Tessl • The management layer for AI agent skills

SkillPublic

improve-test-coverage

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

Quality

73%

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

77%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.

This is a highly actionable, well-sequenced orchestration skill: every step is executable as written, validation checkpoints and resume handling are explicit, and the batch workflow fully satisfies the workflow-clarity bar. Its weaknesses are repetition between the opening protocol section and the step definitions, and the absence of any progressive disclosure — a 788-line monolith where the YAML format, gap taxonomy, and report templates belong in referenced files.

Suggestions

Move the YAML scenario format spec, the Step 5 gap-category tables, and the Step 11/13 report templates into references/ files (e.g., references/yaml-format.md, references/gap-taxonomy.md, references/report-templates.md) linked from the body, cutting the main file substantially.

Deduplicate the opening 'STOP' section against Steps 1-2: state the task-list creation and COVERAGE_PROGRESS.md resume check once and reference it from the protocol instead of repeating the instructions.

Trim repeated directives such as 'do not ask for confirmation' and the multiple restatements of the resume-vs-fresh check to a single authoritative statement.

Dimension	Reasoning	Score
Conciseness	The body is dense with project-specific, non-redundant-by-nature detail (paths, YAML conventions, CLI flags), but the opening 'STOP' protocol section repeats the task-list and resume-check instructions that are restated nearly verbatim in Steps 1-2, and several directives (e.g., 'do not ask for confirmation', the resume check) are stated two or three times, matching the 'mostly efficient but could be tightened' anchor rather than the 4 anchor's 'minor instances'.	3 / 5
Actionability	Every step supplies copy-paste-ready material: exact find/grep/diff commands, a complete YAML scenario template, commit-message and PR-report templates, the CLI-flag mirroring table for sandbox config, and a concrete classification rubric for every decision point — fully executable guidance covering the common cases, matching the 5 anchor.	5 / 5
Workflow Clarity	The workflow is explicitly phased (A/B/C) into 14 sequenced steps with per-step validation checkpoints (TaskList verification of the prior step, re-reading sub-bullets before marking complete), batch verification in Step 10, a /fix-ci-tests feedback loop in Phase C, and a crash-resume protocol via COVERAGE_PROGRESS.md — this is a batch operation with explicit feedback loops and checklists, matching the 5 anchor rather than the 4 anchor's 'minor validation gaps'.	5 / 5
Progressive Disclosure	There are no bundle files at all (references/, scripts/, assets/ are absent) and the 788-line body inlines material that clearly belongs in separate reference files — the YAML format spec, the gap-category tables, the Step 6 layer-selection rubric, and the PR-report templates — which fits the 3 anchor ('content that should be separate is inline'); it is not a 2 because internal section structure and navigation within the single file are good, not minimal.	3 / 5
	Total	16 / 20 Passed

Description

61%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 anchors it to a specific niche via the named reference suites, but it lacks any 'Use when...' trigger guidance and only hints at the full set of concrete actions. Adding an explicit use-when clause and one or two more action verbs (e.g., 'identify gaps, write scenario tests, prune duplicates') would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to improve or expand test coverage, close test gaps, or strengthen tests for shell features or builtin commands.'

Enumerate the concrete actions the skill performs — e.g. 'audit existing coverage, identify gaps, write scenario and unit tests, and prune duplicates' — so specificity reaches comprehensive coverage.

Include natural synonyms such as 'test gaps', 'unit tests', and 'scenario tests' that users would likely say when invoking this skill.

Dimension	Reasoning	Score
Specificity	The description names the domain ('test coverage for shell features and commands') and one concrete method ('using reference test suites from yash, GNU coreutils, and uutils/coreutils'), matching the 'names domain and 1-2 concrete actions' anchor; it does not enumerate the actual actions performed (identify gaps, write scenario/unit tests, prune duplicates), so it falls short of the 4 anchor's 'several specific actions'.	3 / 5
Completeness	The 'what' is clear (improve test coverage by mining reference suites), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines; it is not a 4 because the 'when' is entirely absent rather than merely implicit.	3 / 5
Trigger Term Quality	'test coverage', 'shell features', and 'commands' are natural phrases a user would say, giving good keyword coverage, but common variations like 'tests', 'unit tests', 'scenario tests', or 'test gaps' are missing, so it is not at the 5 anchor's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	The pairing of test-coverage improvement with three named external test suites carves a mostly distinct niche with minor overlap risk against a generic write-tests skill; it is not a 5 because the trigger phrase 'test coverage' alone could plausibly fire for a broader testing 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
Revision: df8b605

Reviewed: 25 days ago

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.

improve-test-coverage

Table of Contents

Is this your skill?