CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

nex-screencast-cleaner

Automatically crops OS taskbars and removes dead air from screen recordings for upload-ready demos. Use when: Crop Windows taskbar or macOS Dock from screen captures automatically; Remove static pauses from demos to create high-density product clips; Normalize non-standard recording resolutions to 1080p for web players.

Quality

61%

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 ./plugins/nex-business-operations/skills/nex-screencast-cleaner/SKILL.md

The canonical home for this skill is nex-screencast-cleaner in NexaiGuy/nex-ai-skills

SKILL.md
Quality
Evals
Security

Quality

Content

15%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 a marketing brochure rather than an operational skill file: it describes capabilities and limitations well but provides no code, commands, workflow steps, or validation guidance, and the actual processing scripts are explicitly absent from the folder. An agent reading this would have no idea how to execute the skill.

Suggestions

Add the actual processing script (or at minimum a copy-paste-ready ffmpeg/Python command sequence) and an 'Example' section showing how to invoke it, moving the skill from description-only to executable guidance.

Replace the prose capability list with a numbered workflow (detect chrome -> crop -> detect static spans -> cut -> normalize to 1920x1080 with +faststart -> encode H.264), including a validation checkpoint that verifies output dimensions and duration before finishing.

Cut the promotional sections ('Why this beats prompting it yourself', 'What is included in my purchase', creator catalog link) and move the FAQ answers into a separate reference file or fold the essential ones (audio dropped, no talking-head footage) into a short limitations section.

DimensionReasoningScore

Conciseness

Multiple padded sections add no instructional value: "Why this beats prompting it yourself", a six-question FAQ that restates the description, "What is included in my purchase", and a paid-catalog plug. It is not 1 because it does not explain concepts Claude already knows, but most of the body is promotional filler rather than lean guidance.

2 / 5

Actionability

There is no executable code, command, or concrete instruction anywhere; passages like "The skill uses pixel-level analysis to detect static frames" and "Uses a specialized logic gate" only describe the tool rather than instruct. This matches the anchor for entirely descriptive content with no concrete code or commands.

1 / 5

Workflow Clarity

No sequenced steps exist; the closest content is the prose bullet list in "What it does" and the Example's input/output transcript, which is less instructive than the anchor-1 example's rough two-step instruction. There are no validation checkpoints for this batch video-processing operation, which would cap the score at 3 regardless.

1 / 5

Progressive Disclosure

Sections are clearly headed and the file is self-contained with no broken or nested references, but at roughly 77 lines it exceeds the under-50-line exception, and ~30 lines of FAQ and purchase/promotional content are inlined that should be split out or removed. It is not 4 because substantial content is inappropriately placed, and not 2 because the existing organization is genuinely easy to navigate.

3 / 5

Total

7

/

20

Passed

Description

87%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 strong: it states concrete capabilities in third person and provides an explicit 'Use when:' clause with three distinct, natural trigger scenarios. Coverage is nearly comprehensive, missing only the output-format capability and a few synonym terms.

DimensionReasoningScore

Specificity

"Automatically crops OS taskbars and removes dead air from screen recordings" plus "Normalize non-standard recording resolutions to 1080p" lists three specific concrete actions, matching the anchor with several specific actions and minor gaps. It is not 5 because the H.264/MP4 output generation documented in the body is omitted, and not 3 because coverage goes beyond 1-2 actions.

4 / 5

Completeness

A clear 'what' (crops taskbars, removes dead air, normalizes resolution) is paired with an explicit "Use when:" clause listing three concrete trigger phrases. Anti-drift check: the 'when' is explicit and concrete, so anchor 4's 'when could be more explicit' does not fit.

5 / 5

Trigger Term Quality

Natural terms like "Windows taskbar", "macOS Dock", "screen captures", "static pauses", "demos", and "1080p" give good keyword coverage. It is not 5 because common synonyms ("screencast", "video", "OBS recording") and source-tool names are missing, and it clearly exceeds anchor 3's single-phrase coverage.

4 / 5

Distinctiveness Conflict Risk

The screen-recording cleanup niche with distinct triggers ("taskbar", "Dock", "dead air", "static pauses") has minimal overlap with any plausible sibling skill. Anchor 4's 'minor overlap risk' does not apply since no related-skill triggers share this vocabulary.

5 / 5

Total

18

/

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

NexaiGuy/nex-ai-skills

Path

plugins/nex-business-operations/skills/nex-screencast-cleaner/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.