pnpm
Node.js package manager with strict dependency resolution. Use when running pnpm specific commands, configuring workspaces, or managing dependencies with catalogs, patches, or overrides.
77
66%
Does it follow best practices?
Impact
96%
1.14xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/pnpm/SKILL.mdQuality
Discovery
89%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 a solid skill description that clearly identifies its niche (pnpm specifically, not generic package management) and provides explicit trigger guidance. The main weakness is that it focuses more on features/concepts than concrete actions a user might request. Adding specific verbs like 'install', 'add', 'update' would strengthen the specificity.
Suggestions
Add concrete action verbs like 'install packages', 'add dependencies', 'configure monorepos' to improve specificity
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Node.js package manager) and mentions some specific features (workspaces, catalogs, patches, overrides), but doesn't list concrete actions like 'install packages', 'update dependencies', or 'run scripts'. | 2 / 3 |
Completeness | Clearly answers both what (Node.js package manager with strict dependency resolution) and when (Use when running pnpm specific commands, configuring workspaces, or managing dependencies with specific features). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'pnpm', 'workspaces', 'dependencies', 'catalogs', 'patches', 'overrides'. These are terms developers naturally use when working with pnpm. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly distinguishes itself from npm/yarn by explicitly naming 'pnpm' and pnpm-specific features like 'catalogs' and 'strict dependency resolution'. Unlikely to conflict with other package manager skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels at progressive disclosure with a well-organized reference structure, but fails to provide actionable quick-start content. The main body is essentially a table of contents with explanatory text that Claude doesn't need, lacking any executable examples or concrete commands that would make it immediately useful.
Suggestions
Add a 'Quick start' section with 3-5 executable pnpm commands (e.g., `pnpm install`, `pnpm add -D`, `pnpm --filter`) before the reference tables
Remove the explanatory paragraph about what pnpm is and how content-addressable storage works - Claude knows this
Add a concrete workflow example for a common task like 'Adding a dependency to a workspace package' with actual commands and validation steps
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The intro paragraph explains what pnpm is and how it works (content-addressable store, deduplication), which Claude already knows. The version note and general description add tokens without actionable value. | 2 / 3 |
Actionability | No executable code or concrete commands are provided in the main skill body. Everything is deferred to reference files with only abstract descriptions of what each topic covers. | 1 / 3 |
Workflow Clarity | The 'Important' note mentions checking config files and using --frozen-lockfile in CI, but there's no sequenced workflow, validation steps, or concrete process to follow for common pnpm operations. | 2 / 3 |
Progressive Disclosure | Excellent structure with clear categorization (Core, Features, Best Practices), well-organized tables, and one-level-deep references to specific topic files. Navigation is straightforward. | 3 / 3 |
Total | 8 / 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
- antfu/skills
- Commit
c35a558
- 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.