059-design-atdd

Use when reviewing whether an OpenSpec change's execution goal, acceptance criteria, and implementation or verification tasks are aligned. This should trigger for requests such as Review this OpenSpec change with ATDD; Check acceptance criteria against tasks; Find acceptance criteria without task coverage; Detect tasks that diverge from the execution goal; Explain what is missing, vague, ambiguous, partial, absent, or divergent in this OpenSpec change. Part of Plinth Toolkit

Quality

89%

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

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, mostly lean instruction-only skill with a clear sequenced workflow and excellent progressive disclosure via a single bundled reference. Minor repetition of the read-reference directive and the status taxonomy keeps it just short of fully lean and fully actionable.

Suggestions

Consolidate the repeated 'read references/059-design-atdd.md' instruction and the 'complete, partial, missing, ambiguous, absent, divergent' status list into a single authoritative mention to reduce redundancy across 'What is covered', 'Constraints', and 'Workflow'.

Add a brief concrete alignment-finding example (one short traceability matrix row with status + evidence + recommended refinement) inline so the report format is immediately actionable without opening the reference.

Make the validation checkpoint in the workflow explicit—e.g., a step that verifies every goal and criterion has been traced before classifying the outcome as ready or changes-requested.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence without re-explaining ATDD or OpenSpec, but the 'read references/059-design-atdd.md' instruction and the status list ('complete, partial, missing, ambiguous, absent, divergent') recur across 'What is covered', 'Constraints', and 'Workflow', so it is not perfectly tight.	4 / 5
Actionability	Concrete, specific instruction-only guidance is provided (decompose goals into obligations, link to criteria, report fields 'finding id, goal, criteria, tasks, status, evidence, recommended refinement'), with the detailed classification definitions and examples deferred to the bundled reference rather than inlined.	4 / 5
Workflow Clarity	A clearly sequenced six-step workflow with an explicit ready/changes-requested decision gate in step 6; because the skill is read-only (MUST NOT edit artifacts) the destructive-operation cap does not apply, though explicit error-recovery checkpoints are minimal.	4 / 5
Progressive Disclosure	The body is an overview that points to a single one-level-deep reference (references/059-design-atdd.md, confirmed present) for full definitions and report examples, signaled clearly in multiple sections and a dedicated Reference section, with content appropriately split.	5 / 5
	Total	17 / 20 Passed

Description

100%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, third-person description that clearly states the skill's purpose and enumerates concrete, naturally-worded trigger phrases. It comprehensively covers capabilities, triggers, and distinctiveness with no padding.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete review actions—'reviewing whether an OpenSpec change's execution goal, acceptance criteria, and implementation or verification tasks are aligned', 'Check acceptance criteria against tasks', 'Find acceptance criteria without task coverage', 'Detect tasks that diverge from the execution goal'—giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	It explicitly answers both what (alignment review across goal/criteria/tasks) and when ('Use when reviewing whether...', 'This should trigger for requests such as...') with concrete trigger phrases, satisfying the top anchor.	5 / 5
Trigger Term Quality	It embeds verbatim natural trigger phrases users would say ('Review this OpenSpec change with ATDD', 'Check acceptance criteria against tasks', 'Find acceptance criteria without task coverage') plus synonym coverage ('missing, vague, ambiguous, partial, absent, or divergent'), matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	The OpenSpec + ATDD + acceptance-criteria niche is distinct with specific triggers unlikely to fire for unrelated skills, giving minimal conflict risk.	5 / 5
	Total	20 / 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/059-design-atdd/SKILL.md
Commit: f6dfc6f

Reviewed: 18 minutes 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.