link-workspace-packages
Link workspace packages in monorepos (npm, yarn, bun). USE WHEN: (1) you just created or generated new packages and need to wire up their dependencies, (2) user imports from a sibling package and needs to add it as a dependency, (3) you get resolution errors for workspace packages (@org/*) like "cannot find module", "failed to resolve import", "TS2307", or "cannot resolve". DO NOT patch around with tsconfig paths or manual package.json edits - use the package manager's workspace commands to fix actual linking.
76
93%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines its scope (monorepo workspace package linking), provides explicit trigger conditions with real error messages users would encounter, and even includes anti-patterns to prevent misuse. The description is concise yet comprehensive, covering the what, when, and when-not dimensions effectively.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists concrete actions: linking workspace packages in monorepos, wiring up dependencies for new packages, adding sibling packages as dependencies, and fixing resolution errors. Also specifies what NOT to do (tsconfig paths, manual edits). | 3 / 3 |
Completeness | Clearly answers both 'what' (link workspace packages in monorepos using package manager workspace commands) and 'when' with an explicit 'USE WHEN' clause listing three specific trigger scenarios, plus a 'DO NOT' anti-pattern clause. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would encounter: 'npm', 'yarn', 'bun', 'monorepo', '@org/*', 'cannot find module', 'failed to resolve import', 'TS2307', 'cannot resolve', 'workspace packages', 'sibling package'. These are exactly the error messages and terms users would mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on monorepo workspace package linking. The specific error codes (TS2307), package patterns (@org/*), and explicit anti-patterns (not tsconfig paths) clearly distinguish it from general dependency management or TypeScript configuration skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%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, concise skill that provides clear, executable commands for all three major package managers with expected outputs. Its main weakness is the lack of explicit verification commands and error recovery steps in the workflow—telling Claude to 'verify symlinks' without showing how, and the debug section could include a more structured feedback loop. Overall it's a strong, practical skill.
Suggestions
Add an explicit verification command in the workflow (e.g., `ls -la packages/app/node_modules/@org/ui` or `node -e "require.resolve('@org/ui')"`) to make step 4 actionable and close the validation gap.
Expand the debug example with a feedback loop: after adding the dependency and running install, verify resolution succeeds, and if not, suggest clearing caches (`npm cache clean`, `yarn cache clean`, `rm -rf node_modules && bun install`).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what monorepos or workspaces are, assumes Claude knows package managers, and every section delivers actionable information without padding. The brief notes at the end are all genuinely useful context. | 3 / 3 |
Actionability | Provides fully executable, copy-paste-ready commands for all three package managers with concrete examples showing exact syntax and expected package.json output. The multi-package example and debug steps are specific and actionable. | 3 / 3 |
Workflow Clarity | The 4-step workflow is listed clearly, and step 4 mentions verifying symlinks, but there's no explicit validation command or feedback loop for error recovery. For example, it doesn't specify how to verify symlinks were created or what to do if they weren't. The debug example is helpful but lacks a retry/validation checkpoint. | 2 / 3 |
Progressive Disclosure | For a skill of this scope and size (under 80 lines, single focused task), the content is well-organized with clear sections per package manager, a detection guide, workflow overview, and examples. No bundle files are needed, and the structure supports easy scanning. | 3 / 3 |
Total | 11 / 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.