coverage-loop

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

Quality

71%

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

85%Weight 40%Scale 1-3

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

A tight, well-structured coverage loop with a genuine feedback loop and a clear stop condition; the only gap is that the actual coverage command is referenced generically rather than given explicitly.

Suggestions

Name the concrete baseline/coverage command (e.g. the actual `cargo llvm-cov` invocation) instead of "the repository-supported command" so step 1 and step 4 are directly executable.

Add a brief validation note for what to do when the re-run shows coverage did not improve (e.g. discard the new test before repeating) to make the feedback loop's error path explicit.

Optionally show the one-line command for step 1 alongside the prose so the entry point is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is a lean 7-step list plus one constraint sentence with no concept-explaining fluff; it assumes Claude knows what coverage and cargo-llvm-cov are, so every token earns its place.	3 / 3
Actionability	It gives a concrete sequenced process and one named command (`review`), but defers the actual coverage command to "the repository-supported command" / "the same coverage command" without stating the invocation, so it is not copy-paste ready.	2 / 3
Workflow Clarity	The numbered steps form a clear sequence with an explicit feedback loop (step 4 re-run coverage, step 5 keep-only-if-it-improves as an evaluation gate, step 6 repeat-until-covered) plus a final "Run `review`" checkpoint.	3 / 3
Progressive Disclosure	This is an under-50-line single-purpose skill with no need for external references; the single well-organized "Coverage loop" section satisfies progressive disclosure per the simple-skills note.	3 / 3
	Total	11 / 12 Passed

Description

57%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, tool-named description with a clear purpose, but it lacks an explicit "Use when..." trigger clause and relies on somewhat technical phrasing, capping completeness and trigger-term quality at 2.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to improve or increase Rust test coverage, mentions cargo-llvm-cov, or wants to find untested behavior in Fallow."

Soften jargon by adding natural phrasings like "code coverage" or "increase coverage" alongside "test coverage".

List the distinct concrete actions (e.g. "measure coverage, identify untested behavior, add behavior-focused tests, drop tests that don't improve coverage") to raise specificity.

Dimension	Reasoning	Score
Specificity	It names a concrete tool ("cargo-llvm-cov") and domain ("Fallow Rust test coverage"), but centers on a single action ("improve") with qualifiers rather than listing multiple distinct concrete actions like the score-3 anchor.	2 / 3
Completeness	The "what" is clear ("Iteratively improve Fallow Rust test coverage..."), but there is no explicit "Use when..." or equivalent trigger clause, so per the judging guidelines completeness caps at 2.	2 / 3
Trigger Term Quality	It includes some natural terms a user would say ("test coverage", "Rust"), but leans technical ("Fallow", "cargo-llvm-cov", "runtime correctness") and misses common variations such as "increase coverage" or "code coverage".	2 / 3
Distinctiveness Conflict Risk	The combination of "Fallow Rust", "test coverage", and "cargo-llvm-cov" defines a narrow, specific niche that is unlikely to trigger for an unrelated skill.	3 / 3
	Total	9 / 12 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: 55944e8

Reviewed: 11 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.