add-effect

Add a new effect to @remotion/effects, including implementation, package exports, docs, demos, preview images, Remotion skill updates, tests, formatting, and builds.

Quality

87%

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

Quality

Content

92%

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

A highly actionable, well-sequenced procedural skill with concrete commands and a justified code template. Its main weakness is structural: it is a monolithic SKILL.md with no bundle references, so detail that could live one level deeper is kept inline.

Suggestions

Move the WebGL2 effect template and the detailed docs/demo registration steps into reference files under references/ (e.g. references/webgl2-template.ts, references/docs-demo-steps.md) and link to them from SKILL.md to improve progressive disclosure.

Keep SKILL.md as a concise overview of the 10 steps with one-level-deep pointers to those references so the entry point stays scannable.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no basic-concept padding — with every token tied to Remotion-specific paths, commands, or API patterns; even the large WebGL2 template encodes non-obvious package conventions rather than generic knowledge.	3 / 3
Actionability	It provides concrete commands ('bunx remotion still ...', 'bun render-cards.ts', 'bunx oxfmt src --write'), exact file paths, and a real code template; the one deferred helper (createMyEffectState) is explicitly justified by pointing to existing files rather than left as vague pseudocode.	3 / 3
Workflow Clarity	A clearly numbered 1–10 sequence with explicit verification checkpoints — tests in step 4, build/format/git-diff checks in step 10 — plus a 'Common pitfalls' checklist, matching the score-3 anchor for sequenced validation with error-recovery guidance.	3 / 3
Progressive Disclosure	Sections are well-organized, but the skill is a single ~360-line monolith with no reference bundle files; the large WebGL2 template and detailed docs/demo steps that could be split out remain inline, fitting the score-2 'content that should be separate is inline' anchor rather than the split-with-references score-3 anchor.	2 / 3
	Total	11 / 12 Passed

Description

82%

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 specific, well-scoped description that enumerates the full set of sub-tasks and targets a distinct package niche. It is held back from a perfect score only by the absence of an explicit 'Use when...' trigger clause.

Suggestions

Add an explicit trigger clause such as 'Use when adding a new effect to @remotion/effects or when the user asks to create a new Remotion effect.' to lift completeness to 3.

Dimension	Reasoning	Score
Specificity	The description lists many concrete actions — 'implementation, package exports, docs, demos, preview images, Remotion skill updates, tests, formatting, and builds' — matching the multi-action score-3 anchor rather than a single vague domain.	3 / 3
Completeness	It clearly states what the skill does, but there is no explicit 'Use when...' trigger clause; per the guidelines a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Natural trigger terms for this domain are present — 'Add a new effect', 'effect', and '@remotion/effects' — which are the phrases a Remotion contributor would actually say; no irrelevant jargon.	3 / 3
Distinctiveness Conflict Risk	Scoping to the '@remotion/effects' package carves out a clear niche unlikely to fire for unrelated skills, matching the distinct-triggers score-3 anchor.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: remotion-dev/remotion
Path: .agents/skills/add-effect/SKILL.md
Commit: 1b58387

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.