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

96%

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

Quality

Content

92%

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

The body is lean, highly actionable, and sequenced with a real verification/retry loop, reflecting deep FRB-specific operational knowledge. Its main weakness is progressive disclosure: most detail is inline and the bundled analyzer script it depends on is absent from the bundle.

Suggestions

Ship the referenced codecov_analyzer.py in a scripts/ directory (or remove the command examples) so the primary commands are actually executable.

Move the long 'acceptable reasons' and 'good test candidates' lists into a references/ file linked from SKILL.md to reduce inline bulk.

Confirm the cross-referenced skills (frb-develop-feature, frb-test, tom-frb-env, gh-actions-live-logs) exist and are reachable from this skill's context.

Dimension	Reasoning	Score
Conciseness	The body is operational throughout — exact marker names, file outputs, and line_coverage semantics — and avoids explaining what Codecov or coverage is. Not 2 because nearly every line is domain-specific guidance Claude would not already know, with no padding.	3 / 3
Actionability	Provides copy-paste commands ('python3 .claude/skills/frb-fix-codecov/codecov_analyzer.py download --pr <number>') and concrete Rust/Dart ignore-marker code blocks. Not 2 because guidance is executable and specific rather than pseudocode or abstract direction.	3 / 3
Workflow Clarity	Sequences Step 1 (collect facts) → Step 2 (choose fix, Option A/B) → a numbered Verification section with a retry feedback loop ('If Codecov is still red, repeat the workflow'). Not 2 because validation checkpoints and an error-recovery loop are explicit, so the destructive/batch cap does not apply.	3 / 3
Progressive Disclosure	Sections are well-organized, but the document is a monolithic inline block (long acceptable-reasons and test-candidate lists inline) and its one bundled-file reference (codecov_analyzer.py) is not present in any scripts/references/assets directory. Not 3 because content that could be split out is inline and the referenced bundle file is missing; not 1 because section structure and one-level references do exist.	2 / 3
	Total	11 / 12 Passed

Description

100%

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, third-person, and supplies explicit 'Use when' triggers covering both what the skill does and when to invoke it. It carves out a distinct FRB+Codecov niche with natural trigger terms.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions in a specific domain: 'Codecov patch or project coverage drops', 'Codecov comments mention missing lines', and 'decide whether to add tests or justified coverage-ignore markers'. Not below 3 because it lists several specific concrete actions rather than naming only a domain.	3 / 3
Completeness	Explicit 'Use when a flutter_rust_bridge PR has ...' trigger answers 'when', and 'decide whether to add tests or justified coverage-ignore markers' answers 'what'. Not 2 because both what and when are explicit, not merely implied.	3 / 3
Trigger Term Quality	Uses natural terms a contributor would actually say — 'flutter_rust_bridge PR', 'Codecov patch', 'project coverage drops', 'Codecov comments mention missing lines', 'coverage-ignore markers'. Not below 3 because it covers the common phrasings a user would voice when hitting this situation.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to flutter_rust_bridge + Codecov coverage drops, a clear niche unlikely to fire for unrelated skills. Not 2 because the trigger combination is distinctive rather than broadly overlapping.	3 / 3
	Total	12 / 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: fzyzcjy/flutter_rust_bridge
Path: .claude/skills/frb-fix-codecov/SKILL.md
Commit: 1d5348b

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.