Automatically updates regression tests based on interval analysis to maintain coverage of key program intervals. Use when code changes affect value ranges, conditionals, or control flow, and existing tests need updating to maintain interval coverage. Analyzes interval information from updated code, identifies coverage gaps, adjusts test inputs and assertions, removes redundant tests, and generates new tests for uncovered intervals. Supports Python, Java, JavaScript, and C/C++ with various test frameworks (pytest, JUnit, Jest, Google Test).
79
71%
Does it follow best practices?
Impact
88%
0.92xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/interval-guided-regression-test-update/SKILL.mdQuality
Discovery
85%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 well-crafted description that excels in specificity and completeness, with a clear 'Use when...' clause and detailed capability list. The main weakness is the heavy use of technical jargon ('interval analysis', 'interval coverage') that users may not naturally use when requesting this functionality, which could reduce discoverability.
Suggestions
Add more natural trigger terms users might say, such as 'update tests after refactoring', 'fix test coverage', 'tests failing after code changes', or 'boundary value testing'
Consider adding common synonyms or simpler phrasings alongside technical terms, e.g., 'value ranges (boundaries, edge cases)'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Analyzes interval information', 'identifies coverage gaps', 'adjusts test inputs and assertions', 'removes redundant tests', 'generates new tests'. Also specifies supported languages and frameworks. | 3 / 3 |
Completeness | Clearly answers both what ('updates regression tests based on interval analysis') and when ('Use when code changes affect value ranges, conditionals, or control flow, and existing tests need updating'). Has explicit 'Use when...' clause with specific trigger conditions. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'regression tests', 'interval analysis', 'coverage', and specific frameworks (pytest, JUnit, Jest, Google Test), but uses technical jargon ('interval analysis', 'interval coverage') that users may not naturally say. Missing common variations like 'unit tests', 'test updates', 'fix failing tests'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche focusing on interval analysis for test maintenance, which is distinct from general testing skills. The combination of 'interval analysis', 'value ranges', and 'coverage gaps' creates a clear, unique domain unlikely to conflict with other testing-related skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a comprehensive conceptual framework for interval-guided test updates with good examples and structure. However, it suffers from verbosity (redundant examples, generic best practices) and lacks truly executable tooling - the actual interval extraction and test generation are delegated to referenced files or described abstractly. The workflow would benefit from stronger validation checkpoints.
Suggestions
Remove redundant content: consolidate the 'Core Concept' example with 'Quick Start Examples', and merge 'Best Practices' and 'Tips' sections which overlap significantly
Add executable code for interval extraction - either inline a minimal working implementation or provide specific tool commands rather than abstract descriptions like 'Parse conditionals'
Strengthen validation in the workflow: add explicit checkpoint after step 4 (e.g., 'Run tests in dry-run mode before committing changes') and include rollback guidance if validation fails
Remove generic advice Claude already knows (e.g., 'Use descriptive test names', 'Keep tests simple and focused') to reduce token usage
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains significant redundancy - the 'Core Concept' example and 'Quick Start Examples' overlap substantially. The 'Update Strategies' section repeats information already covered in the workflow. Some sections like 'Best Practices' and 'Tips' contain generic advice Claude already knows. | 2 / 3 |
Actionability | While the skill provides concrete Python examples, they are illustrative rather than executable tools. The workflow references external files for 'detailed extraction methods' and 'detailed strategies' but doesn't provide actual executable code for interval analysis or test generation - the core operations are described abstractly. | 2 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced, but validation is weak - step 5 just says 'Run the updated test suite' without explicit checkpoints or error recovery. For operations that modify test suites, there should be explicit validation before committing changes and rollback guidance if tests fail. | 2 / 3 |
Progressive Disclosure | Good structure with clear overview, workflow, examples, and references to external files (interval-analysis.md, test-update-strategies.md). Navigation is well-signaled with one-level-deep references. Content is appropriately organized into logical sections. | 3 / 3 |
Total | 9 / 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.
0f00a4f
Table of Contents
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.