nx-run-tasks

Helps with running tasks in an Nx workspace. USE WHEN the user wants to execute build, test, lint, serve, or run any other tasks defined in the workspace.

1.14x

Quality

88%

Does it follow best practices?

Impact

95%

1.14x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

The canonical home for this skill is nx-run-tasks in nrwl/nx

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable command reference with excellent conciseness and organization. The main gap is the absence of validation/verification guidance for the batch run-many and affected operations, which caps workflow clarity.

Suggestions

Add a brief verification checkpoint for batch operations, e.g. recommending `nx run-many -t build --skipNxCache` in CI or checking the affected set with `nx show projects --affected` before running, to satisfy the validation-guidance the rubric expects for batch workflows.

Note how to interpret a failed task run (e.g. reading `--verbose` stack traces and re-running the single failing target with `nx run <project>:<task>`) to give an explicit error-recovery feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude knows what Nx is, jumping straight to executable commands with only minimal, useful framing (e.g. "This is especially useful in CI and for large workspaces"). Every line earns its place; not a 2 because there is no padded concept explanation to trim.	3 / 3
Actionability	It provides fully executable commands ("nx run <project>:<task>", "nx run-many -t build test lint typecheck") plus concrete copy-paste examples with specific flags and project patterns. Not a 2 because the examples are complete and runnable rather than pseudocode.	3 / 3
Workflow Clarity	Commands are well-organized by scenario, but the batch operations "nx run-many" and "nx affected" include no validation or verification checkpoints, which per the rubric caps workflow clarity at 2. Not a 3 because of those missing feedback loops; not a 1 because the sequencing and flags are clearly laid out.	2 / 3
Progressive Disclosure	Under 50 lines with no external references needed, organized into clear sections (Understand tasks, Run single, Run multiple, Affected, Useful flags) for easy navigation. Per the rubric, a sub-50-line skill with no need for external references can score 3 with well-organized sections.	3 / 3
	Total	11 / 12 Passed

Description

90%

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, third-person description with an explicit USE WHEN trigger and concrete task verbs. Its only weakness is the generic "any other tasks" catch-all that keeps specificity from the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain (Nx workspace) and several concrete actions ("build, test, lint, serve"), but pads with the generic clause "or run any other tasks defined in the workspace", so it is not a comprehensive list of specific actions. Not a 3 because of that vague catch-all; not a 1 because multiple real task types are named.	2 / 3
Completeness	It explicitly answers both what ("running tasks in an Nx workspace") and when ("USE WHEN the user wants to execute build, test, lint, serve") with an explicit trigger clause. Not a 2 because the trigger is explicit rather than merely implied.	3 / 3
Trigger Term Quality	"execute build, test, lint, serve" are exactly the natural terms a user would say when needing this skill, giving good coverage of common phrasings. Not a 2 because it goes well beyond a single keyword to several user-natural terms.	3 / 3
Distinctiveness Conflict Risk	Scoping to an "Nx workspace" with task-execution triggers carves a clear niche unlikely to fire for unrelated skills. Not a 2 because the Nx-specific framing and concrete task verbs make overlap unlikely.	3 / 3
	Total	11 / 12 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: leboncoin/spark-web
Path: .cursor/skills/nx-run-tasks/SKILL.md
Commit: 9f4792e

Reviewed: 5 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.