CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

nx-workspace

Explore and understand Nx workspaces. USE WHEN answering questions about the workspace, projects, or tasks. ALSO USE WHEN an nx command fails or you need to check available targets/configuration before running a task. EXAMPLES: 'What projects are in this workspace?', 'How is project X configured?', 'What depends on library Y?', 'What targets can I run?', 'Cannot find configuration for task', 'debug nx task failure'.

68

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is nx-workspace in whimzyLive/nightshift-ai

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 with executable commands for every common Nx exploration question and a properly linked reference file. Its weaknesses are redundant sections that repeat the same jq recipes and a long body that could offload more detail to reference files.

Suggestions

Merge 'Common Exploration Patterns' and 'Programmatic Answers' into the earlier sections (or drop 'Common Exploration Patterns' entirely) to eliminate the repeated `nx show project X --json | jq '.targets | keys'` and listing-projects recipes.

Move the detailed filter syntax catalog and the example JSON outputs for `nx graph --print` into a reference file (e.g. references/FILTERS.md), keeping SKILL.md as a lean overview like the AFFECTED.md pattern already used.

In the duplicated schema pointers, vary the wording or combine them into one note so the identical 'You can read the full project schema at node_modules/nx/schemas/...' sentences don't read as padding.

DimensionReasoningScore

Conciseness

Every snippet is a lean executable command with no concept-explanation fluff, but there is noticeable duplication: `jq '.targets | keys'` and related recipes appear in 'Target Information', 'Common Exploration Patterns', and 'Programmatic Answers', and 'Common Exploration Patterns' largely restates 'Listing Projects' and 'Target Information'. Mostly efficient but could be tightened by merging the redundant sections.

3 / 5

Actionability

Fully executable copy-paste-ready commands throughout — listing/filtering, `nx show project --json` with jq extraction recipes, `nx graph --print`, and troubleshooting commands — with example JSON outputs that cover the common cases.

5 / 5

Workflow Clarity

This is a single-purpose read-only exploration skill with unambiguous per-question commands, so the simple-skill exception applies; there are no destructive or batch operations requiring validation, and the Troubleshooting section provides an error-to-recovery flow (check targets, `nx sync`, `nx reset`).

5 / 5

Progressive Disclosure

Good structure with a real, well-signaled, one-level-deep reference (references/AFFECTED.md linked from the Affected Projects section), but the ~280-line body inlines substantial detail (full filter syntax catalog, programmatic answer recipes, example JSON) that could be split into reference files, which is a minor organization gap rather than fully appropriate splitting.

4 / 5

Total

17

/

20

Passed

Description

86%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 explicit USE WHEN triggers, natural example phrasings, and error-message triggers that make it highly discoverable. Its main weakness is that the 'what' relies on generic verbs ('explore and understand') rather than naming the specific capabilities it provides.

Suggestions

Replace the generic 'Explore and understand Nx workspaces' with the concrete capabilities, e.g. 'List Nx projects, inspect resolved project configuration and targets, and query the project dependency graph.'

Include 'monorepo' as a trigger synonym, since Nx users commonly ask 'what's in this monorepo?' or 'which projects are affected?'

DimensionReasoningScore

Specificity

"Explore and understand Nx workspaces" names the domain but the actions are generic; concrete capabilities like listing projects or inspecting configuration appear only indirectly through example questions, matching the anchor for domain plus 1-2 concrete actions rather than a list of several specific actions.

3 / 5

Completeness

Both what ("Explore and understand Nx workspaces") and when are explicitly and clearly answered via 'USE WHEN ... ALSO USE WHEN ...' with concrete trigger phrases and example questions, matching the top anchor.

5 / 5

Trigger Term Quality

The description covers natural user phrasings comprehensively: 'What projects are in this workspace?', 'How is project X configured?', 'What depends on library Y?', 'What targets can I run?', 'Cannot find configuration for task', 'debug nx task failure', plus 'nx command fails' — users would naturally say these exact things.

5 / 5

Distinctiveness Conflict Risk

The Nx branding and nx-specific triggers (nx command fails, targets, 'Cannot find configuration for task') give it a clear niche, but 'answering questions about the workspace, projects, or tasks' is slightly broad, leaving minor overlap risk with generic workspace/monorepo questions — mostly distinct rather than minimal conflict risk.

4 / 5

Total

17

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

whimzyLive/nightshift-ai

Path

.github/skills/nx-workspace/SKILL.md

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.