improve-test-coverage

Improve test coverage for shell features and commands using reference test suites from yash, GNU coreutils, and uutils/coreutils

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/improve-test-coverage/SKILL.md

Quality

Content

55%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and well-sequenced with strong validation checkpoints, but it is severely over-long with no progressive disclosure — 788 lines inlined into SKILL.md with no supporting reference files — and would benefit materially from splitting large reference tables/templates into separate files and trimming the protocol prose.

Suggestions

Move the stable reference material (YAML format spec, gap-category tables, per-target report template) into a reference file (e.g. references/scenario-format.md, references/report-templates.md) and link to it, enabling progressive disclosure.

Consolidate the repeated find/grep discovery snippets (Steps 4, 7, 8) into one shared block and remove duplicated commit-message templates to cut length.

Trim the exhortation/protocol prose ('STOP — READ THIS', the 'Do NOT stop the run voluntarily' bullets) to the essential rule; the enforcement tone is token-cost that does not aid execution.

Dimension	Reasoning	Score
Conciseness	At 788 lines this is extensively verbose: large duplicated find/grep snippets across Steps 4/7/8, full commit-message templates repeated, and lengthy protocol exhortations ('Do NOT stop the run voluntarily', 'STOP — READ THIS') that pad the skill well past what Claude needs to execute.	2 / 5
Actionability	Provides concrete, executable bash/go commands (find/grep, curl\|tar downloads, git commit/push, gh pr comment) and a complete YAML scenario template with field semantics; minor gaps such as placeholder '<report content here>' and unverified PR-number flow keep it just below 5.	4 / 5
Workflow Clarity	Three-phase (A/B/C) structure with numbered Steps 1-14, explicit sequencing, TaskCreate/TaskList gating before each step, and validation checkpoints (Step 10 /fix-ci-tests, Step 12 CI re-check); just shy of 5 because the per-target loop's error-recovery feedback loop is less explicit than the validation-heavy Phase A/C checkpoints.	4 / 5
Progressive Disclosure	There are no bundle files (references/scripts/assets) at all and no external file references — all 788 lines live inline in SKILL.md, so content that clearly belongs in separate files (the YAML format spec, the gap-category tables, the report templates) is inlined rather than split, matching the anchor for inlined content that should be separate.	3 / 5
	Total	13 / 20 Passed

Description

57%Weight 40%Scale 1-5

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 clearly states what the skill does and is domain-specific, but it lacks an explicit 'Use when...' trigger clause and the natural trigger phrases a user would actually say, capping completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when asked to increase test coverage for shell commands or shell language features, or when finding untested edge cases.'

Include more natural user phrasing and file/area references like 'untested flags', 'coverage gaps', 'scenario tests', '.yaml' to improve trigger-term quality.

Tighten the verb from the generic 'Improve' to concrete actions like 'Audit, identify gaps in, and add scenario/unit tests for shell command and feature coverage.'

Dimension	Reasoning	Score
Specificity	Names the domain (test coverage for shell features/commands) and a concrete action (improving coverage by mining reference suites), plus the specific sources (yash, GNU coreutils, uutils/coreutils), but 'improve coverage' is itself a somewhat generic verb and the concrete actions of how are thin.	4 / 5
Completeness	The 'what' is stated clearly (improve test coverage by mining reference suites) but there is no explicit 'Use when...' clause or trigger guidance for when Claude should invoke this skill, which caps completeness at 3 per the guidelines.	3 / 5
Trigger Term Quality	Includes relevant keywords ('test coverage', 'shell features', 'commands', reference suite names) but lacks the natural phrases a user would actually say ('add tests', 'find untested code', 'coverage gaps') and includes no file extensions.	3 / 5
Distinctiveness Conflict Risk	The niche is fairly distinct (shell feature/command coverage mining from specific named suites) with limited overlap risk against general testing skills; only minor overlap with a generic 'write tests' skill.	4 / 5
	Total	14 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (789 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: DataDog/rshell
Path: .claude/skills/improve-test-coverage/SKILL.md
Commit: 30a7e9e

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.