turborepo

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

Quality

90%

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

86%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 body is highly actionable and well-structured with a strong one-level-deep reference system, assuming Claude's competence throughout. The main weakness is length and some intentional-but-redundant repetition of the 'turbo run' rule, plus workflow guidance that is rule-based rather than built around explicit validate-fix-retry loops.

Suggestions

Consolidate the 'turbo run' vs 'turbo' shorthand guidance into one section and cross-reference it from the anti-patterns list to remove the duplicated explanation and trim tokens.

For the multi-step configuration fixes (e.g. prebuild removal, missing outputs), frame them as explicit validate -> fix -> re-check sequences so workflow_clarity can reach anchor 5.

Consider moving some of the more exhaustive anti-pattern code examples (e.g. the repetitive-task and globalDependencies blocks) into a reference file, keeping only the canonical pattern inline.

Dimension	Reasoning	Score
Conciseness	Dense and competence-assuming with no padding about basic concepts, but the body is long (~937 lines) and repeats the 'turbo run' vs 'turbo' shorthand rule across both the 'Secondary Rule' section and the 'Critical Anti-Patterns' section, so not every token earns its place (anchor 4 rather than 5).	4 / 5
Actionability	Pervasive copy-paste-ready JSON/YAML/bash examples and decision trees with exact commands and config keys (e.g. 'turbo run build --affected', dependsOn/outputs/env keys) covering build, lint, test, dev, CI, filtering, and env cases, matching anchor 5.	5 / 5
Workflow Clarity	Decision trees give clear sequenced routing and there are checklists (the 3-step 'before flagging missing outputs' check, the conditional prebuild fix), but there is no explicit validate -> fix -> retry feedback loop for the main workflows, placing it at anchor 4 rather than 5.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview with decision trees plus a comprehensive Reference Index table linking to one-level-deep references/<topic>/<file>.md files (all verified to exist), with content appropriately split and easy navigation, matching anchor 5.	5 / 5
	Total	18 / 20 Passed

Description

95%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 specific, comprehensive in trigger terms, and explicitly answers both what the skill does and when to use it in third-person voice. Only minor gap: the capability list reads as trigger areas rather than a discrete enumerated action set.

Dimension	Reasoning	Score
Specificity	Names the Turborepo domain plus many concrete capability areas and action-oriented 'when' clauses ('configures tasks/workflows/pipelines', 'creates packages', 'runs changed/affected packages', 'debugs cache'), landing at anchor 4 rather than 5 because the 'what' is framed more as trigger areas than a crisp enumerated action list.	4 / 5
Completeness	Explicitly answers both 'what' ('Turborepo monorepo build system guidance') and 'when' via a concrete 'Use when user: ...' clause with multiple trigger phrases, matching the anchor-5 example.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms, the config filename (turbo.json), CLI flags (--filter, --affected), concept names (dependsOn, remote cache, internal packages), and directory shapes (apps/packages), matching the anchor-5 example of coverage with file extensions and synonyms.	5 / 5
Distinctiveness Conflict Risk	Clearly scoped to Turborepo with distinct triggers (turbo.json, --affected, dependsOn) and minimal overlap with other skills, matching anchor 5.	5 / 5
	Total	19 / 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 (952 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 24 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 35 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: primer/react
Path: .github/skills/turborepo/SKILL.md
Commit: b111781

Reviewed: 1 day 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.