coverage-loop

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

Quality

68%

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

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.

A tight, disciplined workflow with excellent token efficiency and a genuine feedback loop. Its main weaknesses are unspecified executable details (the coverage command is never named) and the absence of an error-recovery step in the loop.

Suggestions

Name the actual baseline command (e.g., `cargo llvm-cov --lcov --branch` or the repo's canonical invocation) instead of 'the repository-supported command'.

Add an explicit recovery step, e.g., 'If a new test fails or reduces coverage, fix or delete it before continuing the loop.'

Specify where to read coverage output (e.g., the cargo-llvm-cov report path or `--summary-only` flag) so step 4's comparison is executable.

Dimension	Reasoning	Score
Conciseness	The body is a 15-line numbered loop where every line carries an instruction ('Select uncovered behavior by risk, not by easiest lines') and the closing line adds a real constraint ('Do not add assertions that merely execute code without checking behavior'). Nothing explains concepts Claude already knows, and no token is wasted.	5 / 5
Actionability	Steps are directionally specific but omit executable details: 'Capture a coverage baseline with the repository-supported command' never states the actual command (e.g., the cargo-llvm-cov invocation), and only `review` is a concrete runnable reference. This matches 'some concrete guidance but incomplete; missing key details' rather than 4, which requires mostly executable guidance.	3 / 5
Workflow Clarity	The 7-step sequence is clear with a built-in feedback loop (step 4 re-runs tests and coverage, step 5 keeps only improving tests) and an explicit termination condition (step 6). It falls short of 5 because there is no error-recovery checkpoint — nothing says what to do when a new test fails or regresses coverage — though the validation loop itself is present.	4 / 5
Progressive Disclosure	The skill is under 50 lines, single-purpose, and needs no external files, so a simple organized structure suffices. It earns 4 rather than 5 because there is no section organization at all (just a title, list, and a stray 'Generated from .agents/skills. Do not edit.' comment), making navigation slightly less clean than the well-organized-sections bar for simple skills.	4 / 5
	Total	16 / 20 Passed

Description

62%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.

A lean, specific description with a clear niche and named tool, but it lacks any 'Use when...' trigger guidance and has thin natural-keyword coverage. Adding an explicit trigger clause would lift both completeness and trigger-term quality.

Suggestions

Append a trigger clause such as 'Use when the user asks to improve or increase Rust test coverage, mentions uncovered or untested code, or references cargo-llvm-cov.'

Include natural synonyms users would actually say (e.g., 'coverage report', 'uncovered lines', 'increase coverage') alongside 'test coverage'.

Optionally name one concrete output of the skill (e.g., producing a coverage delta per iteration) to round out the action list.

Dimension	Reasoning	Score
Specificity	The description names concrete actions ('Iteratively improve Fallow Rust test coverage', 'prioritizing meaningful untested behavior', 'preserving runtime correctness') and a specific tool (cargo-llvm-cov), giving several specific actions with only minor coverage gaps. It falls short of 5 because the action list is brief — e.g., it does not mention coverage reporting or interpreting results.	4 / 5
Completeness	The 'what' is clear and specific, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because 'when' is entirely absent rather than merely weakly implied.	3 / 5
Trigger Term Quality	'test coverage', 'Rust', and 'cargo-llvm-cov' are relevant keywords a user might say, but common natural variations such as 'increase coverage', 'uncovered code', 'coverage report', or '.rs' are missing. Not 4 because the natural-phrase coverage is thin beyond the single phrase 'test coverage'.	3 / 5
Distinctiveness Conflict Risk	The description pins a specific repository (Fallow), language (Rust), and tool (cargo-llvm-cov), establishing a clear niche with minimal overlap risk against generic testing skills. Not 4 because the tool and repo qualifiers make it more distinct than the 'PDF and Word files' overlap example.	5 / 5
	Total	15 / 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: 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.