coverage-loop

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

Quality

64%

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 ./.claude/skills/coverage-loop/SKILL.md

Quality

Content

71%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 concise and well-structured as a clear feedback loop with good progressive disclosure for a simple skill. Its main weakness is actionability: steps are abstract process directions rather than concrete commands or selection criteria.

Suggestions

Name the actual coverage command in the body (e.g. the specific cargo-llvm-cov invocation) instead of 'the repository-supported command', or point to where it is defined.

Give a concrete heuristic for 'Select uncovered behavior by risk' (e.g. prioritize branches handling error paths, external input, or state mutations over trivial getters).

Add a brief validation/error-recovery step for when re-run tests fail or coverage does not improve.

Dimension	Reasoning	Score
Conciseness	The body is a lean numbered list plus one guardrail sentence with no padding or explanation of concepts Claude already knows; every line earns its place. Matches the 'lean and efficient; assumes Claude's competence' anchor.	5 / 5
Actionability	Steps are high-level process hints ('Capture a coverage baseline with the repository-supported command', 'Select uncovered behavior by risk', 'Add behavior-focused tests') with no named coverage command in the body and only one concrete token (`review`). Matches the 'minimal concrete guidance; high-level hints but missing specific steps' anchor. Not a 3 because no executable command or specific selection method is provided.	2 / 5
Workflow Clarity	A clear 7-step numbered sequence with an explicit repeat/stopping condition (step 6) and feedback checkpoints (step 4 re-run tests and coverage, step 5 keep only improving tests). Matches 'clear sequence with most checkpoints present; minor validation gaps'. Not a 5 because there is no explicit error-recovery guidance if tests fail.	4 / 5
Progressive Disclosure	A simple skill under 50 lines with no need for external references and no bundle files present; content is well-organized with a heading, numbered steps, and a guardrail note. Per the scoring notes this scores 5 for simple skills.	5 / 5
	Total	16 / 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 is specific and distinct, naming the project, language, and tool, but lacks an explicit 'Use when' trigger clause and uses somewhat abstract action verbs. It is clearly better than generic placeholders but stops short of comprehensive, trigger-rich guidance.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when improving Fallow Rust test coverage or when the user asks to increase coverage of untested behavior.'

Include natural trigger synonyms such as 'code coverage', 'untested code', or 'coverage gaps' that a user might actually say.

Replace abstract verbs ('prioritizing', 'preserving') with at least one more concrete capability statement (e.g. 'identifies uncovered behavior by risk and adds behavior-focused tests').

Dimension	Reasoning	Score
Specificity	Names the domain ('Fallow Rust test coverage with cargo-llvm-cov') and a couple of actions ('improve', 'prioritizing meaningful untested behavior', 'preserving runtime correctness'), but the actions are abstract rather than concrete operations, matching the 'names domain and 1-2 concrete actions, not comprehensive' anchor. Not a 4 because it does not list several specific concrete actions.	3 / 5
Completeness	Clearly states the 'what' (iteratively improve Fallow Rust test coverage) but provides no 'when'/'Use when' trigger guidance, which per the judging guidelines caps completeness at 3. Not a 4 because there is no explicit 'when' clause at all.	3 / 5
Trigger Term Quality	Contains relevant natural terms like 'test coverage' and 'Rust' plus the tool 'cargo-llvm-cov', but misses common synonyms and variations users might say (e.g. 'code coverage', 'untested code'). Not a 4 because keyword coverage is incomplete.	3 / 5
Distinctiveness Conflict Risk	Targets a very specific niche (the Fallow project's Rust test coverage via cargo-llvm-cov), making it clearly distinguishable with minimal conflict risk against other skills. Matches the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 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: .claude/skills/coverage-loop/SKILL.md
Commit: 7e1e075

Reviewed: 3 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.