elements from steer see get role-based IDs: B (button), T (text field), S (static text), I (image), C (checkbox), L (link), M (menu item), O (OCR element), etc.
IDs regenerate with each snapshot. Always use IDs from the most recent steer see or steer ocr --store.
Rules
- One command per bash call — never chain steer commands
- Always verify —
steer seeafter every action - Focus first — activate the app before interacting
- Know your screens — check
steer screensbefore clicking - Use
--jsonalways — structured output is reliable - Write all files to /tmp — never write output files into the project directory
- Run
steer help <cmd>if you're unsure about a command's flags
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.

