turborepo-monorepo

Configure pipelines, set up local/remote caching, and run scoped tasks in a Turborepo monorepo. Use when you say: 'enable remote caching', 'optimize pipeline inputs/outputs', or 'filter builds to affected packages'.

Quality

83%

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

88%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.

A highly actionable, well-organized reference: all commands are executable, the CI caching workflow is clearly sequenced with verification and an error-recovery feedback loop, and the section structure is easy to navigate. The only soft spots are minor token inefficiency (boilerplate workspace tree, management comment) and everything being inlined in one file rather than split into references.

Dimension	Reasoning	Score
Conciseness	The body is dominated by lean, commented command blocks and terse "Key Concepts" bullets, with only minor trims available: the boilerplate "Package Workspace Structure" tree Claude could infer and the OpenCastle managed-by HTML comment. Not 5 because those few tokens do not earn their place; not 3 because there is no concept re-explanation or padded prose.	4 / 5
Actionability	Every section is copy-paste ready: executable "turbo run" invocations with flags (--filter, --dry-run, --graph, --concurrency), a complete turbo.json example, and a concrete CI workflow with named secrets. This matches the fully-executable top anchor.	5 / 5
Workflow Clarity	"Quick Workflow: Setup remote caching in CI" gives a numbered 1-4 sequence with verification in step 2 ("Locally run turbo login and turbo link to verify the project is linked"), outcome observation in step 3 ("watch for cache hit/miss logs"), and an explicit feedback loop in step 4 ("If cache misses persist: verify inputs/outputs ..., then re-run"), plus a --dry-run validation callout. Not 4 because validation and error-recovery checkpoints are explicit, not merely implied.	5 / 5
Progressive Disclosure	Sections are clearly headed and easy to navigate (Commands, Pipeline Configuration, Caching, Workflow, Structure, Best Practices) with no buried or nested references. Not 5 because at ~130 lines with several distinct topic areas (command reference, config schema, caching setup, workspace layout) some content could be split into reference files, and none is.	4 / 5
	Total	18 / 20 Passed

Description

78%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.

A strong description with a clear what/when structure and natural quoted trigger phrases anchored to a specific tool. The main deductions are the second-person "Use when you say" voice (voice penalty on specificity) and missing common trigger variations such as "turbo" or "monorepo build".

Suggestions

Rewrite the trigger clause in third person (e.g. "Use when the user asks to enable remote caching, optimize pipeline inputs/outputs, or filter builds to affected packages") to remove the second-person voice penalty.

Add common trigger variations users would naturally say, such as "turbo", "monorepo builds", or "cache misses in CI", to broaden natural keyword coverage.

Mention configuring turbo.json or task dependencies explicitly in the capability list to close the minor coverage gaps in specificity.

Dimension	Reasoning	Score
Specificity	"Configure pipelines", "set up local/remote caching", and "run scoped tasks" list several concrete actions (base 4), but the second-person voice in "Use when you say: ..." triggers the rubric's -1 voice penalty, reducing this to 3. It is above level 2 because the domain (Turborepo) and multiple distinct actions are explicitly named, not generic.	3 / 5
Completeness	Clearly answers both: what ("Configure pipelines, set up local/remote caching, and run scoped tasks in a Turborepo monorepo") and when ("Use when you say: 'enable remote caching', 'optimize pipeline inputs/outputs', or 'filter builds to affected packages'") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Quoted phrases "enable remote caching", "optimize pipeline inputs/outputs", and "filter builds to affected packages" are natural user utterances with good coverage. Not 5 because common variations users would actually say are missing, e.g. "turbo", "monorepo build", "cache hit", or "turbo.json".	4 / 5
Distinctiveness Conflict Risk	"Turborepo monorepo" names a specific niche with mostly distinct triggers, but phrases like "enable remote caching" could independently match generic CI/caching skills, giving minor overlap risk. Not 3 because the tool is explicitly named and the trigger set is fairly distinctive.	4 / 5
	Total	16 / 20 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: monkilabs/opencastle
Path: src/orchestrator/plugins/turborepo/SKILL.md
Commit: c0f4566

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.