058-design-bdd

Use when a Java change needs independent Behavior-Driven Development guidance from trusted behavior facts through concrete examples and observable scenarios, with focused clarification when behavior is pending or ambiguous. This should trigger for requests such as Apply BDD; Facilitate behavior examples; Discover scenarios with Given When Then; Review these examples for shared domain language; Complete BDD discovery as a self-contained interaction. Part of Plinth Toolkit

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/058-design-bdd/SKILL.md

Quality

Content

71%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.

The content is well-structured with a clear workflow and excellent progressive disclosure to a single real reference file. The main weakness is conciseness — repetitive reference mentions and overlap between the 'What is covered' and 'Constraints' sections could be consolidated.

Suggestions

Consolidate the repeated mentions of references/058-design-bdd.md into one 'MUST read' constraint and reference it by short name elsewhere to reduce token redundancy.

Merge or cross-reference the 'What is covered' list with the 'Constraints' section so closely related points (e.g., discovering main/alternative/boundary/error examples) are stated once.

Consider adding an explicit validation/feedback checkpoint in the workflow (e.g., re-confirm unresolved questions before reporting) to strengthen the existing clarifying-question loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but it repeats the reference file path four times and the 'What is covered' list overlaps materially with the 'Constraints' bullets, so it could be tightened.	3 / 5
Actionability	As an instruction-only skill it gives concrete, specific guidance — named example types (main/alternative/boundary/error), Given/When/Then, a named reference file to read, and explicit report categories — with only minor gaps.	4 / 5
Workflow Clarity	Four clearly sequenced workflow steps are present with checkpoints (focused follow-up questions on ambiguous facts, tracking unresolved questions), and the skill is non-destructive so the validation cap does not apply; minor validation gaps remain.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview pointing to a single, real, one-level-deep reference (references/058-design-bdd.md) that is well signaled both inline and in a dedicated Reference section, with content appropriately split.	5 / 5
	Total	16 / 20 Passed

Description

83%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.

The description is strong: it explicitly covers both what the skill does and when to trigger it, with several natural trigger phrases and a clear BDD niche. It could improve by adding synonym/extension trigger terms and tightening the abstract guidance phrasing into more concrete actions.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Apply BDD', 'Facilitate behavior examples', 'Discover scenarios with Given When Then', 'Review these examples for shared domain language', 'Complete BDD discovery'), though they are guidance-oriented rather than concrete file/data operations, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what it does ('independent Behavior-Driven Development guidance from trusted behavior facts through concrete examples and observable scenarios') and when to use it via 'Use when...' plus concrete 'This should trigger for requests such as...' phrasing.	5 / 5
Trigger Term Quality	Includes multiple natural trigger phrases a user would say ('Apply BDD', 'Facilitate behavior examples', 'Discover scenarios with Given When Then'), but lacks common synonyms or file extensions (e.g., .feature, Cucumber, Gherkin) that would round out coverage.	4 / 5
Distinctiveness Conflict Risk	Has a clear BDD-for-Java niche with distinct Given/When/Then triggers and minimal conflict risk, though 'Part of Plinth Toolkit' implies sibling skills with which closely related BDD/scenario-review skills could mildly overlap.	4 / 5
	Total	17 / 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: jabrena/plinth
Path: skills/058-design-bdd/SKILL.md
Commit: f6dfc6f

Reviewed: about 2 hours 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.