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

78%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 an exemplary lean, well-sequenced workflow with real validation gates and a clear termination condition. Its main weakness is actionability: it defers the actual coverage command to 'the repository-supported command' instead of naming an executable command.

Suggestions

Name the concrete coverage command (e.g. `cargo llvm-cov --html` or the repo's documented invocation) in step 1 instead of 'the repository-supported command'.

Add a brief failure-handling branch after step 4 (e.g. 'If new tests fail or regress runtime behavior, fix or drop them before proceeding').

Clarify what 'Run `review`' refers to (a slash command or verification skill) so the final step is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is 15 lean lines with zero padding and no explanation of concepts Claude already knows; every instruction, including 'Do not add assertions that merely execute code without checking behavior', earns its place.	5 / 5
Actionability	The steps are concrete in intent ('Select uncovered behavior by risk, not by easiest lines', 'Re-run targeted tests'), but executable specifics are missing: 'the repository-supported command' never names the actual command (e.g. cargo llvm-cov) and no copy-paste-ready invocation appears.	3 / 5
Workflow Clarity	A clear 7-step sequence with a re-run checkpoint (step 4), a keep/drop gate (step 5), and explicit termination conditions (step 6), but error-recovery handling (what to do when tests fail or coverage regresses) remains implicit.	4 / 5
Progressive Disclosure	Under 50 lines with no need for external references; the header and numbered list are well-organized, satisfying the simple-skill exception for progressive disclosure.	5 / 5
	Total	17 / 20 Passed

Description

53%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 concise and specific about what the skill does, with a clear tool and domain, but lacks any explicit 'when to use' trigger guidance and misses common keyword variations a user might naturally say. Adding a 'Use when...' clause would substantially improve it.

Suggestions

Add an explicit trigger clause such as 'Use when the user asks to improve or close test coverage gaps in a Rust project, mentions cargo-llvm-cov, or wants untested code covered.'

Include common synonyms users would naturally say, e.g. 'code coverage', 'untested code', or 'coverage gaps', not just 'test coverage'.

Consider naming one or two additional concrete actions (e.g. capturing a coverage baseline, generating coverage reports) to lift specificity beyond a single framed activity.

Dimension	Reasoning	Score
Specificity	Names the domain and tool ('Fallow Rust test coverage with cargo-llvm-cov') with qualifiers ('prioritizing meaningful untested behavior and preserving runtime correctness'), but these frame a single coherent activity rather than listing several distinct concrete actions, matching the 'names domain and 1-2 concrete actions' anchor.	3 / 5
Completeness	The 'what' is clear (iteratively improve coverage with cargo-llvm-cov, prioritizing meaningful behavior, preserving correctness), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Contains relevant natural keywords ('test coverage', 'Rust', 'cargo-llvm-cov') but misses common variations and synonyms such as 'code coverage', 'untested code', or 'branch coverage', matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	A clear niche (Rust test coverage with a specific tool) that is mostly distinct, with only minor overlap risk against general test-writing or code-review skills.	4 / 5
	Total	13 / 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: 74177e5

Reviewed: 5 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.