Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub Β· AI
UI Element Ops
Parse UI screenshots into structured element JSON (type, OCR text, bbox) and operate desktop UI from parsed elements. Use when a user asks to detect/locate U...
skill openclawclawhub Free
Parse UI screenshots into structured element JSON (type, OCR text, bbox) and operate desktop UI from parsed elements. Use when a user asks to detect/locate U...
β¬ 0 downloads β
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- SKILL.md, scripts/run_parse_ui.sh, scripts/operate_ui.py, scripts/bootstrap_omniparser_env.sh, scripts/parse_ui.py, scripts/capture_and_parse.sh
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.0.2
Provenance
- Publisher
- murongg
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
UI Element Ops
Parse one or more screenshots into a machine-readable JSON schema with: type (normalized UI element type) bbox_px and bbox_norm text (OCR/caption content when available) clickable flag optional overlay image with labeled boxes desktop actions via scripts/operate_ui.py (click/type/key/hotkey/screenshot) element query and orchestration via scripts/operate_ui.py (find, wait) coordinate calibration profile for multi-display/DPI/window offset (calibrate)
Quick Start
Prepare runtime once per machine: skills/ui-element-ops/scripts/bootstrap_omniparser_env.sh "$PWD" Parse one screenshot: skills/ui-element-ops/scripts/run_parse_ui.sh /abs/path/to/1.jpeg Read outputs: <image>.elements.json <image>.overlay.png One-step capture + parse with randomized names: skills/ui-element-ops/scripts/capture_and_parse.sh
Workflow
Confirm screenshot path and desired output path. Run scripts/bootstrap_omniparser_env.sh when .venv or OmniParser weights are missing. Run scripts/run_parse_ui.sh for standard parsing. Report absolute output paths and summary counts: total, clickable, by_type. Call out obvious quality risks for tiny text or dense icon layouts. Execute desktop actions when requested: list elements: python3 skills/ui-element-ops/scripts/operate_ui.py list --elements <json> find elements: python3 skills/ui-element-ops/scripts/operate_ui.py find --elements <json> --type button --text-contains login wait for appear/disappear: python3 skills/ui-element-ops/scripts/operate_ui.py wait --elements <json> --state appear --text-contains continue click by id: python3 skills/ui-element-ops/scripts/operate_ui.py click --elements <json> --id e_0001 screenshot: python3 skills/ui-element-ops/scripts/operate_ui.py screenshot (defaults to user tmp dir) calibrate coordinates: python3 skills/ui-element-ops/scripts/operate_ui.py calibrate --parsed-size <w> <h> --actual-size <w> <h>
Tunables
Edit type mapping keywords in references/type_rules.example.json. Use advanced parser args via scripts/parse_ui.py --help. Use --use-paddleocr only when paddleocr/paddlepaddle are installed.
Outputs
Main JSON output: schema_version, pipeline, image, counts, elements each element has id, type, bbox_px, bbox_norm, text, clickable Overlay PNG output: same screenshot with labeled detection boxes
Failure Handling
Missing dependencies or weights: run bootstrap script again. Permission/cache errors under $HOME: keep temporary caches under /tmp (handled by run script). CPU-only machine: expect slower inference. Performance note: parse/capture-and-parse commands are heavy; avoid very tight loops and reuse recent elements.json when possible. Headless environment limitation: usable without GUI: parse/list/find/wait/calibrate on existing files. requires GUI session: click/click-xy/type/key/hotkey/screenshot/screen-info.
Category context
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
5 Scripts1 Docs
- SKILL.md
- scripts/bootstrap_omniparser_env.sh
- scripts/capture_and_parse.sh
- scripts/operate_ui.py
- scripts/parse_ui.py
- scripts/run_parse_ui.sh