Record your screen to video from Claude Code. Guided capture setup: pick a display, window, or screen region, then start/stop recording on demand. Uses ffmpeg — cross-platform (macOS, Linux, Windows). Produces MP4 with sensible defaults. Pairs with demo-narrate for voice-over. Triggers on: screencast, record screen, screen recording, capture screen, record window, record region, start recording, screen capture video.
100
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that excels across all dimensions. It provides specific capabilities (guided capture, display/window/region selection, MP4 output), uses third-person voice correctly, includes comprehensive natural trigger terms, and clearly distinguishes itself from related skills like demo-narrate.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'pick a display, window, or screen region', 'start/stop recording on demand', 'Produces MP4 with sensible defaults', and mentions cross-platform support and ffmpeg usage. | 3 / 3 |
Completeness | Clearly answers 'what' (screen recording with guided capture setup, display/window/region selection, MP4 output) and 'when' with explicit 'Triggers on:' clause listing specific trigger terms. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms explicitly listed: 'screencast, record screen, screen recording, capture screen, record window, record region, start recording, screen capture video' - these are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche focused specifically on screen recording to video. The explicit trigger terms and mention of ffmpeg/MP4 output clearly distinguish it from other media or capture skills. Also notes pairing with demo-narrate for voice-over, showing awareness of related but distinct skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that demonstrates best practices across all dimensions. It provides concrete, executable commands with clear workflow steps, handles edge cases explicitly, and maintains token efficiency throughout. The progressive structure from setup through recording to stopping is logical and includes appropriate validation checkpoints.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, providing only necessary information without explaining concepts Claude already knows. Every section serves a clear purpose with no padding or unnecessary context. | 3 / 3 |
Actionability | Provides fully executable bash commands with specific flags, clear JSON output expectations, and copy-paste ready examples. The script location logic and all command variations are concrete and complete. | 3 / 3 |
Workflow Clarity | Clear 4-step workflow with explicit sequencing, validation checkpoints (deps check, status check), and edge case handling including feedback loops for already-running recordings and dead processes. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from prerequisites to commands to workflow. Appropriately references external REFERENCE.md for advanced details while keeping the main skill self-contained. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents