CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

minutes-video-review

Analyze a product walkthrough, bug report video, Loom, or ScreenPal using Minutes transcription plus visual review. Use when the user wants a recorded demo or bug clip turned into a durable brief with transcript, key frames, issues, and next steps.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

82%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-built skill body: executable commands with realistic flags, a clear three-phase workflow, disciplined context guidance, and genuine one-level-deep reference files. Main improvements are removing the description-duplicating intro and the artifact-list duplication with output-schema.md, and adding failure-handling guidance for missing dependencies.

DimensionReasoningScore

Conciseness

The body is efficient with no concept explanations and clear sectioning, but the opening paragraph ('Analyze a product walkthrough, bug report video, Loom, ScreenPal, or local recording into a durable artifact bundle') near-duplicates the frontmatter description, and lines like 'Do not send the full video itself to the reasoning layer' explain the obvious. Not 5 due to this trimmable repetition; not 3 because there is no padding or taught material.

4 / 5

Actionability

Provides copy-paste-ready commands for local files, hosted URLs, and the full options case ('--focus', '--cookies-from-browser chrome', '--frame-step 15'), plus the exact JSON output keys to read. Fully executable guidance covering the common cases, matching the 5 anchor.

5 / 5

Workflow Clarity

Three clearly sequenced phases (run pipeline, inspect artifacts in a defined order, produce the brief) with explicit direction to read analysis.md first. Not 5 because there are no explicit validation or error-recovery checkpoints (e.g., what to do if the script fails or yt-dlp is missing); the pipeline writes to an isolated bundle so it is not destructive/batch and no cap applies.

4 / 5

Progressive Disclosure

Well-organized sections with two clearly signaled, one-level-deep references (references/dependencies.md, references/output-schema.md) that exist in the bundle, plus a bundled script kept out of the body. Not 5 because the 'Expected files' list and artifact-key details duplicate output-schema.md content that could live entirely in the reference; not 3 because structure and navigation are good.

4 / 5

Total

17

/

20

Passed

Description

83%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 that names a specific niche, lists concrete outputs, and includes an explicit and specific 'Use when' trigger clause. Keyword coverage is good but misses common synonyms like 'screen recording' or file extensions, and the generic 'Analyze a... video' opening leaves slight conflict risk with general video-analysis skills.

DimensionReasoningScore

Specificity

Names the domain ('product walkthrough, bug report video, Loom, or ScreenPal') and several concrete actions and outputs ('Minutes transcription plus visual review', 'durable brief with transcript, key frames, issues, and next steps'). Not 5 because pipeline-level capabilities (download, frame sampling, artifact bundle) are not surfaced; well above the 1-2-action anchor of 3.

4 / 5

Completeness

Explicitly answers both: what ('Analyze a product walkthrough, bug report video... using Minutes transcription plus visual review' into 'a durable brief with transcript, key frames, issues, and next steps') and when ('Use when the user wants a recorded demo or bug clip turned into a durable brief'). Both are concrete and explicit, matching the 5 anchor; the 'when' clause is specific rather than generic, so 4's 'could be more explicit' does not apply.

5 / 5

Trigger Term Quality

Includes natural phrases users would say: 'product walkthrough', 'bug report video', 'Loom', 'ScreenPal', 'recorded demo', 'bug clip'. Not 5 because common variations like 'screen recording', 'screen cast', 'mp4', or other platforms are missing; clearly better than the partial-coverage anchor of 3.

4 / 5

Distinctiveness Conflict Risk

The Minutes/Loom/ScreenPal product-demo niche is mostly distinct with anchored triggers. Not 5 because 'Analyze a... video' phrasing leaves minor overlap risk with generic video-understanding skills; well above the vague-overlap anchors of 2-3.

4 / 5

Total

17

/

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

silverstein/minutes

Path

.claude/plugins/minutes/skills/minutes-video-review/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.