CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/coverage-diff-reporter

Builds a per-PR coverage delta report from any pair of LCOV / Cobertura / JSON coverage outputs (current run + baseline from the merge target) - emits a per-file table with line% / branch% deltas, called-out new files, hidden drops (overall +0.1pp but one file -8pp), and a single-line PR-comment summary. Use when the team has coverage in CI but needs human-readable PR feedback that points at the specific file the reviewer should focus on, not just an aggregate number.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

Quality

Content

87%

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

An actionable, concise, well-organized skill with executable code and concrete CI patterns. The main gap is the absence of explicit validation/verification checkpoints in the pipeline, which keeps workflow_clarity at 2.

Suggestions

Add an explicit validation step between parsing and diffing, e.g. 'assert current.json has N files and baseline.json parsed cleanly; abort if a parse produced 0 files' to catch empty/corrupt artifacts before the report is generated.

Add a verification checkpoint before posting the PR comment (e.g. confirm diff.md is non-empty and the overall line% delta is within a sane range) so a malformed parse never posts a misleading summary.

Surface baseline-age validation from the Limitations section into the workflow (Step 2): explicitly check the baseline artifact's run date and warn in the report header when main coverage is stale.

DimensionReasoningScore

Conciseness

Lean and assumes Claude's competence — it does not explain what coverage, LCOV, or PR comments are, and every section (Overview, code, anti-patterns, limitations) earns its place without padding.

3 / 3

Actionability

Provides fully executable Python (compute_diff/classify) and copy-paste-ready GitHub Actions YAML with real action versions and concrete commands like `python scripts/coverage_diff.py current.json baseline.json > diff.md`, plus a concrete rendered report example.

3 / 3

Workflow Clarity

The seven steps are clearly sequenced, but the multi-step pipeline lacks explicit validation checkpoints (e.g., 'verify current.json parsed N files before diffing'); per the rubric, a multi-step process without validation checkpoints caps at 2.

2 / 3

Progressive Disclosure

Single well-sectioned file with clearly signaled one-level-deep references (the References section points to peer skills, not nested files); no bundle files exist, and the body is organized for easy navigation.

3 / 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.

A strong description: concrete, third-person, with explicit what-and-when triggers and a distinct niche separated from upstream parsers and downstream gates. It is on the longer side but every clause is load-bearing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'per-file table with line% / branch% deltas', 'called-out new files', 'hidden drops (overall +0.1pp but one file -8pp)', and 'single-line PR-comment summary' — matching the anchor for multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both what ('Builds a per-PR coverage delta report...') and when ('Use when the team has coverage in CI but needs human-readable PR feedback...') with an explicit trigger clause, in third person.

3 / 3

Trigger Term Quality

Uses natural domain terms a user would say ('coverage', 'PR', 'CI', 'per-file', 'LCOV / Cobertura'); technical jargon is appropriate to the audience and covers the common ways the need surfaces.

3 / 3

Distinctiveness Conflict Risk

Carves a clear niche — a per-PR coverage *diff* report pointing at the specific file — and explicitly distinguishes itself from pass/fail gates ('does not decide pass/fail - that's the gate's job'), making wrong-skill triggering unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 5 missing

Warning

Total

15

/

16

Passed

Reviewed

Table of Contents