upgrade-caniuse

Upgrade the caniuse-lite override in the Remotion repo. Use when asked to update caniuse-lite to the latest npm version.

Quality

73%

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/upgrade-caniuse/SKILL.md

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is admirably lean and well-sequenced for a simple task, scoring well on conciseness and progressive disclosure. It loses points on actionability (vague version lookup) and workflow clarity (no validation before commit/push).

Suggestions

Replace "Look up the latest version with npm" with an executable command such as `npm view caniuse-lite version`.

Add a validation checkpoint after `bun i` (e.g. confirm the lockfile/override updated) before committing and pushing.

Specify the exact package.json edit, e.g. set `overrides.caniuse-lite` to the resolved version, so the guidance is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The five-bullet body is lean with no padding and no explanation of concepts Claude already knows; every token earns its place, matching the top anchor.	3 / 3
Actionability	"Run `bun i`" and the commit message format are concrete, but "Look up the latest version with npm" gives no executable command and the package.json edit is described rather than specified, leaving key details missing.	2 / 3
Workflow Clarity	Steps are clearly sequenced with a pre-flight clean-status check, but there is no validation checkpoint after install or before the destructive commit-and-push, capping it at 2 per the rubric guidance.	2 / 3
Progressive Disclosure	This is a simple single-purpose skill under 50 lines with no external references, and its single organized list is appropriately structured per the simple-skills scoring note.	3 / 3
	Total	10 / 12 Passed

Description

75%

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, in third person, and clearly pairs a specific action with an explicit trigger, giving it strong completeness and distinctiveness. Its main weakness is single-action specificity and limited trigger-term variation.

Suggestions

Broaden the action list (e.g. "check the latest version, update the override, reinstall, commit") to lift specificity toward the top anchor.

Add a couple of natural trigger phrasings (e.g. "bump caniuse-lite", "refresh caniuse-lite dependency") to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The phrase "Upgrade the caniuse-lite override in the Remotion repo" names the domain and one concrete action, but lists only a single action rather than the multiple concrete actions the top anchor requires.	2 / 3
Completeness	It states both what it does ("Upgrade the caniuse-lite override") and an explicit trigger ("Use when asked to update caniuse-lite to the latest npm version"), matching the top anchor.	3 / 3
Trigger Term Quality	"Use when asked to update caniuse-lite to the latest npm version" includes the natural keyword users would say, but offers limited variation coverage compared to the broad term list in the top anchor.	2 / 3
Distinctiveness Conflict Risk	The narrow scope of "caniuse-lite override in the Remotion repo" with its specific trigger is a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 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/upgrade-caniuse/SKILL.md
Commit: a2a8435

Reviewed: 2 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.