CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

living-documentation-publisher

Use when BDD scenarios pass in CI and stakeholders need an always-current, readable report of which acceptance criteria pass. Turns Cucumber JSON into HTML living documentation (multiple-cucumber-html-reporter or Serenity BDD) and publishes it to GitHub or GitLab Pages.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is testland/living-documentation-publisher

SKILL.md
Quality
Evals
Security

Quality

Content

78%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-structured skill body: executable commands for every workflow step, an explicit publication gate, and exemplary one-level-deep reference structure with all three bundle files real and clearly signaled. Remaining gains are small — trimming the redundancy between the summary, worked example, and step sections, and adding error-recovery guidance for generate/publish failures.

DimensionReasoningScore

Conciseness

The body is largely efficient — code blocks carry the content and conceptual framing is limited to skill-specific Serenity doctrine. Minor trims possible: the "How to use" list, worked example, and Steps sections partially repeat each other, and a few trailing sentences restate their code blocks ("This ensures the published artefact reflects only a fully-green run").

4 / 5

Actionability

Concrete executable commands for every key action: the cucumber-js JSON formatter and "not @wip" tag filters, mvn aggregate/serenity:check invocations, and a set -e gating script. Not 5 because the core renderer steps (generate-report.js, the Serenity plugin XML) are not executable from the body alone — they are precisely deferred to references, leaving minor gaps in the body itself.

4 / 5

Workflow Clarity

Six clearly sequenced, individually headed steps with an explicit validation checkpoint — Step 5 gates publication on a green exit code (set -e, serenity:check) and the anti-patterns table acts as a failure-mode checklist. Not 5 because there are no error-recovery feedback loops (e.g., what to do when report generation or the Pages publish itself fails) and no post-publish verification of the artefact.

4 / 5

Progressive Disclosure

The body is a well-organized overview whose three references (node-reporter.md, serenity-reporter.md, ci-publish.md) all exist, are one level deep, are clearly signaled inline with descriptions of what each contains ("Full install, script, and options table"), and are summarized again in a References section. Detail is appropriately split and navigation is easy.

5 / 5

Total

17

/

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 strong description with an explicit "Use when" trigger, concrete tool-named actions, and a distinct BDD/Cucumber/Pages niche. Trigger coverage is good but misses a few natural phrasings (e.g., "test report", ".feature") that would push it to the top anchor.

DimensionReasoningScore

Specificity

"Turns Cucumber JSON into HTML living documentation (multiple-cucumber-html-reporter or Serenity BDD) and publishes it to GitHub or GitLab Pages" names specific concrete actions with named tools and target platforms. It falls short of 5 because it covers only the render and publish actions, omitting other workflow capabilities (tag-based section routing, gating publication on green runs), but exceeds 3 because the actions are tool-specific rather than generic.

4 / 5

Completeness

Explicitly answers both: what ("Turns Cucumber JSON into HTML living documentation... and publishes it to GitHub or GitLab Pages") and when ("Use when BDD scenarios pass in CI and stakeholders need an always-current, readable report of which acceptance criteria pass") with concrete trigger conditions. Both clauses are explicit and specific, matching the top anchor.

5 / 5

Trigger Term Quality

Strong natural keyword coverage: "BDD scenarios", "Cucumber JSON", "acceptance criteria", "living documentation", "Serenity BDD", "GitHub or GitLab Pages", and "CI". Not 5 because common user phrasings like "test report", "cucumber report", or ".feature files" are absent; not 3 because the terms span the domain's main synonyms rather than a single keyword.

4 / 5

Distinctiveness Conflict Risk

A clear niche (BDD/Cucumber living documentation published to Pages) with distinct triggers (Cucumber JSON, Serenity BDD, acceptance criteria reports) that no generic skill would claim. Minor theoretical overlap with generic Pages-publishing skills is pre-empted by the specific BDD/Cucumber framing, matching the minimal-conflict anchor.

5 / 5

Total

18

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

15

/

16

Passed

Repository

testland/qa

Path

plugins/qa-bdd/skills/living-documentation-publisher/SKILL.md

Reviewed

Table of Contents

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.