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.
86
81%
Does it follow best practices?
Impact
95%
1.25xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description with excellent trigger term coverage and clear 'when to use' guidance. Its main weakness is that the 'what it does' portion is somewhat abstract ('guidance') rather than listing concrete actions the skill performs. The extensive trigger terms and explicit use-when clause make it highly functional for skill selection despite this.
Suggestions
Replace the vague 'guidance' with specific concrete actions, e.g., 'Configures turbo.json task pipelines, optimizes caching strategies, sets up remote cache, structures internal packages, and debugs build issues in Turborepo monorepos.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Turborepo monorepo build system) and mentions several relevant concepts (task pipelines, caching, remote cache, CI optimization), but it reads more like a list of trigger topics than concrete actions the skill performs. It doesn't clearly list specific actions like 'configure turbo.json pipelines' or 'debug cache misses'. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (Turborepo monorepo build system guidance) and 'when' with a clear 'Use when user:' clause listing multiple specific trigger scenarios like configuring tasks, creating packages, debugging cache, and working with apps/packages directories. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'turbo.json', 'dependsOn', 'remote cache', '--filter', '--affected', 'monorepo', 'apps/packages directories', 'CI optimization', 'internal packages'. These are highly specific terms a user working with Turborepo would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with Turborepo-specific terms like 'turbo.json', 'dependsOn', '--filter', '--affected', and 'turbo CLI'. These are unique to Turborepo and unlikely to conflict with other monorepo tools (Nx, Lerna) or general build system skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive, well-structured Turborepo skill with excellent actionability through concrete JSON examples and clear progressive disclosure via decision trees and a reference index. The main weaknesses are verbosity (some anti-pattern explanations could be tighter) and missing validation/verification steps in workflows — there's no guidance on confirming that configuration changes produce the expected caching or parallelization behavior.
Suggestions
Add validation checkpoints to key workflows, e.g., 'After configuring outputs, run `turbo run build --summarize` to verify hash inputs include expected files' or 'Use `--dry` to confirm task execution order matches expectations'.
Tighten the root .env anti-pattern section — the 4 bullet points explaining problems are verbose and could be reduced to 1-2 sentences since Claude can infer security and coupling implications.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long with extensive anti-pattern examples that include both WRONG and CORRECT versions, which is valuable but verbose. Some sections like the root .env anti-pattern explanation include rationale bullets that Claude could infer. However, most content is Turborepo-specific knowledge Claude wouldn't inherently know, and the JSON examples are necessary for clarity. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready JSON configurations throughout. Every anti-pattern has a concrete WRONG and CORRECT example with real turbo.json, package.json, and CLI commands. Decision trees map specific scenarios to concrete actions or reference files. | 3 / 3 |
Workflow Clarity | The decision trees provide clear routing for common scenarios, and the task configuration section shows sequenced patterns. However, there are no explicit validation checkpoints or feedback loops — for example, no guidance on verifying cache correctness after configuration changes (e.g., 'run --summarize to verify hash inputs'), and the prebuild migration steps lack explicit verification. | 2 / 3 |
Progressive Disclosure | The skill has an excellent structure: core rules and anti-patterns inline, with a comprehensive Reference Index table pointing to one-level-deep reference files organized by topic (configuration, caching, environment, filtering, CI, CLI, best practices, watch, boundaries). Decision trees also link directly to specific reference files. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 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 |
Total | 10 / 11 Passed | |
- Repository
- vercel/turborepo
- Commit
09900b9
- 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.