CtrlK
BlogDocsLog inGet started
Tessl Logo

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'.

86

1.40x
Quality

86%

Does it follow best practices?

Impact

90%

1.40x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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-structured read-only exploration guide: nearly all content is executable commands, one cleanly signaled reference file, and useful question-to-command patterns. Its main cost is redundancy — repeated jq examples and a 'Programmatic Answers' section that restates earlier material inflate the token budget without adding new capability.

Suggestions

Consolidate the repeated '.targets | keys' / '.targets.build' jq examples into a single section and reference it from the others.

Move the example JSON outputs and repeated commands in 'Programmatic Answers' into a reference file (e.g. references/EXAMPLES.md) or trim them to only the operations not already shown.

Add a short ordering note (e.g. 'check nx.json targetDefaults when a target exists but fails') to tighten the Troubleshooting feedback loop.

DimensionReasoningScore

Conciseness

The body is mostly lean command blocks with no conceptual padding, but jq examples repeat across sections ('.targets | keys' appears in Project Configuration, Target Information, Programmatic Answers, and Troubleshooting) and the 'Programmatic Answers' section largely restates earlier commands. This is more than minor trimming, so it sits at anchor 3 rather than 4.

3 / 5

Actionability

Every example is a copy-paste-ready executable command with realistic jq pipelines, covering the common exploration cases (list, filter, inspect targets, graph queries, troubleshooting). The guidance is fully executable.

5 / 5

Workflow Clarity

'Common Exploration Patterns' cleanly maps user questions to command sequences and Troubleshooting pairs errors with fixes including a fallback ('nx reset' if sync doesn't help). As a read-only skill no destructive-validation cap applies, but there are minor gaps (no ordering guidance or general error-handling loop beyond the two troubleshooting entries), so anchor 4 rather than 5.

4 / 5

Progressive Disclosure

Sections are well organized and the single reference (references/AFFECTED.md) is clearly signaled and exactly one level deep. The inline 'Programmatic Answers' section (example outputs plus repeated commands) is content that could live in a reference file or be trimmed, keeping this at anchor 4 rather than 5.

4 / 5

Total

16

/

20

Passed

Description

90%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, multi-clause trigger guidance and natural example queries that clearly delimit when to use the skill. The main weakness is a thin 'what' statement that undersells the concrete capabilities (listing projects, inspecting targets/config, dependency queries) the body actually delivers.

Suggestions

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

Mention the affected-projects capability in the description since it is a dedicated reference in the skill bundle.

DimensionReasoningScore

Specificity

The 'what' is mostly generic ('Explore and understand Nx workspaces'), but 'check available targets/configuration' names a concrete action. It stops short of listing the several specific capabilities (listing projects, dependency graphs, target inspection) the skill actually provides, so it matches anchor 3 rather than 4.

3 / 5

Completeness

Both 'what' ('Explore and understand Nx workspaces') and explicit 'when' ('USE WHEN...', 'ALSO USE WHEN...') are present, with concrete EXAMPLES trigger phrases. The when clauses are maximally explicit, matching the anchor-5 example pattern.

5 / 5

Trigger Term Quality

Natural user phrases are comprehensively covered: 'What projects are in this workspace?', 'How is project X configured?', 'What targets can I run?', 'nx command fails', 'debug nx task failure'. These mirror what a user would actually say, including failure-mode triggers.

5 / 5

Distinctiveness Conflict Risk

'Nx workspaces' is a clear, tool-specific niche with distinct triggers ('nx command fails', 'Cannot find configuration for task') that would not fire for unrelated skills, so conflict risk is minimal.

5 / 5

Total

18

/

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
leboncoin/spark-web
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.