coverage-enhancer
Raises test coverage by identifying uncovered code regions, ranking them by risk, and generating targeted tests that hit them — prioritizing branches and conditions over raw line count. Use when coverage is below target, when untested code is blocking a release, or when deciding which tests to write next.
Install with Tessl CLI
npx tessl i github:santosomar/general-secure-coding-agent-skills --skill coverage-enhancer100
Quality
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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 well-crafted skill description that excels across all dimensions. It provides specific, concrete actions (identifying gaps, ranking by risk, generating tests), uses natural developer terminology, includes an explicit 'Use when...' clause with three distinct trigger scenarios, and carves out a clear niche around test coverage improvement that won't conflict with general testing or code review skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'identifying uncovered code regions', 'ranking them by risk', 'generating targeted tests', and 'prioritizing branches and conditions over raw line count'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (identifies uncovered regions, ranks by risk, generates tests) AND when with explicit 'Use when...' clause covering three specific trigger scenarios: coverage below target, untested code blocking release, deciding which tests to write. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'test coverage', 'coverage is below target', 'untested code', 'blocking a release', 'which tests to write'. These match how developers naturally discuss testing gaps. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on test coverage improvement and gap analysis. The focus on 'uncovered code regions', 'risk ranking', and 'branches and conditions' distinguishes it from general testing or code quality skills. | 3 / 3 |
Total | 12 / 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 that demonstrates excellent token efficiency through strategic use of tables, provides fully actionable guidance with real commands and code examples, and maintains clear workflow structure. The 'Do not' section adds valuable guardrails, and the output format ensures consistent, useful results.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely efficient use of tokens. Tables compress information well, no explanation of basic concepts Claude knows, and every section adds unique value. The coverage levels table and ecosystem commands are dense with actionable information. | 3 / 3 |
Actionability | Provides concrete, executable commands for every major ecosystem, a complete worked example with real Python code, and specific git commands for measuring churn. The test example is copy-paste ready with clear reasoning. | 3 / 3 |
Workflow Clarity | Clear 4-step sequence (get gap report → rank gaps → construct tests → handle uncoverable code) with explicit decision criteria at each stage. The ranking factors table provides clear validation criteria for prioritization decisions. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections, appropriate use of tables for reference material, and cross-references to related skills (mutation-test-suite-optimizer, dead-code-eliminator) without deep nesting. Content is appropriately self-contained. | 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.
- 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.