monorepo

Monorepo scripts, package boilerplate, conventions. Use when: "how do I run", "bun run", "build this", "run tests", "typecheck", "create a new package", linting, scaffolding packages.

Quality

81%

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

82%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 strong, information-dense skill body: every section delivers repo-specific conventions Claude could not infer, with executable commands and complete boilerplate blocks. Its only real weakness is mild verbosity in the Dev Scripts section and the absence of explicit error-recovery steps in its workflows.

Dimension	Reasoning	Score
Conciseness	The body is dense with repo-specific, non-obvious knowledge (script naming conventions, dev script semantics, license rules) and explains nothing Claude already knows; a few Dev Scripts sentences could still be tightened, keeping it just below anchor 5.	4 / 5
Actionability	Guidance is fully executable: exact commands (`bun typecheck`, `bun install`), copy-paste-ready package.json and tsconfig.json blocks, and a precise command table with purposes and usage context.	5 / 5
Workflow Clarity	The after-code-changes flow has an explicit validation step (`bun typecheck`), and package creation is sequenced through boilerplate files ending in `bun install`, with a safety flag on `db:*:remote` ("Production data; treat as admin"); minor gaps remain (no error-recovery loop, no explicit lint/test ordering after changes).	4 / 5
Progressive Disclosure	The body is well-sectioned with no bundle files to organize, and detail is appropriately deferred via clearly signaled one-level references (the tsconfig skill, docs/licensing/licensing-strategy.md, app READMEs, `bun run check:licenses`); navigation is easy with only minor gaps, such as README references given without paths.	4 / 5
	Total	17 / 20 Passed

Description

70%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 solid description with an explicit and natural trigger list that clearly signals when to use the skill. The main weakness is the 'what' half: it enumerates topics as noun phrases rather than stating concrete actions, which costs specificity and keeps completeness just below the top anchor.

Suggestions

Rewrite the 'what' clause with concrete verb-led actions, e.g. 'Run monorepo scripts (format, lint, typecheck, test, bench), scaffold new packages with boilerplate package.json/tsconfig.json, and follow workspace conventions.'

Add a few missing natural trigger terms such as 'format this', 'benchmark', or 'start the dev server' to round out trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and deliverables ("Monorepo scripts, package boilerplate, conventions") but as noun phrases rather than the concrete, verb-stated actions the anchors reward; it conveys only 1-2 implied actions and is not comprehensive.	3 / 5
Completeness	Both 'what' ("Monorepo scripts, package boilerplate, conventions") and an explicit 'Use when' clause with concrete trigger phrases are present; the 'what' is explicit but terse, so it sits between anchors 4 and 5 rather than clearly matching 5.	4 / 5
Trigger Term Quality	Triggers like "how do I run", "bun run", "run tests", "typecheck", "create a new package" are natural phrases users would actually say, with good variation; a few natural terms are missing (e.g. formatting, benchmarks, dev server startup).	4 / 5
Distinctiveness Conflict Risk	Triggers like "bun run" and "create a new package" are specific to this monorepo workflow, keeping conflict risk low; minor overlap remains with closely related repo skills such as the referenced tsconfig skill.	4 / 5
	Total	15 / 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: EpicenterHQ/epicenter
Path: .agents/skills/monorepo/SKILL.md
Commit: f9441c8

Reviewed: 3 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.