CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

demo-video

Record captioned product walkthrough videos of any web app with Playwright + ffmpeg — proof videos for stakeholders, feature demos, bug-fix evidence

67

Quality

84%

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

SKILL.md
Quality
Evals
Security

Quality

Content

96%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.

This is an exemplary operational skill: fully executable code and commands, an explicit validation gate before delivery, and dense battle-tested gotchas with zero concept-explanation padding. The only structural note is that at ~100 lines with no reference files, some material (caption helper, gotchas) could eventually be split into references/ as the skill grows.

DimensionReasoningScore

Conciseness

The body never explains concepts Claude already knows (no 'what is Playwright/ffmpeg' padding) and every section is operational: the 5-step method, hard-won gotchas, exact commands, and a naming convention with its failure mode justified ('never a count (wc -l), which reuses an index'). Minor narrative flavor ('Battle-tested', 'learned the hard way') still conveys provenance, matching the lean anchor 5 rather than the 'could be tightened' anchor 4.

5 / 5

Actionability

Fully executable throughout: the Playwright `test.use({ video: ... })` config, a complete copy-paste `caption()` injection function, ffmpeg conversion and frame-extraction commands, and a working no-clobber index-allocation loop. Placeholders like `e2e/zz-<name>-video.spec.ts` are clearly parameterized rather than pseudocode, matching the copy-paste-ready anchor 5.

5 / 5

Workflow Clarity

A clear sequence (write spec → record → caption chapters → convert → verify → deliver → clean up) with an explicit validation checkpoint: 'ALWAYS spot-check frames before delivering... Never deliver an unviewed video', plus real in-spec assertions so 'a video of a broken flow must fail loudly'. The gotchas section supplies error-recovery guidance for the known failure modes, matching anchor 5; not below because both checkpoints and feedback guidance are explicit.

5 / 5

Progressive Disclosure

Sections are well-organized, all content is one level deep, and nothing is buried — but the body is ~100 lines, above the under-50-line simple-skill exception, and no bundle files exist to split out content like the caption helper or the gotchas catalog. It matches anchor 4 (good structure, minor organization gaps) rather than 5, which expects a concise overview with well-signaled references or a genuinely short single-purpose body.

4 / 5

Total

19

/

20

Passed

Description

66%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.

The description is specific and tool-named with good natural trigger terms, but it lacks an explicit 'Use when...' clause, leaving the 'when' only weakly implied and capping completeness at 3. Adding explicit trigger guidance and common synonyms like 'screen recording' would make it a top-tier description.

Suggestions

Add an explicit trigger clause, e.g. 'Use when asked for a video, screen recording, walkthrough, or visual proof of a feature or fix in a web app' — the missing 'when' currently caps completeness at 3.

Include common synonyms users would naturally say, such as 'screen recording' or 'screen capture', to broaden trigger-term coverage beyond 'video/walkthrough/demo/proof'.

State the downstream actions explicitly (e.g., 'converts recordings to mp4, spot-checks frames, and delivers a named file') to round out the action coverage toward the top specificity anchor.

DimensionReasoningScore

Specificity

Concrete action 'Record captioned product walkthrough videos' with named tools 'Playwright + ffmpeg' and specific deliverable types ('proof videos for stakeholders, feature demos, bug-fix evidence'). Not 5 because it names one core action rather than enumerating multiple concrete actions (e.g., conversion to mp4 and delivery are not stated); not 3 because tools and deliverable types go beyond a bare domain-plus-one-action description.

4 / 5

Completeness

The 'what' is clear (record captioned walkthrough videos with Playwright + ffmpeg), but there is no explicit 'Use when...' clause — the trailing use-case list ('proof videos for stakeholders, feature demos, bug-fix evidence') only weakly implies when, which caps completeness at 3 per the judging guidelines. Not 4 because the 'when' is not stated as explicit trigger guidance.

3 / 5

Trigger Term Quality

Includes natural terms users would say — 'video', 'walkthrough', 'demo', 'proof' — plus the domain phrase 'any web app'. Not 5 because common synonyms such as 'screen recording', 'screen capture', or 'feature demo video' phrasing variations are missing; well above 3 since several genuinely natural trigger words are present.

4 / 5

Distinctiveness Conflict Risk

A clear niche (video walkthrough recording) with distinct triggers ('video', 'walkthrough', 'proof') that would not fire for unrelated skills. Not 5 because there is minor overlap risk with closely related skills (Playwright E2E testing, screenshot-based visual validation); not 3 because the video-recording trigger terms are well differentiated from those neighbors.

4 / 5

Total

15

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

alinaqi/maggy

Path

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.