turborepo

Turborepo expert guidance. Use when setting up or optimizing monorepo builds, configuring task caching, remote caching, parallel execution, or the --affected flag for incremental CI.

Quality

76%

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 ./plugins/vercel/skills/turborepo/SKILL.md

Quality

Content

65%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.

The content is highly actionable with extensive copy-paste examples and well-organized sections, but it is a monolithic single file with some padded/marketing prose and lacks validation checkpoints in its batch/destructive workflows, capping workflow_clarity and progressive_disclosure.

Suggestions

Add explicit validation feedback loops for batch/destructive operations — e.g., after `turbo prune` or CI `turbo build --affected`, show how to verify the output/lockfile before proceeding — to lift workflow_clarity above 3.

Move the Microfrontends & Multi-App Composition deep-dive (and the full CI matrix examples) into one-level-deep reference files linked from SKILL.md, so the overview stays lean and progressive_disclosure improves.

Trim the marketing-flavored intro ('the build system for agentic coding', 'Rust-powered core') and any concept explanation Claude already knows to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, code-and-table reference content, but it carries padding (the marketing intro 'the build system for agentic coding ... Rust-powered core') and a lengthy Microfrontends deep-dive covering Next.js multi-zone patterns Claude largely already knows, so it sits at 'mostly efficient with some unnecessary explanation'.	3 / 5
Actionability	Fully executable guidance throughout — copy-paste turbo.json pipelines, bash commands, CI YAML, a filter-syntax table, and concrete config-key explanations cover the common cases comprehensively.	5 / 5
Workflow Clarity	Sequences are present (the --affected 4-step traversal, the detect→test CI matrix) but there are no validation/feedback checkpoints; per the rubric, batch/destructive operations like `turbo prune` and CI builds without validate→fix→retry loops cap this at 3.	3 / 5
Progressive Disclosure	The single 595-line file has clear section headers and is navigable, but everything is inlined (microfrontends, CI matrix, full config examples) with no one-level-deep reference files to split the bulk, matching 'some structure but content that should be separate is inline'.	3 / 5
	Total	14 / 20 Passed

Description

87%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 well-crafted: it names a clear niche, lists concrete capability areas, and provides an explicit 'Use when' trigger clause with natural terms. Minor gaps in action coverage keep specificity and trigger_term_quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability areas ('setting up or optimizing monorepo builds, configuring task caching, remote caching, parallel execution, or the --affected flag for incremental CI') but the 'expert guidance' framing is generic and a few capabilities (prune, boundaries) are absent, so it falls just below the comprehensive anchor.	4 / 5
Completeness	Explicitly answers both what ('Turborepo expert guidance') and when with a concrete 'Use when ...' clause enumerating specific trigger scenarios, matching the anchor that requires concrete trigger phrases for both.	5 / 5
Trigger Term Quality	Contains natural phrases users actually say ('monorepo builds', 'task caching', 'remote caching', 'parallel execution', '--affected flag', 'incremental CI') with good keyword coverage, though a few synonyms/extensions are missing so it does not reach full comprehensiveness.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Turborepo/JS-TS monorepo build system) with distinct triggers and named flags, making it unlikely to fire for unrelated skills.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (612 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	13 / 16 Passed

Repository: openai/plugins
Path: plugins/vercel/skills/turborepo/SKILL.md
Commit: 1e28582

Reviewed: 4 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.