catalan-adobe/demo-narrate
Use when the user wants to narrate a demo, add voice-over to a screen recording, or create AI narration for a silent video. End-to-end pipeline that extracts frames, analyzes with parallel subagents, writes a word-budgeted voice-over script, generates TTS audio per act, and merges everything back.
94
94%
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 an excellent skill description that clearly articulates both the capability (an end-to-end video narration pipeline) and the trigger conditions (demo narration, voice-over for recordings, AI narration for silent videos). It uses third person voice correctly, includes natural user-facing keywords, and provides enough technical detail about the pipeline steps without being overly verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'extracts frames, analyzes with parallel subagents, writes a word-budgeted voice-over script, generates TTS audio per act, and merges everything back.' This describes a clear end-to-end pipeline with distinct steps. | 3 / 3 |
Completeness | Explicitly answers both what ('End-to-end pipeline that extracts frames, analyzes with parallel subagents, writes a word-budgeted voice-over script, generates TTS audio per act, and merges everything back') and when ('Use when the user wants to narrate a demo, add voice-over to a screen recording, or create AI narration for a silent video'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'narrate a demo', 'voice-over', 'screen recording', 'AI narration', 'silent video'. These are terms users would naturally use when requesting this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on video narration/voice-over with specific triggers like 'demo narration', 'screen recording voice-over', and 'silent video'. Unlikely to conflict with general video editing or audio processing skills due to the specific use case framing. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill for a complex multi-step pipeline. It excels at actionability with executable commands and workflow clarity with explicit validation steps and feedback loops. Minor verbosity in script location fallbacks and some repeated explanations prevent a perfect conciseness score, but overall the skill is production-ready.
Suggestions
Condense the script location fallback logic into a single code block with inline comments rather than separate explanation paragraphs
Remove the explanatory text about what contact sheets are and the 2 words-per-second rationale - Claude can infer these from context
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some redundant explanations (e.g., explaining what contact sheets are, repeating the timing.txt format). The fallback script location logic is verbose and could be condensed. | 2 / 3 |
Actionability | Provides fully executable bash commands throughout, specific file formats, exact word-per-second calculations, and copy-paste ready code blocks. The Agent() syntax and ffprobe commands are concrete and immediately usable. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear sequencing (Steps 0-7), explicit validation checkpoints (--dry-run, ffprobe verification), and feedback loops (LONG status triggers text trimming and re-run). The act approval step before audio generation is a good checkpoint. | 3 / 3 |
Progressive Disclosure | Well-structured overview with clear references to REFERENCE.md for detailed command documentation, voice options, and installation. Content is appropriately split between the main skill and reference guide with one-level-deep navigation. | 3 / 3 |
Total | 11 / 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