frb-fix-codecov

Use when a flutter_rust_bridge PR has Codecov patch or project coverage drops, Codecov comments mention missing lines, or you need to decide whether to add tests or justified coverage-ignore markers.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%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 well-sequenced, actionable skill body with a strong verification/feedback loop and concrete commands, hindered mainly by progressive-disclosure gaps: it references a bundled analyzer script that is not in the bundle and inlines detail that belongs in reference files.

Suggestions

Ship the referenced `codecov_analyzer.py` under `scripts/` (or remove the bundled-script framing) so the download/analyze commands are actually executable from the bundle.

Move the acceptable-reasons catalog and the Codecov endpoint/line-coverage encoding details into a `references/` file, keeping SKILL.md as an overview with a clearly signaled link.

Tighten the Step-1 troubleshooting bullets and the acceptable-reasons list to reduce token spend on edge-case enumeration.

Dimension	Reasoning	Score
Conciseness	Dense and domain-aware — it assumes Claude knows Codecov/coverage/FFI concepts rather than explaining them — with only minor over-explanation in the acceptable-reasons list and the Step-1 troubleshooting bullets that could be trimmed, matching the 'efficient; minor instances of over-explanation' anchor.	4 / 5
Actionability	Provides concrete executable commands (the analyzer download/analyze invocations, `git diff --unified=0`), real Rust/Dart ignore-marker code blocks, and named endpoints, but execution depends on the bundled analyzer and sibling skills, leaving minor gaps versus the fully copy-paste-ready anchor.	4 / 5
Workflow Clarity	Two sequenced steps (collect facts, choose fix with Options A/B) plus a numbered Verification section with an explicit feedback loop — 'If Codecov is still red, repeat the workflow from the latest exact report' — satisfying the validation-checkpoint requirement even though the work touches tests and ignore markers.	5 / 5
Progressive Disclosure	Sectioning (Overview / Workflow / Verification) is reasonable and sibling-skill references are one-level and clearly signaled, but the body leans on a bundled `codecov_analyzer.py` and several detail blocks (endpoint variants, acceptable-reasons catalog) that are inlined rather than split out, and the referenced analyzer is not present in the bundle directories.	3 / 5
	Total	16 / 20 Passed

Description

87%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 precise, third-person description that explicitly pairs a concrete 'what' with a multi-condition 'Use when' trigger and is tightly scoped to the FRB-Codecov niche. It is comprehensive and distinguishable with only minor trigger-synonym gaps.

Dimension	Reasoning	Score
Specificity	Names the narrow domain (flutter_rust_bridge PR Codecov) and several concrete actions/triggers — 'Codecov patch or project coverage drops', 'Codecov comments mention missing lines', 'decide whether to add tests or justified coverage-ignore markers' — with only minor coverage gaps, matching the 'lists several specific actions; minor gaps' anchor.	4 / 5
Completeness	Explicitly answers both 'what' (decide whether to add tests or justified coverage-ignore markers) and 'when' via a concrete 'Use when...' clause listing three trigger conditions, matching the 'clearly and explicitly answers both what AND when' anchor.	5 / 5
Trigger Term Quality	Uses natural domain terms a user would actually say — 'Codecov patch', 'project coverage drops', 'Codecov comments mention missing lines', 'add tests', 'coverage-ignore markers' — giving good keyword coverage, though a few synonyms (e.g. 'coverage report', 'coverage gate') are absent.	4 / 5
Distinctiveness Conflict Risk	The trigger is tightly scoped to flutter_rust_bridge Codecov coverage handling — a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 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: fzyzcjy/flutter_rust_bridge
Path: .claude/skills/frb-fix-codecov/SKILL.md
Commit: 0876e2e

Reviewed: 4 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.