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.
87
83%
Does it follow best practices?
Impact
95%
1.14xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
67%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 has a solid structure with an explicit 'USE WHEN' clause and names the Nx workspace domain clearly. However, it leans on generic task verbs (build, test, lint, serve) that could overlap with other development skills, and the opening 'Helps with' phrasing is vague rather than action-oriented. Adding more Nx-specific terminology and concrete capabilities would strengthen both specificity and distinctiveness.
Suggestions
Replace 'Helps with running tasks' with more specific actions like 'Executes and configures Nx workspace targets, manages task pipelines, and runs affected commands'.
Add Nx-specific trigger terms such as 'nx run', 'nx affected', 'monorepo', 'project.json', 'targets', or 'nx graph' to improve trigger term coverage and distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Nx workspace) and lists some actions (build, test, lint, serve, run tasks), but 'Helps with running tasks' is somewhat vague and the actions listed are generic task types rather than specific concrete capabilities like 'configure task pipelines' or 'resolve dependency graphs'. | 2 / 3 |
Completeness | Clearly answers both 'what' (running tasks in an Nx workspace) and 'when' (explicit 'USE WHEN' clause specifying build, test, lint, serve, or any other workspace tasks). The trigger guidance is explicit and actionable. | 3 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Nx workspace', 'build', 'test', 'lint', 'serve', and 'tasks', which users would naturally say. However, it misses common variations like 'nx run', 'nx affected', 'monorepo', 'project targets', or specific file references like 'project.json'. | 2 / 3 |
Distinctiveness Conflict Risk | The Nx workspace context provides some distinctiveness, but terms like 'build', 'test', 'lint', and 'serve' are very common across many development tools and could overlap with generic CI/CD, testing, or build skills. The 'Nx' qualifier helps but the broad 'any other tasks' phrasing weakens distinctiveness. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that efficiently covers the key Nx task-running workflows. It's concise, actionable with real commands and examples, logically structured from simple to complex use cases, and appropriately scoped. The inclusion of the discovery command (`nx show project`) and the note about package manager prefixing add genuine value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It assumes Claude knows what Nx is, what package managers are, and how CLI tools work. The brief note about prefixing with npx/pnpx/yarn is genuinely useful context. Every section earns its place. | 3 / 3 |
Actionability | Provides concrete, copy-paste ready commands throughout: `nx run <project>:<task>`, `nx run-many -t build test lint`, `nx affected -t build test lint`, with multiple real-world examples showing flag combinations. The `nx show project <projectname> --json` discovery command is particularly actionable. | 3 / 3 |
Workflow Clarity | The skill follows a clear logical sequence: discover available tasks → run single task → run multiple tasks → run affected tasks → useful flags. For a non-destructive task-running skill, this progression is appropriate and no validation checkpoints are needed since these are read-only or standard build operations with their own error output. | 3 / 3 |
Progressive Disclosure | For a skill of this scope and size (~50 lines), the content is well-organized into clear sections without being monolithic. It appropriately points to `--help` for deeper details rather than inlining all flag documentation. No bundle files are needed for this self-contained reference. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- leboncoin/spark-web
- Commit
76a3678
- 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.