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, well-crafted description that clearly identifies a specific niche (Nix packaging for JS/TS CLI tools), lists concrete actions, and includes an explicit 'Use when' clause with natural trigger terms. It covers multiple relevant ecosystems and source types, making it easy for Claude to select this skill precisely when needed.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: packaging CLI tools, creating Nix derivations, handling pre-built packages, source builds, and dependency management. Covers specific ecosystems (npm, TypeScript, Bun) and sources (npm registry, GitHub). | 3 / 3 |
Completeness | Clearly answers both 'what' (package npm/TypeScript/Bun CLI tools for Nix, handling pre-built packages or source builds with dependency management) and 'when' (explicit 'Use when creating Nix derivations for JavaScript/TypeScript 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', 'npm registry', 'GitHub sources', 'pre-built packages', 'dependency management'. Good coverage of terms a user packaging JS tools for Nix would naturally use. | 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 npm 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 templates and a well-sequenced workflow including validation steps. Its main weakness is length—the document tries to be both a quick-start guide and a comprehensive reference, resulting in a monolithic file that could benefit from splitting detailed troubleshooting and patterns into separate referenced files. Some explanatory text (why stripping breaks Bun, what sourceProvenance means) could be trimmed since Claude can infer these.
Suggestions
Move troubleshooting, anti-patterns, and special cases sections into a separate REFERENCE.md file, keeping only the quick_start and workflow in SKILL.md with links to the reference
Remove explanatory comments that Claude can infer, such as why stripping breaks Bun binaries, what sourceProvenance affects, and the success_criteria section which duplicates the build checklist
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some unnecessary explanations (e.g., explaining what sourceProvenance means for security auditing, explaining why stripping breaks Bun binaries, the success_criteria section restating what's already in the checklist). The anti-patterns section with ❌/✅ pairs is somewhat verbose for things Claude would know. However, most content is substantive and pattern-specific. | 2 / 3 |
Actionability | Excellent actionability with fully executable Nix derivation templates, concrete bash commands for hash fetching, complete package.nix examples for both pre-built and source-build approaches, and specific commands for testing. The code is copy-paste ready with clear placeholder values. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced across 5 steps with explicit validation checkpoints: step 2 includes hash iteration feedback loop, step 5 includes build testing and ldd verification, and the build checklist provides comprehensive validation. The lockfile diff check in the build phase is an explicit verification step for dependency integrity. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections (quick_start, workflow, common_patterns, troubleshooting, validation), but it's a monolithic document that could benefit from splitting detailed reference material (troubleshooting, anti-patterns, special cases) into separate files. At ~300+ lines, the inline content is heavy for a SKILL.md overview. | 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
aed1afb
- 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.