CtrlK
BlogDocsLog inGet started
Tessl Logo

video-report

Generate a report about a video

44

Quality

45%

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 ./.agents/skills/video-report/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 concise and gives two concrete executable steps, but it presents only a rough sequence with no validation or feedback loop for what is essentially a diagnostic workflow, leaving Claude without checkpoints to confirm the report succeeded. Structure is fine for a small single-purpose skill with no bundle files.

Suggestions

Add a validation step after rendering, e.g. inspect the verbose log output for the specific error and confirm the report identifies why the video failed.

Clarify how the downloaded video becomes the src (e.g., save path and the exact code edit in NewVideo.tsx) to remove the gap between downloading and rendering.

Specify what the 'report' output should contain so the result is verifiable rather than implied.

DimensionReasoningScore

Conciseness

The two-line body is lean and assumes Claude's competence with no padded explanations of what Remotion or rendering is, matching the efficient-with-minor-trimmable-instances anchor; it is not a perfect 5 only because 'we should' phrasing is slightly informal rather than maximally lean.

4 / 5

Actionability

It provides concrete, executable guidance — a specific file path to edit and an exact command (`bunx remotion render NewVideo --log=verbose`) — with only minor gaps (no verification of the download or what to inspect in verbose logs), fitting the mostly-executable-minor-gaps anchor.

4 / 5

Workflow Clarity

There is a rough two-step sequence (download + set src, then render) but it lacks any validation checkpoints despite the operation being a diagnostic/render workflow where verification of the report matters; validation absence caps the score low, and the rough-sequence-many-gaps anchor fits best.

2 / 5

Progressive Disclosure

For a short single-purpose skill under 50 lines with no external bundle files needed, the content is appropriately contained in well-organized lines with no nested references, qualifying for the simple-skill exception that allows a 5.

5 / 5

Total

15

/

20

Passed

Description

30%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 minimal and vague: it names the video domain but offers no concrete actions, no natural trigger terms, and no 'Use when...' guidance, leaving Claude unlikely to know when to invoke it. It is broadly applicable and at risk of overlapping with other media-handling skills.

Suggestions

Add concrete actions, e.g. 'Downloads a reported video URL, renders it with Remotion, and diagnoses why it failed to play.'

Add a 'Use when...' trigger clause, e.g. 'Use when a user reports a video is not working or fails to play in the example app.'

Include natural trigger phrases users would actually say such as 'video not working', 'broken video', or 'video won't render' to improve match quality and distinctiveness.

DimensionReasoningScore

Specificity

The description 'Generate a report about a video' names the domain (video) and a single minimal action (generate a report) but no concrete actions, matching the anchor that names the domain with minimal/generic actions.

2 / 5

Completeness

It states a vague 'what' (generate a report about a video) with no 'when' / 'Use when...' clause; a missing explicit trigger guidance caps completeness at 3 at most, and the absence of any 'when' puts it at the vague-what-no-when anchor.

2 / 5

Trigger Term Quality

It contains only the generic terms 'video' and 'report', lacking the natural phrases a user would say (e.g., 'video not working', 'broken video', 'debug video'), which is one or two generic keywords missing natural phrasing.

2 / 5

Distinctiveness Conflict Risk

'Generate a report about a video' is very broad with high overlap risk against many media/analysis skills, matching the very-broad high-overlap anchor; it is not entirely generic enough for a 1 but lacks any distinguishing triggers for a 3.

2 / 5

Total

8

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
remotion-dev/remotion
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.