Menú
QA inspection tools for visual testing -- video frame extraction, screenshot analysis
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Backlog-scale orchestration on top of /workflow — drives PM items through refine → plan → implement → review → local-merge via role-specialized sub-agents dispatched in parallel waves, each item isolated in its own git worktree. Bare /swarm summarizes state; /swarm <goal> runs the orchestrator; /swarm:setup sets up the charter and .agent-tools/ umbrella; /swarm:continue resumes a paused run.
Capture durable knowledge from any engineering work — debugging solutions, refactors, features, design decisions, reusable patterns — and maintain memory quality so each unit of work compounds the next
Principal workflow entry — resolve portfolio mode (swarm resume/handoff or unit state machine), drive work without inventing path; hard-stop when path is not established
Initialize and maintain planning root (.agent-tools/planning preferred), conventions (tracks, gates, integration), runs ledger scaffold, and shared memory under .agent-tools/memory/ (AGENTS.md memory-link) for the workflow family.
Parent skill for the workflow family — principal session entry is /workflow:continue (also bare /workflow). Horizon mapping, brainstorm, refine, plan, execute, review, audit, compound. Vertical-slice and deliverable-partition modes.
Detect gaps in the canonical skill corpus, propose targeted improvements, validate changes, and present for review. Inventories src/** skill trees; optional run-ledger seeds for process IP gaps.
| name | qa:tools |
| user-invocable | true |
| description | QA inspection tools for visual testing -- video frame extraction, screenshot analysis |
Tools for inspecting visual artifacts during QA workflows. Use this skill when you need to analyze screen recordings, identify UI regressions, or document visual behavior from test runs.
The video_frames.py tool extracts frames from a video file at regular intervals, saving them as images that can be inspected with the Read tool.
Run from this skill's own directory (shown as "Base directory for this skill" when the skill loads):
cd <base directory of this skill> && uv sync && uv run video_frames.py <video_path>
| Flag | Default | Description |
|---|---|---|
--output-dir | /tmp/qa-frames/ | Directory for extracted frames |
--interval | 2 | Seconds between frames |
--format | png | Output format: png, jpg, or webp |
Extract frames every 2 seconds (default):
cd <base directory of this skill> && uv sync && uv run video_frames.py /tmp/recording.webm
Extract frames every half-second for detailed inspection:
cd <base directory of this skill> && uv sync && uv run video_frames.py /tmp/recording.webm --interval 0.5
Save as JPEG to a specific directory:
cd <base directory of this skill> && uv sync && uv run video_frames.py /tmp/recording.webm --output-dir /tmp/bug-123/ --format jpg
After extraction, use the Read tool to view individual frames. The Read tool supports image files natively:
Read /tmp/qa-frames/frame_0000s.png
Read /tmp/qa-frames/frame_0004s.png
frame_0002s.png = 2 seconds in), making it easy to correlate with video playback--output-dir to keep frames organized per investigationpng for lossless quality when inspecting UI details; use jpg for smaller files when reviewing many frames