demo-video
Build a narrated demo video from a screen recording, a talk track script with act timelines, branded intro/outro slides, background music, and AI-generated voiceover via ElevenLabs. Use when user asks to create a "demo video", "product demo", "narrated screencast", "talk track video", or "voiceover video".
94
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 specific capabilities (screen recording processing, talk track scripting, branded slides, background music, ElevenLabs voiceover) and provides explicit trigger guidance with five natural user phrases. It is concise, uses third-person voice, and occupies a distinct niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: building narrated demo video from screen recording, talk track script with act timelines, branded intro/outro slides, background music, and AI-generated voiceover via ElevenLabs. | 3 / 3 |
Completeness | Clearly answers both 'what' (build narrated demo video with specific components like screen recording, talk track, branded slides, music, ElevenLabs voiceover) and 'when' (explicit 'Use when' clause with five trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes excellent natural trigger terms users would actually say: 'demo video', 'product demo', 'narrated screencast', 'talk track video', 'voiceover video'. These cover common variations of how users would phrase this request. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining screen recording, narrated voiceover, branded slides, and ElevenLabs integration. Very unlikely to conflict with other skills due to the specific combination of video production elements. | 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 that provides a comprehensive pipeline for building narrated demo videos. Its main strengths are excellent workflow clarity with validation checkpoints, highly actionable guidance with specific commands and parameters, and good progressive disclosure to supplementary files. The primary weakness is moderate verbosity — the Script Writing Methodology section and some repeated information between the input gathering and workflow sections could be tightened to save tokens.
Suggestions
Consolidate the 'Required Input' section and 'Step 1: Gather Input' in the workflow to eliminate redundancy — one or the other is sufficient.
Consider moving the Script Writing Methodology to a separate SCRIPT_WRITING.md file and linking to it, since it's a substantial sub-process that adds ~30 lines to the main skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly well-structured but includes some sections that could be tightened — the Script Writing Methodology is quite lengthy and detailed, and some explanations (e.g., 'generic scripts feel dubbed, synced scripts feel alive') are stylistic filler. The pipeline overview and input gathering sections repeat information that appears again in the workflow steps. | 2 / 3 |
Actionability | The skill provides concrete commands (ffmpeg, ffprobe, mkdir), specific parameter values (stability=0.6, similarity_boost=0.8), exact file paths, API endpoints, and clear examples of script format. The incremental build instructions with specific file deletion patterns are highly actionable. | 3 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced with explicit validation (Step 7: verify audio channels, sync drift, music overlap). Step 8 provides a feedback loop for common adjustments with specific remediation steps. The incremental build section adds another layer of error recovery guidance. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to FFMPEG_REFERENCE.md and ELEVENLABS.md for detailed technical content. The build directory structure, dependency table, and workflow steps are well-organized sections that allow scanning without deep reading. | 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.
- Repository
- paolomoz/skills
- Commit
3591fab
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.