video-report

Generate a report about a video

Quality

52%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/video-report/SKILL.md

Quality

Content

80%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 exemplary in its token efficiency and gives mostly executable guidance — exact paths and a runnable command — but the workflow has no validation or feedback loop and leaves the input (the URL) and output location implicit. For a two-sentence skill the structure is appropriate, so the weaknesses are confined to actionability and workflow rigor.

Suggestions

Add a concrete download step, e.g. "Download the reported URL: `curl -L <url> -o packages/example/public/report.mp4`", so the first action is copy-paste ready like the render command.

Add a validation checkpoint after the render, e.g. "Check the render exits 0 and inspect the output in `out/NewVideo.mp4`; re-run with `--log=verbose` output if frames are dropped".

Disambiguate the input by naming where the reported URL comes from (the user's message, a ticket field) rather than the bare "the URL".

Dimension	Reasoning	Score
Conciseness	The body is two lean sentences with zero padding and no explanation of concepts Claude already knows — "download the URL and put it as the `src` in `packages/example/src/NewVideo.tsx`" plus a single exact command. Every token earns its place, matching anchor 5.	5 / 5
Actionability	The guidance is mostly executable: a specific file path, a specific field (`src`), and the exact command `bunx remotion render NewVideo --log=verbose`. It stops short of anchor 5 because the download step has no command and the render's output location is never stated.	4 / 5
Workflow Clarity	A clear two-step sequence is present ("Then, in `packages/example`..."), but there are no validation checkpoints — nothing confirms the download succeeded or that the render completed — and "the URL" is ambiguous. Anchor 3 ("sequence present but checkpoints missing or implicit") fits better than 4, where checkpoints would exist with only minor gaps.	3 / 5
Progressive Disclosure	The body is well under 50 lines, needs no external references, and its two sentences are trivially navigable (download/swap, then render). Per the rubric's simple-skill guideline, a skill this small with no need for bundle files can score 5 on structure alone.	5 / 5
	Total	17 / 20 Passed

Description

25%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 a near-minimal one-liner: it names the domain but gives a generic action, no trigger guidance, and no distinguishing niche. Every dimension lands at the second-lowest anchor because the phrase is short but uninformative rather than concise-and-clear.

Suggestions

Add an explicit trigger clause, e.g. "Use when a user reports a video not playing, rendering incorrectly, or failing to render in a Remotion project".

State the concrete actions instead of the vague "generate a report", e.g. "Downloads the reported video URL, swaps it into the Remotion composition, and renders it with `bunx remotion render` to reproduce the issue".

Include the natural vocabulary of this niche — "video not working", "render", "Remotion", "playback failure" — so the skill is distinguishable from generic video-analysis skills.

Dimension	Reasoning	Score
Specificity	"Generate a report about a video" names the domain but the action is minimal and generic — there is no mention of rendering, diagnosing, or what the report contains. It matches anchor 2 ("Names the domain but actions are minimal or generic") rather than 3, which requires at least one or two genuinely concrete actions.	2 / 5
Completeness	The description has a vague "what" (a report about what aspect of the video?) and no "when" clause whatsoever. Per the guideline capping a missing 'Use when...' at 3, it fits anchor 2 ("Has a vague 'what' and no 'when'") and cannot score higher.	2 / 5
Trigger Term Quality	The only keywords are "video" and "report" — two generic terms — while the natural phrases a user would actually say ("video not working", "render fails", "remotion") are absent. This matches anchor 2 rather than 3, since anchor 3 presumes a relevant keyword set is present and merely missing variations.	2 / 5
Distinctiveness Conflict Risk	"Generate a report about a video" would plausibly trigger for video analysis, media processing, and playback debugging skills alike — very broad with high overlap risk, matching anchor 2. It is not a 3 because nothing in the phrasing narrows the overlap with similar skills.	2 / 5
	Total	8 / 20 Passed

Validation

100%

Warnings & errors only

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: remotion-dev/remotion
Path: .agents/skills/video-report/SKILL.md
Commit: 6f4e0d5

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.