improve-test-coverage
Improve test coverage for shell features and commands using reference test suites from yash, GNU coreutils, and uutils/coreutils
54
43%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/improve-test-coverage/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a specific niche (shell test coverage using reference test suites) but lacks concrete action verbs describing what the skill actually does and completely omits explicit trigger guidance. It would benefit from listing specific actions (e.g., porting tests, identifying coverage gaps, generating test cases) and adding a 'Use when...' clause to help Claude select it appropriately.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to add or improve tests for shell builtins, POSIX commands, or coreutils utilities by referencing existing test suites.'
List specific concrete actions the skill performs, such as 'Ports test cases from reference suites, identifies coverage gaps, generates new test scenarios for shell commands and builtins.'
Include additional natural trigger terms users might say, such as 'bash tests', 'POSIX compliance', 'shell builtins', 'command tests', or specific command names.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (test coverage for shell features/commands) and mentions specific reference test suites (yash, GNU coreutils, uutils/coreutils), but doesn't list concrete actions beyond 'improve test coverage' — e.g., it doesn't specify what improving means (writing tests, porting tests, analyzing gaps, etc.). | 2 / 3 |
Completeness | Describes what it does ('improve test coverage for shell features') but has no explicit 'Use when...' clause or equivalent trigger guidance, and the 'what' itself is not very detailed. Per rubric guidelines, a missing 'Use when' clause caps completeness at 2, and the weak 'what' brings it to 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'test coverage', 'shell', 'yash', 'GNU coreutils', 'uutils/coreutils', but misses common user-facing terms like 'unit tests', 'integration tests', 'bash', 'POSIX', 'shell builtins', or specific command names that users might mention. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of specific reference test suites (yash, GNU coreutils, uutils/coreutils) provides some distinctiveness, but 'improve test coverage for shell features and commands' is broad enough to potentially overlap with general testing or shell development skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is highly actionable with excellent workflow clarity — every step has concrete commands, clear sequencing, and validation checkpoints. However, it is severely over-long and monolithic, cramming ~400+ lines of content into a single file without progressive disclosure. Many sections (gap category tables, YAML format rules, report templates) should be extracted into referenced files, and significant verbosity could be trimmed by trusting Claude's existing knowledge of git, bash, and testing concepts.
Suggestions
Extract the gap category tables (Step 4), YAML format reference (Step 5), and report template (Step 10) into separate referenced files to reduce the main skill to an overview with clear navigation.
Remove explanations of things Claude already knows — e.g., how to use `grep -rl`, how `git push -u origin` works, what 'exact duplicates' means, and basic bash command syntax.
Consolidate repeated instructions (e.g., 'do NOT ask for confirmation' appears multiple times, security warnings are restated) into a single prominent section.
Trim the gap category tables to just the category names — Claude understands what 'edge case inputs' and 'error conditions' mean without needing examples like 'Empty file, single-line file, no trailing newline'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines. It over-explains processes Claude already understands (how to run bash commands, how to use grep, how to commit with git), includes extensive tables for gap categories that are general testing knowledge, and repeats instructions multiple times (e.g., 'do NOT ask for confirmation' appears multiple times). The security preamble, while important, is also lengthy. | 1 / 3 |
Actionability | The skill provides fully executable commands throughout — concrete bash commands for downloading test suites, finding files, running tests, committing, and posting PR comments. The YAML format examples are copy-paste ready with clear field explanations. Every step has specific, executable guidance. | 3 / 3 |
Workflow Clarity | The workflow is exceptionally well-sequenced with explicit phases (A and B), numbered steps with dependencies, validation checkpoints (Step 9 runs tests before committing), feedback loops (batch size of 10-15 then verify, fix and re-validate), and clear task dependency management. The protocol for verifying step completion before proceeding is explicit. | 3 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to supporting files. Despite the complexity warranting separation (e.g., gap category tables, YAML format reference, report template could all be separate files), everything is inlined. The skill references a `/fix-ci-tests` skill but no bundle files are provided to support the content structure. | 1 / 3 |
Total | 8 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- DataDog/rshell
- Commit
729dfbb
- 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.