r-testing
R package testing with testthat 3rd edition. Use when writing R tests, fixing failing tests, debugging errors, or reviewing coverage—e.g., "write testthat tests", "fix failing R tests", "snapshot testing", "test coverage".
95
95%
Does it follow best practices?
Impact
93%
1.25xAverage score across 3 eval scenarios
Passed
No known issues
Quality
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 strong skill description that excels in trigger term quality, completeness, and distinctiveness. It clearly identifies the specific technology (testthat 3rd edition for R) and provides explicit usage triggers. The main weakness is that the capability description could be more specific about concrete actions beyond the general categories of writing, fixing, debugging, and reviewing.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (R package testing with testthat) and mentions some actions (writing tests, fixing tests, debugging errors, reviewing coverage), but doesn't list comprehensive concrete actions like 'create test fixtures', 'mock functions', or 'generate test reports'. | 2 / 3 |
Completeness | Clearly answers both what (R package testing with testthat 3rd edition) and when (writing R tests, fixing failing tests, debugging errors, reviewing coverage) with explicit 'Use when' clause and concrete example trigger phrases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'write testthat tests', 'fix failing R tests', 'snapshot testing', 'test coverage', plus implicit triggers like 'R tests' and 'testthat'. These are phrases users would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: specifically R language, testthat framework, 3rd edition. The trigger terms like 'testthat', 'R tests', and 'snapshot testing' are unlikely to conflict with other testing skills for different languages or frameworks. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exemplary skill file that demonstrates best practices across all dimensions. It provides comprehensive, actionable guidance for R testing while maintaining excellent token efficiency through assumed competence. The strong emphasis on non-negotiable practices (withr cleanup, test_path usage, snapshot review) with clear consequences ('= leaked state. Every time.') makes critical requirements unmistakable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, assuming Claude's R competence. It avoids explaining basic concepts (what testthat is, what testing means) and jumps directly into actionable patterns with minimal preamble. | 3 / 3 |
Actionability | Provides fully executable R code throughout—setup commands, test patterns, withr usage, fixture creation, and common patterns are all copy-paste ready with real function calls and complete examples. | 3 / 3 |
Workflow Clarity | Clear three-scale testing workflow (micro/mezzo/macro), explicit snapshot review workflow with validation checkpoint ('IMMEDIATELY after creating snapshots'), and strong emphasis on cleanup discipline with withr patterns. | 3 / 3 |
Progressive Disclosure | Excellent structure with core content in main file and clear one-level-deep references to specialized topics (advanced.md, bdd.md, snapshots.md, fixtures.md). Each reference includes when to load it. | 3 / 3 |
Total | 12 / 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
- jjjermiah/dotagents
- Commit
b74de5e
- 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.