coverage-loop

Iteratively improve Fallow Rust test coverage with cargo-llvm-cov, prioritizing meaningful untested behavior and preserving runtime correctness.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/coverage-loop/SKILL.md

Quality

Content

75%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 content is an exemplar of conciseness with a well-sequenced feedback loop and a useful anti-pattern guardrail, but it stops short of naming the actual coverage command, leaving a small actionability gap. Adding the concrete cargo-llvm-cov invocation would push it higher.

Suggestions

Replace 'the repository-supported command' with the actual cargo-llvm-cov (or repo-specific) command so step 1 and step 4 are copy-paste ready.

Add a brief failure/validation checkpoint, e.g. 'If a test does not change coverage, drop it before proceeding' to make the feedback loop explicit.

Optionally show the one-line coverage invocation inline so the loop is fully executable without consulting external docs.

Dimension	Reasoning	Score
Conciseness	The body is a lean ~9-line loop with zero padding and no over-explanation of concepts Claude already knows; every token earns its place and the closing anti-pattern line is maximally tight.	5 / 5
Actionability	The numbered loop is concrete as a process (select by risk, add behavior tests, re-run, keep/discard), but key executable details are missing — 'the repository-supported command' is never named and the cargo-llvm-cov invocation from the description is not shown.	3 / 5
Workflow Clarity	A clear 7-step sequence with an explicit feedback loop (re-run coverage, keep only tests that improve, repeat until covered) and a final verification step ('Run review'); minor gaps in explicit failure-handling detail keep it just below 5.	4 / 5
Progressive Disclosure	A short single-purpose skill with a single H1, a well-ordered numbered loop, and a clearly separated anti-pattern note; no bundle files exist and none are needed, so structure is appropriate for the size with only minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

58%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 is specific and third-person with a clear 'what', but it omits any explicit 'when to use' trigger guidance, which caps completeness and limits natural trigger-term coverage. Adding a 'Use when...' clause would materially raise the score.

Suggestions

Add an explicit trigger clause, e.g. 'Use when improving Rust test coverage for the Fallow project or when the user asks to increase coverage with cargo-llvm-cov.'

Include natural synonyms a user might say (e.g. 'code coverage', 'untested code', 'coverage report') to broaden trigger-term quality.

Clarify the concrete actions available (e.g. 'measure coverage gaps, add behavior-focused tests, prune low-value tests') to push specificity toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain ('Fallow Rust test coverage with cargo-llvm-cov') and several concrete actions ('improve... coverage', 'prioritizing meaningful untested behavior', 'preserving runtime correctness'), but the actions are somewhat conceptual rather than a comprehensive list of concrete operations.	4 / 5
Completeness	Has a clear 'what' (iteratively improve Fallow Rust test coverage) but no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Contains relevant keywords ('Rust test coverage', 'cargo-llvm-cov') but lacks common synonyms or natural variations a user would say; 'Fallow' is project-specific jargon rather than a natural trigger phrase.	3 / 5
Distinctiveness Conflict Risk	The combination of 'Fallow', 'Rust', and 'cargo-llvm-cov' carves a distinct niche with low overlap risk; minor overlap possible with general Rust testing/coverage skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: fallow-rs/fallow
Path: .agents/skills/coverage-loop/SKILL.md
Commit: d0ebe05

Reviewed: ~12 hours 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.