release

Release a new Remotion version

Quality

42%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/release/SKILL.md

Quality

Content

77%

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

The body is a highly actionable, well-sequenced release runbook with strong validation checkpoints, excelling on actionability and workflow clarity. Its weaknesses are conciseness (some redundant prose) and progressive disclosure (a monolithic inline document with no file structure or navigation).

Suggestions

Tighten redundant prose: the npm-token step repeats the OTP retrieval command, and the Codex rbenv note can be condensed to its essential PATH prefix and verification command.

Split the runbook into clearly headed sections (e.g. 'Pre-flight checks', 'Version bump & build', 'Publish', 'Changelog') so the high-level flow is skimmable, even without external bundle files.

Consider moving the lengthy changelog-generation sub-procedure into a separate reference file referenced one level deep, leaving SKILL.md as a concise overview.

Dimension	Reasoning	Score
Conciseness	The runbook is mostly lean actionable bullets, but prose passages like the Codex rbenv paragraph and the npm-token bullet (which repeats the OTP retrieval twice) could be tightened, fitting the 'mostly efficient but could be tighter' anchor.	2 / 3
Actionability	Nearly every step is a concrete, copy-paste-ready command (gcloud, op, npm, bun, gh) with explicit arguments and value substitution, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Steps are explicitly sequenced with validation checkpoints and abort conditions (gcloud auth check, exit-code abort on set-version, lambda failure abort, template failure abort), matching the clear-sequence-with-feedback-loops anchor.	3 / 3
Progressive Disclosure	The content is a single monolithic inline runbook with no section headers, no bundle files, and no one-level-deep references, so although self-contained it is not structured for progressive disclosure.	2 / 3
	Total	10 / 12 Passed

Description

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 terse four-word label that identifies the product niche but conveys no concrete capabilities and no usage triggers, scoring poorly on every dimension except distinctiveness. It reads as a name rather than a discoverable skill description.

Suggestions

List concrete release actions in the description, e.g. 'Bump the Remotion version, publish packages to npm, generate a changelog, and republish templates.'

Add an explicit 'Use when...' trigger clause naming natural user phrasings such as 'release', 'publish Remotion', or 'cut a new Remotion version'.

Mention key artifacts the user would reference (npm packages, changelog, GitHub release) to improve both specificity and trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description 'Release a new Remotion version' names the domain but lists no concrete actions (e.g. bump version, publish to npm, generate changelog), matching the vague/abstract anchor rather than the multi-action anchor.	1 / 3
Completeness	It weakly states what the skill does but provides no 'Use when...' or equivalent trigger guidance, missing the 'when' half entirely.	1 / 3
Trigger Term Quality	Only 'Remotion' and 'version' appear; there is no coverage of natural user phrasing such as 'publish', 'npm release', or 'cut a release', so it lacks common keyword variations.	1 / 3
Distinctiveness Conflict Risk	'Remotion' is a distinct niche unlikely to collide with other skills, but the thin trigger phrasing ('Release a new version') could overlap with generic release tooling.	2 / 3
	Total	5 / 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/release/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.