Real Skill packageSource verifiedClawHub registry

Mediapipe vision

Use Google MediaPipe for on-device computer vision — face, hand, and pose landmark detection, face detection, object detection, and image segmentation on images, videos, or webcam streams. Activate when the user asks to detect faces/hands/poses/objects, extract landmarks or keypoints, do background

Identity and source

Publisher attributionpromiseyukiregistry owner unverified by skillvetai
Functional categoryImage & Visual Designautomatically inferred · 55% rule confidence
Package forminstruction with code8 recorded files
Canonical sourceClawHub registryclawhub:promiseyuki:mediapipe
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/30/2026.claude/skills/mediapipe

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/30/2026.agents/skills/mediapipe

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/30/2026skills/mediapipe

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @promiseyuki/mediapipe
clawhub inspect @promiseyuki/mediapipe --version 1.0.0

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
8 / 8 inspected as text
Checked
8/30/2026, 4:44:55 PM
Scanner
0.1.3
Policy
1.0.3
2 inferred permission indicators
  • network access — automatically inferred
  • filesystem write — automatically inferred
6 dependency and API indicators
  • pypi: mediapipe >=0.10.14
  • pypi: opencv-python >=4.8.0
  • pypi: numpy >=1.24.0
  • api: ai.google.dev
  • api: clawhub.ai
  • api: storage.googleapis.com
External clawhub result: clean

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
8/30/2026, 6:03:39 AM
Release binding
Matches this record
  • vt: clean
  • skillspector: suspicious
  • llm: clean

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:bbf3bb537b3e53e044dd7bc340c1698c98596a16666035816d61ae513766931e
Show up to 8 recorded paths
  • LICENSE
  • README.md
  • references/api_cheatsheet.md
  • references/landmarks.md
  • scripts/requirements.txt
  • scripts/run_mediapipe.py
  • skill-card.md
  • SKILL.md

Source changelog

Initial release: MediaPipe skill for on-device computer vision - Provides a CLI script (`scripts/run_mediapipe.py`) for face, hand, and pose landmark detection, object detection, and image segmentation across images, videos, and webcam streams. - Supports both the legacy solutions API (with bundled models) and the newer MediaPipe Tasks API (requires downloadable model files). - Includes quick-start usage instructions, dependency/environment setup, and bilingual documentation (English & Chinese). - Reference files: model download URLs, API usage patterns (`references/api_cheatsheet.md`), and landmark index tables (`references/landmarks.md`). - Outputs annotated images/videos, per-frame landmark data (JSON/CSV), and segmentation masks.