package-npm-nix
Package npm/TypeScript/Bun CLI tools for Nix. Use when creating Nix derivations for JavaScript/TypeScript tools from npm registry or GitHub sources, handling pre-built packages or source builds with dependency management.
92
88%
Does it follow best practices?
Impact
100%
1.63xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
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 a strong skill description that clearly defines a specific niche (Nix packaging for JS/TS CLI tools), includes rich trigger terms spanning both the Nix and JavaScript ecosystems, and provides explicit 'Use when' guidance. It uses proper third-person voice and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: packaging CLI tools, creating Nix derivations, handling pre-built packages, source builds, and dependency management. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Package npm/TypeScript/Bun CLI tools for Nix') and when ('Use when creating Nix derivations for JavaScript/TypeScript tools from npm registry or GitHub sources, handling pre-built packages or source builds with dependency management'). Has an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'npm', 'TypeScript', 'Bun', 'Nix', 'Nix derivations', 'npm registry', 'GitHub sources', 'JavaScript', 'CLI tools', 'pre-built packages', 'source builds', 'dependency management'. Good coverage of terms across the JS/Nix ecosystem. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche at the intersection of Nix packaging and JavaScript/TypeScript tooling. The combination of Nix + npm/TypeScript/Bun is very specific and unlikely to conflict with general Nix skills or general JavaScript skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with complete executable examples for both pre-built and source-build npm packaging in Nix. The workflow is well-sequenced with proper validation steps and a comprehensive build checklist. The main weaknesses are moderate verbosity (some redundant sections and explanations of concepts Claude already knows) and the monolithic structure that could benefit from splitting detailed reference material into separate files.
Suggestions
Remove the objective and success_criteria sections as they largely duplicate the skill description and validation checklist respectively, saving ~20 lines of redundant content.
Split troubleshooting, anti-patterns, and metadata requirements into separate reference files (e.g., TROUBLESHOOTING.md, REFERENCE.md) and link from the main skill to improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some unnecessary verbosity. The objective section restates what the description already covers, the success_criteria section largely repeats the validation checklist, and some explanations (e.g., what sourceProvenance means, why stripping breaks Bun binaries) are things Claude would already know. However, the code examples themselves are lean and well-structured. | 2 / 3 |
Actionability | Excellent actionability throughout. Both the pre-built and source-build patterns provide complete, copy-paste-ready Nix derivations with real commands for hash fetching, building, and testing. The special cases section provides concrete code for WASM files, multiple executables, and native dependencies. The troubleshooting section pairs specific error messages with concrete solutions. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced from identifying package type through fetching hashes, creating files, handling special cases, and testing. The build checklist provides explicit validation checkpoints. The hash iteration process (use fakeHash → build → get error → update) is a clear feedback loop. The lockfile verification step (`diff -q`) in the build phase adds an explicit validation checkpoint for source builds. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections (quick_start, workflow, common_patterns, anti_patterns, troubleshooting, validation), but it's a monolithic document of ~300+ lines. Some sections like the detailed troubleshooting, anti-patterns, and metadata requirements could be split into separate reference files. No bundle files are provided, so there's no progressive disclosure to external references despite the content length warranting it. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (591 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- YPares/agent-skills
- Commit
84b1da5
- 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.