Agent skill

Aohp Perception

Screenshots and UI hierarchy (windows/nodes) on a logical display via the aohp CLI.

Apache-2.0Auto-check passed

Install Aohp Perception

skills CLI

$ npx skills add aohp-os/aohp --skill aohp-perception -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install aohp-os/aohp aohp-perception --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/aohp-os/aohp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/aohp-perception .claude/skills/aohp-perception && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "aohp-perception" agent skill from https://github.com/aohp-os/aohp/tree/main/skills/aohp-perception into .claude/skills/aohp-perception/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aohp-perception", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/aohp-os/aohp/tree/main/skills/aohp-perception

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add aohp-os/aohp --skill aohp-perception -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install aohp-os/aohp aohp-perception --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aohp-os/aohp.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/aohp-perception .agents/skills/aohp-perception && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "aohp-perception" agent skill from https://github.com/aohp-os/aohp/tree/main/skills/aohp-perception into .agents/skills/aohp-perception/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aohp-perception", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add aohp-os/aohp --skill aohp-perception -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install aohp-os/aohp aohp-perception --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aohp-os/aohp.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/aohp-perception .cursor/skills/aohp-perception && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "aohp-perception" agent skill from https://github.com/aohp-os/aohp/tree/main/skills/aohp-perception into .cursor/skills/aohp-perception/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aohp-perception", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/aohp-os/aohp.git --path skills/aohp-perception

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add aohp-os/aohp --skill aohp-perception -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install aohp-os/aohp aohp-perception --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aohp-os/aohp.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/aohp-perception .gemini/skills/aohp-perception && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "aohp-perception" agent skill from https://github.com/aohp-os/aohp/tree/main/skills/aohp-perception into .gemini/skills/aohp-perception/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aohp-perception", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install aohp-os/aohp aohp-perception

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add aohp-os/aohp --skill aohp-perception -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/aohp-os/aohp.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/aohp-perception .github/skills/aohp-perception && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "aohp-perception" agent skill from https://github.com/aohp-os/aohp/tree/main/skills/aohp-perception into .github/skills/aohp-perception/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aohp-perception", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add aohp-os/aohp --skill aohp-perception -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install aohp-os/aohp aohp-perception --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aohp-os/aohp.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/aohp-perception .opencode/skills/aohp-perception && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "aohp-perception" agent skill from https://github.com/aohp-os/aohp/tree/main/skills/aohp-perception into .opencode/skills/aohp-perception/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aohp-perception", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: aohp-perception
GitHub stars: 155
Token cost: ~1.1k tokens
SKILL.md length: 514 words
Files: 1
Skills in repo: 11
Repo updated: Jul 23, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Screenshots and UI hierarchy (windows/nodes) on a logical display via the aohp CLI.

SKILL.md covers When to use, Workflow, Commands (summary) and Output shape for aohp shot ……, plus 1 more section
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Aohp Perception is an agent skill from aohp-os/aohp. Screenshots and UI hierarchy (windows/nodes) on a logical display via the aohp CLI.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: An OS-level agent harness for personalized, efficient and secure interaction. The licence is Apache-2.0.

Example prompts

“Use the aohp-perception skill to screenshot and UI hierarchy (windows/nodes) on a logical display via the aohp CLI”
“/aohp-perception”

What it can do on your machine

Read from SKILL.md and the folder at commit b8ab9e9. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Aohp Perception loads about 1.1k tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 514 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~25
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from aohp-os/aohp at commit b8ab9e9, republished under its Apache-2.0 licence (© aohp-os). 514 words, ~1,068 tokens.

Download SKILL.mdSave it as .claude/skills/aohp-perception/SKILL.md (or your agent's skills folder).

name: aohp-perception
description: Screenshots and UI hierarchy (windows/nodes) on a logical display via the aohp CLI.

AOHP perception

Capture JPEG screenshots and read UI hierarchy on a logical display (displayId: integer). The default hierarchy is compact HTML-like text with useful node attributes (id, bounds, text/desc/resourceId, action states); use -o only when you need the origin JSON.

Requires aohp on PATH (how it reaches the device is already set in the packaged aohp you run).

When to use

Screenshot the whole display, a rectangle, or a single node’s bounds: aohp shot full, aohp shot region, aohp shot node.
Read or filter the UI tree: aohp ui tree, aohp ui find.
Prefer the subcommands above. Use aohp call <method> '<json>' only if you need JSON fields the high-level commands do not expose; method names look like <area>.<action> (e.g. ui.tree, shot.full).

Workflow

UI hierarchy: run aohp ui tree -d <displayId> whenever you need node id, bounds, text, description, resource id, or action states. Default output is compact HTML; add -o / --origin only when you need the full origin JSON. aohp ui find matches nodes by text / description / resource-id when that is enough.
Screenshots: run aohp shot … whenever you need pixels. By default each shot writes a JPEG under $TMPDIR and prints a short JSON wrapper (see below)—use that path for vision tools.
Quote arguments that contain spaces or shell metacharacters when the command runs inside exec.

Commands (summary)

Goal	CLI
Full-screen JPEG	`aohp shot full -d <id> [-q 1-100]` — default save under `$TMPDIR` as `aohp_shot_full_<timestamp>.jpg`; `-O` sets the local path; `--inline` alone does not write or retain a local JPEG—pixels appear in stdout as a single `type: "image"` block; `-O` + `--inline` writes the file and adds `type: "image"` after the save-path text
Cropped JPEG	`aohp shot region …` — same modes (default prefix `aohp_shot_region_`)
Node bounds JPEG	`aohp shot node …` — same modes (default prefix `aohp_shot_node_`)
UI tree	`aohp ui tree -d <id> [-f flags]` — compact HTML; `-o` / `--origin` returns the full origin JSON
Filter nodes	`aohp ui find -d <id> [--raw] [-s text] [-D desc] [-R resource-id]`
Stubs	`aohp ui focused`, `aohp ui input-text` (may be placeholders on some agents)

Alias: aohp ui-tree → aohp ui tree.

Show full SKILL.md (169 more words)Show less

Output shape for `aohp shot …` (success)

Stdout is one JSON object with content (array) and details (object). When a local file is written, the first content item is type: "text" (includes Saved image bytes to … plus a short completion line). With --inline and no -O, content contains only the type: "image" block.

Invocation	Local JPEG file	`type: "image"` in `content`
Default or `-O` only	Yes (default under `$TMPDIR` or your `-O` path)	No — keeps `exec` output small
`--inline` only	No	Yes — the only content block; raw base64 in `data`, `mimeType` set
`-O` and `--inline` together	Yes, at your `-O` path	Yes — second block after save-path text

details: fields from the agent reply except the duplicated huge base64 string; details.path (when present) is the device-side capture path, not necessarily the path where you saved bytes locally—the local path is only in the text line above.

aohp call … for shot-related methods returns the plain agent JSON (not this wrapper), which is useful for automation but different from aohp shot … stdout.

Examples

bash

aohp ui tree -d 0
aohp ui tree -d 0 -o
aohp shot full -d 0 -q 85
aohp shot full -d 0 -O /tmp/cap.jpg
aohp shot full -d 0 --inline
aohp shot full -d 0 -O /tmp/cap.jpg --inline

Files

Just SKILL.md in skills/aohp-perception of aohp-os/aohp.

Open the folder on GitHubat commit b8ab9e9

Compare with similar skills

Aohp Perception next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Aohp Perception compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Aohp Perception this skillaohp-os/aohp	155	—	~1.1k	Automated safety check: Pass	Apache-2.0	2 mo ago
Screenshotnexu-io/open-design	100k	—	~291	Automated safety check: Pass	Apache-2.0	today
Node Connectopenclaw/openclaw	392k	—	~1.6k	Automated safety check: Pass	MIT	today
Node Inspect Debuggeropenclaw/openclaw	392k	1 repos	~894	Automated safety check: Pass	MIT	today
Heading Hierarchythedaviddias/Front-End-Checklist	74k	—	~516	Automated safety check: Pass	MIT	3 days ago
Windows Desktop E2Eaffaan-m/ECC	276k	1 repos	~7.6k	Automated safety check: Pass	MIT	4 days ago

Similar skills

Screenshot
nexu-io/open-design
Capture desktop, app windows, or pixel regions across OS platforms.
100k GitHub stars~291 tokensUpdated today
Testing & QAAuto-check passed
Node Connect
openclaw/openclaw
Diagnose OpenClaw Control UI browser and native Android, iOS, or macOS node connection failures across route, auth, pairing, QR/setup-code, and reconnect states.
392k GitHub stars~1.6k tokensUpdated today
MobileAuto-check passed
Node Inspect Debugger
openclaw/openclaw
Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.
392k GitHub starsUsed in 1 repo~894 tokens
Frontend & DesignAuto-check passed
Heading Hierarchy
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Use logical heading hierarchy.
74k GitHub stars~516 tokensUpdated 3 days ago
Frontend & DesignAuto-check passed
Windows Desktop E2E
affaan-m/ECC
E2E testing for Windows native desktop apps (WPF, WinForms, Win32/MFC, Qt) using pywinauto and Windows UI Automation.
276k GitHub starsUsed in 1 repo~7.6k tokens
Testing & QAAuto-check passed
Windows Desktop E2E
affaan-m/ECC
E2E testing for Windows native desktop apps (WPF, WinForms, Win32/MFC, Qt) using pywinauto and Windows UI Automation.
276k GitHub stars~5.5k tokensUpdated 4 days ago
Testing & QAAuto-check passed

Questions about Aohp Perception

What does Aohp Perception do?

Screenshots and UI hierarchy (windows/nodes) on a logical display via the aohp CLI. Aohp Perception is an agent skill from aohp-os/aohp. Screenshots and UI hierarchy (windows/nodes) on a logical display via the aohp CLI.

How do I install Aohp Perception in Claude Code?

Run `npx skills add aohp-os/aohp --skill aohp-perception -a claude-code`. Or copy the skill folder (skills/aohp-perception in aohp-os/aohp) into .claude/skills/aohp-perception in your project. Claude Code loads it when a task matches its description.

How do I install Aohp Perception in Codex?

Run `npx skills add aohp-os/aohp --skill aohp-perception -a codex`. Or copy the skill folder (skills/aohp-perception in aohp-os/aohp) into .agents/skills/aohp-perception in your project. Codex loads it when a task matches its description.

Can I use Aohp Perception in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aohp-os/aohp --skill aohp-perception -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/aohp-perception, .gemini/skills/aohp-perception, .github/skills/aohp-perception and .opencode/skills/aohp-perception in your project.

What does Aohp Perception need to run?

SKILL.md names no scripts, command-line tools or credentials: Aohp Perception is instructions for the agent only.

Does Aohp Perception access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Aohp Perception safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Aohp Perception use?

Aohp Perception is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Aohp Perception use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Aohp Perception?

Skills that share tags, products or a category with Aohp Perception: Screenshot (nexu-io/open-design, 100k stars), Node Connect (openclaw/openclaw, 392k stars), Node Inspect Debugger (openclaw/openclaw, 392k stars) and Heading Hierarchy (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Aohp Perception?

aohp-os (a GitHub organization) maintains it in aohp-os/aohp, which has 155 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on July 23, 2026.

Source: aohp-os/aohp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Aohp Perception

Install Aohp Perception

Facts

At a glance

What it does

Example prompts

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

AOHP perception

When to use

Workflow

Commands (summary)

Output shape for `aohp shot …` (success)

Examples

Files

Compare with similar skills

Similar skills

Screenshot

Node Connect

Node Inspect Debugger

Heading Hierarchy

Windows Desktop E2E

Windows Desktop E2E

More from aohp-os/aohp

Aohp App Launch

Aohp Event Stream

Aohp File

Aohp Sandbox

Aohp Sys

Aohp Uda

Questions about Aohp Perception

Install Aohp Perception

Facts

At a glance

What it does

Example prompts

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

AOHP perception

When to use

Workflow

Commands (summary)

Output shape for aohp shot … (success)

Examples

Files

Compare with similar skills

Similar skills

More from aohp-os/aohp

Questions about Aohp Perception

Output shape for `aohp shot …` (success)