CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/gherkin-scenario-coverage-map

Parses new Gherkin scenarios produced by acceptance-criteria-extractor, fingerprints each scenario by its Given/When/Then step sequence, diffs the fingerprints against existing step-definition usage in the live suite, and emits a coverage/duplicate map showing which new scenarios are already covered, which overlap partially, and which are genuine gaps. Use when acceptance criteria have been converted to .feature files and before any new automated tests are authored.

74

Quality

93%

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

85%

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

The body is well-structured and highly actionable with a clear sequenced workflow and proper progressive disclosure; its only weakness is mild verbosity from extended quotation and explanatory rationale that Claude could largely infer.

Suggestions

Trim the verbatim Gherkin-reference quote in the Overview to the single load-bearing rule (the step-text identity principle) rather than reproducing the full sentence.

In Step 6, state each hard-reject condition as a one-line gate without the follow-on justification paragraphs; the halt instruction itself is the actionable signal.

Consider folding the Anti-patterns table's 'Why it fails' column into the 'Fix' column to reduce token count while preserving the corrective guidance.

DimensionReasoningScore

Conciseness

The body is mostly efficient but includes reasoning Claude could infer — it quotes the Gherkin reference at length ('Keywords are not taken into account...') and explains why each hard-reject condition fails ('A coverage map against an empty suite is vacuous...', 'the map would mislead rather than inform') — so it could be tightened without losing signal.

2 / 3

Actionability

Provides concrete commands ('npx cucumber-js --format json:reports/cucumber.json', 'mvn test -Dcucumber.plugin=...'), explicit data structures ('{ id, title, tags[], steps[] }', 'normalized_step_text -> [{ feature_file, scenario_title, line_number }]'), a status-classification table, and a filled worked example.

3 / 3

Workflow Clarity

Six explicitly sequenced steps with validation gates in Step 6 (empty suite, unparseable Gherkin, index < 5) and a feedback loop ('Fix the syntax first; use acceptance-criteria-extractor to regenerate'), matching the clear-sequence-with-checkpoints anchor.

3 / 3

Progressive Disclosure

Keeps the compact four-part instruction inline while delegating detailed output templates to the real, one-level-deep, clearly-signaled reference 'references/coverage-map-output-format.md', with well-organized sections and a references list.

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.

The description is strong across all dimensions: third-person voice, concrete capabilities, natural trigger terms, an explicit Use-when clause, and a clearly demarcated niche. No changes needed.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Parses new Gherkin scenarios', 'fingerprints each scenario by its Given/When/Then step sequence', 'diffs the fingerprints', 'emits a coverage/duplicate map' — matching the multi-action anchor.

3 / 3

Completeness

Explicitly answers both 'what' (parse, fingerprint, diff, emit map) and 'when' via the 'Use when acceptance criteria have been converted to .feature files and before any new automated tests are authored' trigger clause.

3 / 3

Trigger Term Quality

Uses natural domain terms a BDD practitioner would actually say — 'Gherkin scenarios', '.feature files', 'acceptance criteria', 'automated tests' — giving good coverage rather than jargon-only phrasing.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche tied to the acceptance-criteria-extractor pipeline with distinct triggers (new Gherkin scenarios, before authoring tests), unlikely to fire for unrelated skills.

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Reviewed

Table of Contents