add-new-package

Add a new package to the Remotion monorepo, including package scaffolding, monorepo registration, documentation, build scripts, tests, and release checklist updates. Use when creating a new @remotion package.

Quality

88%

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

83%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, highly actionable workflow that assumes Claude's competence and gives exact commands and config values. Its main gap is the absence of an explicit validation/verification step for this batch monorepo operation, which limits workflow clarity.

Suggestions

Add an explicit validation/verification step at the end of the workflow, e.g. after `bun run make` confirm the build succeeded, run the package's tests, and verify `bun i` completed without errors.

Turn the "See the writing-docs skill" mention into a clearly signaled reference (or note what specifically to consult) so documentation sub-steps can be delegated rather than inlined.

Add a short "Verify" checklist confirming monorepo registration took effect (e.g. the package appears in the studio-shared package-info map and builds via the root tsconfig references).

Dimension	Reasoning	Score
Conciseness	Lean and instruction-only with no padding or explanation of concepts Claude already knows; every line is a concrete file, config value, or command that earns its place.	5 / 5
Actionability	Provides copy-paste-ready specifics: exact file paths, config keys (e.g. `emitDeclarationOnly: true`, `module: "es2020"`), externalization lists, and commands like `cd packages/<name> && bun run make`.	5 / 5
Workflow Clarity	The numbered Steps 1–6 give a clear sequence, but this batch scaffolding operation has no explicit validation or verification checkpoint, which caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Well-organized into Steps/Version/Patterns sections and delegates documentation detail to the writing-docs skill, but that reference is a bare text mention rather than a clearly signaled navigable link, and some doc sub-steps remain inlined.	4 / 5
	Total	17 / 20 Passed

Description

92%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 strong description that clearly states the capability and provides an explicit, natural trigger phrase. It is specific and well-scoped, with only minor room for broader trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("package scaffolding, monorepo registration, documentation, build scripts, tests, and release checklist updates"), giving comprehensive coverage of what adding a package entails.	5 / 5
Completeness	Explicitly answers both what (the six enumerated actions) and when ("Use when creating a new @remotion package") with a concrete trigger phrase.	5 / 5
Trigger Term Quality	The trigger "Use when creating a new @remotion package" is a natural phrase users would say, but it is narrow and lacks synonyms or variations like "adding a package" or "scaffolding a package".	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (creating @remotion packages in the Remotion monorepo) with a distinct trigger and minimal overlap risk with unrelated skills.	5 / 5
	Total	19 / 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/add-new-package/SKILL.md
Commit: dbb2c0a

Reviewed: ~7 hours 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.