CtrlK
BlogDocsLog inGet started
Tessl Logo

product-demo-recording

Plan, capture, edit, and visually QA short product demo recordings for docs, releases, and integration walkthroughs. Use when recording or replacing browser/app videos such as n8n or Node-RED flows; not for general-purpose video production.

75

Quality

94%

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

92%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.

The body is an exceptionally disciplined operational skill: dense rules with no padding, a complete validated workflow with feedback loops, and clean one-level-deep progressive disclosure verified against real bundle files. The only gap is that executable capture/encode commands live in the references rather than the main body, which is a reasonable split for this complexity.

DimensionReasoningScore

Conciseness

The body is dense, prescriptive operational rules with no tutorial prose and no explanation of concepts Claude already knows — e.g. "Prefer a conventional 16:9 frame such as 1440x810 or 1920x1080" and "do not alter a video unless the defect is reproducible independently". Every line carries non-obvious project-specific guidance, matching the lean/every-token-earns-its-place anchor.

5 / 5

Actionability

Concrete executable elements are present — the qa-video.sh invocation with arguments, exact encode specs ("H.264 High, `yuv420p`, constant 30 fps… MP4 fast-start", "`-threads 1`"), and example annotation copy — but the body itself contains no copy-paste capture or encode command, delegating those to the reference files. This fits anchor 4 (mostly executable with minor gaps) rather than 5, and is well above anchor 3's pseudocode level.

4 / 5

Workflow Clarity

A clear end-to-end sequence (establish frame → safe capture boundary → record → edit → audio → QA → ship) with an explicit six-point decoded-deliverable checklist, feedback loops (re-run delivery QA after muxing audio; replace a corrupt segment and re-encode with `-threads 1`), and a hard gate ("Do not describe the recording as reviewed until these checks were performed"). This matches the anchor-5 pattern of explicit validation steps, error recovery, and checklists.

5 / 5

Progressive Disclosure

References are clearly signaled at the top and scoped by domain ("For native macOS or browser capture mechanics, read references/capture-macos.md…"), all three referenced files exist in the bundle, and they are one level deep without further nesting. The body stays at overview/policy level and the bundled script is invoked concretely — matching the well-signaled, one-level-deep anchor.

5 / 5

Total

19

/

20

Passed

Description

92%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 concise, concrete, and fully covers what the skill does and when to use it, including a well-chosen negative boundary. Its only weakness is missing common synonyms (screencast, screen recording, .mp4) that would broaden natural triggering.

DimensionReasoningScore

Specificity

"Plan, capture, edit, and visually QA short product demo recordings for docs, releases, and integration walkthroughs" lists four concrete actions plus their delivery contexts, matching the comprehensive multi-action anchor. Anchor 4 would require gaps in coverage, and none are evident.

5 / 5

Completeness

Explicitly answers both what ("Plan, capture, edit, and visually QA short product demo recordings") and when ("Use when recording or replacing browser/app videos such as n8n or Node-RED flows"), with concrete trigger phrases and an explicit negative boundary ("not for general-purpose video production").

5 / 5

Trigger Term Quality

Good natural keyword coverage — "recording", "replacing browser/app videos", "n8n or Node-RED flows", "docs, releases, and integration walkthroughs" are phrases a user would naturally say. Common synonyms like "screencast", "screen recording", or a file extension like ".mp4" are missing, which keeps it below the comprehensive anchor 5 but above anchor 3's partial coverage.

4 / 5

Distinctiveness Conflict Risk

Clear niche (product demo recordings for docs) with distinct triggers (n8n, Node-RED) and an explicit exclusion of general-purpose video production, giving minimal conflict risk with other skills.

5 / 5

Total

19

/

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
getlarge/themoltnet
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.