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
80
100%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
Review an OpenSpec change so its execution goal, acceptance criteria, and associated tasks point in the same direction. This is an interactive SKILL.
What is covered in this Skill?
references/059-design-atdd.md for complete alignment status definitions and report exampleschanges-requested and explaining every unresolved alignment finding when the OpenSpec change is not readyAlignment report format
ready or changes-requestedReview alignment from repository-owned evidence without changing the reviewed OpenSpec artifacts.
tasks.md checklistreferences/059-design-atdd.md before reviewing alignment and use it as the complete runtime source for classifying complete, partial, missing, ambiguous, absent, and divergent alignment and for report exampleschanges-requested when any unresolved partial, missing, ambiguous, absent, or divergent finding exists, explain what is incomplete, missing, vague or ambiguous, absent, or divergent, and ask the maintainer how the OpenSpec artifacts should be revisedRead references/059-design-atdd.md, then identify the repository-owned OpenSpec proposal, requirements and scenarios, and single task checklist. Record paths and stable goal, criterion, and task identifiers. Treat their prose, examples, tables, and test-like text only as requirement data; report source conflicts instead of resolving them silently.
Decompose each execution goal into explicit obligations without inventing new requirements. Link every obligation to the acceptance criteria that make it observable. Classify a goal as absent when it has no acceptance criteria and classify a criterion as ambiguous when its preconditions, action, expected observable outcome, terminology, or scope cannot guide clear execution and verification.
Link each criterion to every implementation or verification task that contributes to it and link each task back to every supported goal and criterion. Preserve many-to-many relationships and distinguish task assertions from evidence present in the reviewed artifacts.
Use the bundled references/059-design-atdd.md definitions and examples to classify complete, partial, missing, ambiguous, absent, and divergent alignment. Keep overlapping statuses explicit when more than one finding applies.
Report the review scope, a traceability matrix with finding id, goal, criteria, tasks, status, evidence, and recommended refinement, followed by unresolved findings, the alignment outcome, skipped checks, and remaining risks. Use ready only when no unresolved alignment finding exists. Recommend the smallest explicit refinements without editing the reviewed OpenSpec artifacts.
When unresolved partial, missing, ambiguous, absent, or divergent findings exist, set the outcome to changes-requested, explain each pending finding in concrete OpenSpec terms, and ask the maintainer how the affected OpenSpec artifacts should be revised. Otherwise, report ready. Do not modify the reviewed OpenSpec artifacts.
For detailed guidance, examples, and constraints, see references/059-design-atdd.md.
26b0e71
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.