CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

demo-video

Use when the user asks to create a demo video, product walkthrough, feature showcase, animated presentation, marketing video, or GIF from screenshots or scene descriptions. Orchestrates playwright, ffmpeg, and edge-tts MCPs to produce polished video content.

63

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./engineering/demo-video/skills/demo-video/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable skill body: concrete story structures, scene specs, artifact definitions, an anti-patterns table, and exemplary progressive disclosure with a single well-scoped reference file. The main gaps are minor — slight redundancy in fallback instructions and pipeline commands described rather than given.

DimensionReasoningScore

Conciseness

The body is efficient and dense with concrete tables, timings, and checklists, assuming Claude's competence. Minor trimmable padding exists: the persona rhetoric ("You are a video producer. Not a slideshow maker. Every frame has a job.") and the MCP-fallback information repeated across step 1, the mode table, and the Output Artifacts section.

4 / 5

Actionability

Concrete, specific guidance throughout — exact story arcs with per-scene durations, 1920x1080 viewport, exact spring easing curve, a defined artifact tree, and a build.sh pipeline description. However, the actual playwright/edge-tts/ffmpeg commands are sketched ('playwright screenshot each HTML scene') rather than given as copy-paste-ready commands, leaving minor gaps.

4 / 5

Workflow Clarity

A clear four-step sequence (mode selection with tool verification and fallbacks → story structure → scene design → narration) followed by a defined artifact spec, with a Quality Checklist serving as validation checkpoints. The checklist lacks an explicit validate→fix→re-check feedback loop, keeping it short of the full-checkpoint anchor.

4 / 5

Progressive Disclosure

The ~105-line body is well-sectioned, and design-system detail is appropriately split into a real, clearly signaled, one-level-deep reference (references/scene-design-system.md), which itself contains no further nested references. Cross-references to related skills are clearly labeled. This matches 'Clear overview with well-signaled one-level-deep references; content appropriately split'.

5 / 5

Total

17

/

20

Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with an explicit and richly triggered 'Use when' clause and concrete tool names, though the 'what' side is a single composite action that could enumerate the actual capabilities more comprehensively. Minor trigger overlap exists around 'animated presentation' and 'GIF'.

Suggestions

Expand the 'what' clause to enumerate concrete actions, e.g., 'Renders scene HTML to screenshots, generates TTS narration, and composites clips with crossfade transitions into a polished video' — this would lift both specificity and completeness.

Add missing natural trigger synonyms such as 'promo video', 'screen recording', or 'tutorial video' to broaden the natural-phrases users would say.

Clarify the boundary around 'animated presentation' and 'GIF' (e.g., specify motion-video output, not static presentation decks) to reduce overlap with presentation/image skills.

DimensionReasoningScore

Specificity

The description names the domain and a single composite action — "Orchestrates playwright, ffmpeg, and edge-tts MCPs to produce polished video content" — with concrete tool names, but does not enumerate several distinct actions (e.g., rendering scene HTML, generating narration, compositing with transitions). It matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'.

3 / 5

Completeness

Both sides are explicitly present: "Use when the user asks to create a demo video, product walkthrough..." answers 'when' with concrete triggers, and "Orchestrates playwright, ffmpeg, and edge-tts MCPs to produce polished video content" answers 'what'. However, the 'what' clause is thin and slightly vague ("polished video content"), so it does not clearly reach the fully-explicit both-sides anchor.

4 / 5

Trigger Term Quality

Phrases like "demo video", "product walkthrough", "feature showcase", "marketing video", "GIF", and "screenshots" are natural terms users would say, giving good coverage. A few common variations are missing (e.g., "promo video", "screen recording", "tutorial video"), so it falls short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The video-production-from-screenshots niche is mostly distinct with specific triggers, but terms like "animated presentation" and "GIF" create minor overlap risk with presentation-creation and image/animation skills. It fits 'Mostly distinct; minor overlap risk with closely related skills'.

4 / 5

Total

15

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

alirezarezvani/claude-skills

Path

engineering/demo-video/skills/demo-video/SKILL.md

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.