CtrlK
BlogDocsLog inGet started
Tessl Logo

release

Release a new Remotion version

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/release/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

This is an exceptionally strong operational skill: every step is an executable command with exact flags, error-recovery paths, and validation gates (auth checks, installability verification per package, dist-tag verification with rollback planning). The main weakness is structure — it is a monolithic flat checklist with no section headings and no separation of the changelog or publish procedures into reference files.

Suggestions

Add section headings (e.g. "## Pre-flight checks", "## Version bump & build", "## Public package publish", "## Private packages, templates & push", "## Changelog", "## Cleanup") so the long flat checklist is navigable.

Move the detailed changelog-generation procedure (lines 41-55) into a references/ file (e.g. CHANGELOG.md) and keep a one-line pointer in SKILL.md, reducing always-loaded context.

Consider extracting the npm polling/verification loop into a scripts/ file since it is already instructed to be written as a script and run in the background.

DimensionReasoningScore

Conciseness

The body is pure operational directive — exact commands, flags, and conventions — with no explanations of concepts Claude already knows. The few justifications given (npm masking tokens in JSON output, zsh lacking $PIPESTATUS, npm's ~15-minute validating scan) are non-obvious operational gotchas, so every token earns its place.

5 / 5

Actionability

Guidance is fully executable throughout: exact shell snippets (the releaseTag/releaseManifest block), exact env-var token passing (`env "npm_config/registry.npmjs.org/:_authToken=$TOKEN"`), a working extraction regex (`grep -oE 'npm_[A-Za-z0-9]{20,}'`), and per-package polling via the npm lifecycle status API. Copy-paste ready for every common case in the release flow.

5 / 5

Workflow Clarity

The multi-step sequence is explicit with validation checkpoints at every risky boundary: gcloud and npm auth checks up front, abort on non-zero exit from set-version.ts, per-package `npm view` + `npm pack` installability gates before promotion, dist-tag verification with rollback of recorded previous tags, and defined handling of pending/blocked states. This is a batch operation with abundant feedback loops, so no cap applies.

5 / 5

Progressive Disclosure

There are no bundle files at all and the body is a flat ~55-line bullet list with no section headers; the changelog-generation procedure (a self-contained sub-process) and the detailed npm publish/promotion flow could live in separate reference files. Structure exists via nesting and ordering, but nothing is organized into sections or offloaded. Not a 2 because the content is coherently ordered and navigable, and not a 4 because no headings or clearly signaled references exist and the changelog section clearly could be split out.

3 / 5

Total

18

/

20

Passed

Description

48%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.

The description is concise and unambiguous about the target domain (Remotion releases), but it does the minimum: one generic action, no trigger guidance, and no mention of the concrete steps the skill actually covers (npm publishing, dist-tag promotion, changelog, templates). It would be far more discoverable and complete with a fuller action list and an explicit "Use when..." clause.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to release, publish, or cut a new version of Remotion, bump versions, or publish Remotion packages to npm."

List the concrete actions the skill covers, e.g. "Publishes all Remotion packages to npm under a temporary dist-tag, verifies installability, promotes latest tags, publishes templates, and generates the GitHub release changelog."

Include natural synonyms such as "publish", "ship", "cut a release", and "version bump" so the description matches the phrasings a user is likely to say.

DimensionReasoningScore

Specificity

"Release a new Remotion version" names the domain but lists only one minimal, generic action, matching the anchor 'Names the domain but actions are minimal or generic' ('Processes PDF files'). It is not a 3 because no second concrete action (publish to npm, changelog, templates) is mentioned.

2 / 5

Completeness

It has a clear "what" (release a new Remotion version) but no "Use when..." clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3. It is not a 4 because the "when" is entirely absent rather than merely implicit or weak.

3 / 5

Trigger Term Quality

"Release", "Remotion", and "version" are natural terms a user would say, but common variations such as "publish", "ship", or "cut a release" are missing. This matches the anchor 'Some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

"Remotion" establishes a clear niche, but the action phrase "Release a new ... version" is generic and could overlap with a generic release/publish skill. Mostly distinct with minor overlap risk; not a 5 because the trigger lacks the concrete, distinctive phrases the top anchor requires.

4 / 5

Total

12

/

20

Passed

Validation

100%

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
Reviewed

Table of Contents

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.