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), lists concrete actions, includes an explicit 'Use when' clause with relevant trigger terms, and occupies a distinct enough domain to avoid conflicts. The description is concise yet comprehensive, covering both source types (npm registry, GitHub) and build strategies (pre-built, source builds).
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: packaging CLI tools, creating Nix derivations, handling pre-built packages, source builds, and dependency management. Specifies the domain clearly (npm/TypeScript/Bun CLI tools for Nix). | 3 / 3 |
Completeness | Clearly answers both 'what' (package npm/TypeScript/Bun CLI tools for Nix, creating derivations, handling pre-built or source builds with dependency management) and 'when' (explicit 'Use when' clause specifying creating Nix derivations for JS/TS tools from npm registry or GitHub sources). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'npm', 'TypeScript', 'Bun', 'CLI tools', 'Nix', 'Nix derivations', 'JavaScript', 'npm registry', 'GitHub sources', 'pre-built packages', 'source builds', 'dependency management'. Good coverage of variations across the JS/Nix ecosystem. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche at the intersection of Nix packaging and JavaScript/TypeScript CLI tools. 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 solid, highly actionable skill with complete executable examples and a well-structured workflow including validation checkpoints. Its main weakness is length—at ~300 lines with no external references, it could benefit from splitting detailed troubleshooting, anti-patterns, and special cases into separate files. Some sections are mildly verbose or redundant (success_criteria vs build_checklist, explanatory comments Claude doesn't need).
Suggestions
Extract troubleshooting, anti-patterns, and special cases into separate referenced files (e.g., TROUBLESHOOTING.md, PATTERNS.md) to reduce the main skill's token footprint.
Remove the objective section and success_criteria section—the former restates the description, and the latter largely duplicates the build checklist.
Trim explanatory comments like 'This affects security auditing and reproducibility expectations' and 'Stripping would remove the embedded JS, breaking the program'—Claude already understands these implications.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some unnecessary verbosity—e.g., the objective section restates what the skill title already conveys, the success_criteria section largely repeats the build checklist, and some explanations (like what sourceProvenance means, what autoPatchelf does) could be trimmed since Claude knows Nix packaging concepts. The anti-patterns section, while useful, includes obvious items with verbose good/bad comparisons. | 2 / 3 |
Actionability | Excellent actionability throughout. Both the pre-built and source-build patterns provide complete, copy-paste-ready Nix derivations with real structure. Hash fetching commands, directory creation, build/test commands are all concrete and executable. The troubleshooting section provides specific error messages with concrete solutions. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced across 5 steps (identify package type → fetch hashes → create files → handle special cases → test build). Validation is explicit with a comprehensive build checklist, the hash iteration feedback loop is documented, and the lockfile verification step (`diff -q`) provides an in-build validation checkpoint. The troubleshooting section adds error recovery guidance. | 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 ~300-line file with no references to external files. The special cases, troubleshooting, and anti-patterns sections could be split into separate reference files to keep the main skill leaner. No bundle files are provided to offload detail. | 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
d2b7dff
- 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.