add-effect

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

Quality

75%

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/add-effect/SKILL.md

Quality

Content

75%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 dense, well-sequenced operational guide with real commands, file paths, and a near-complete code template — it respects the reader's competence and covers the full pipeline from implementation to rendered docs assets. The main gaps are the placeholder in the code template, missing failure-recovery guidance, and some duplicated rationale.

Suggestions

Make the WebGL template fully executable by inlining or explicitly linking the createMyEffectState() helper, or move the full template to a reference file with a one-line pointer.

Add brief failure-recovery guidance for the verification steps (e.g., what to check when 'bun test' or 'bun run build' fails).

Deduplicate the fit="cover" rationale, keeping it in one section and cross-referencing from the other.

Dimension	Reasoning	Score
Conciseness	Nearly every line is project-specific (file paths, naming conventions, commands) with no explanation of concepts Claude already knows; it assumes competence throughout. Not 5 because the 'fit="cover"' rationale is repeated in sections 6 and 7, and a few passages could be tightened.	4 / 5
Actionability	Concrete commands throughout ('bun test src/test', 'bunx turbo make', 'bunx remotion still ... --image-format=png', 'bun render-cards.ts') plus a detailed template. Not 5 because the main WebGL template is not copy-paste executable — 'createMyEffectState()' is an undefined stand-in.	4 / 5
Workflow Clarity	Ten clearly sequenced sections with explicit validation checkpoints (build-and-verify in section 4; format, build, 'git diff --check', 'git status --short' in section 10). Not 5 because error-recovery feedback loops (e.g., what to do when tests or the build fails) are absent.	4 / 5
Progressive Disclosure	No bundle files exist, so this is a single-file skill; structure is good with well-signaled pointers to concrete repo files ('halftone.ts', 'blur/blur-runtime.ts', 'bundle.ts') and related skills ('writing-docs', 'docs-demo'). Not 5 because the ~130-line WebGL boilerplate template could arguably live in a reference file, trimming the main body.	4 / 5
	Total	16 / 20 Passed

Description

75%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 highly specific, well-scoped description with concrete enumerated actions and third-person voice. Its one material weakness is the absence of any 'Use when...' trigger clause, which caps completeness and leaves invocation conditions implicit.

Suggestions

Append an explicit trigger clause, e.g., 'Use when adding a new effect, filter, or shader to the @remotion/effects package.'

Add natural synonyms users might say ('visual effect', 'shader', 'filter') to broaden trigger-term coverage.

Keep the action list but front-load the most likely trigger phrase so it reads as what-and-when in one line.

Dimension	Reasoning	Score
Specificity	The description lists multiple specific concrete actions — 'implementation, package exports, docs, demos, preview images, Remotion skill updates, formatting, and builds' — giving comprehensive coverage of the task in third-person voice. It matches the 5 anchor ('multiple specific concrete actions; comprehensive coverage') better than 4, which expects minor coverage gaps.	5 / 5
Completeness	The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 4 because the 'when' is entirely absent rather than merely implicit.	3 / 5
Trigger Term Quality	'Add a new effect' and '@remotion/effects' are natural phrases a user would say, giving good keyword coverage. Below 5 because common variations and synonyms (e.g., 'shader', 'visual effect', 'filter', 'transition') are absent.	4 / 5
Distinctiveness Conflict Risk	'@remotion/effects' is a clearly scoped niche with distinct triggers ('effect', 'remotion'), so conflict risk with other skills is minimal. It fits the 5 anchor rather than 4, which expects residual overlap with closely related skills.	5 / 5
	Total	17 / 20 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: 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.