032-architecture-adr-non-functional-requirements
Facilitates conversational discovery to create Architectural Decision Records (ADRs) for non-functional requirements using the ISO/IEC 25010:2023 quality model. Use when the user wants to document quality attributes, NFR decisions, security/performance/scalability architecture, or design systems with measurable quality criteria. This should trigger for requests such as Create ADR for Non-functional requirements; Document Non-functional requirements; Capture Non-functional requirements; Generate Non-functional requirements in an ADR. Part of cursor-rules-java project
88
85%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is a strong skill description that clearly defines its purpose, scope, and trigger conditions. It combines specific domain terminology (ADRs, NFRs, ISO/IEC 25010:2023) with explicit 'Use when' and 'This should trigger for' clauses, making it easy for Claude to select appropriately. The description is well-structured and covers multiple natural user phrasings.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists multiple concrete actions: 'conversational discovery to create Architectural Decision Records (ADRs)', 'document quality attributes', 'NFR decisions', 'security/performance/scalability architecture', and 'design systems with measurable quality criteria'. It also references a specific standard (ISO/IEC 25010:2023). | 3 / 3 |
Completeness | Clearly answers both 'what' (facilitates conversational discovery to create ADRs for NFRs using ISO/IEC 25010:2023) and 'when' (explicit 'Use when' clause plus a 'This should trigger for' clause with specific example requests). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'ADR', 'Architectural Decision Records', 'non-functional requirements', 'NFR', 'quality attributes', 'security', 'performance', 'scalability', plus explicit example phrases like 'Create ADR for Non-functional requirements', 'Document Non-functional requirements', 'Capture Non-functional requirements'. These cover multiple natural variations users would say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: the combination of ADRs, non-functional requirements, ISO/IEC 25010:2023, and the specific cursor-rules-java project context makes it very unlikely to conflict with other skills. The domain is narrow and well-defined. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a reasonably well-structured interactive skill with clear workflow sequencing and good progressive disclosure to a reference file. Its main weaknesses are moderate verbosity (redundant sections) and limited actionability in the skill body itself—concrete examples of discovery questions, expected ADR output structure, or quality metrics would make it more self-contained and executable. The validation checkpoints and conversational constraints are well-defined.
Suggestions
Remove the 'What is covered in this Skill?' section as it largely duplicates the workflow and constraints, or merge it into the workflow steps to reduce redundancy.
Add a brief concrete example of what a generated ADR section looks like (e.g., a sample Quality Metrics & Success Criteria table) so Claude has a clear output target without needing to read the full reference file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has some redundancy—the 'What is covered' section largely duplicates the workflow steps, and the 'When to use this skill' section repeats the description verbatim. The constraints section has useful content but could be tighter. Some unnecessary framing like 'Act as an architecture consultant: challenge-first, consultative, adaptive' is somewhat verbose. | 2 / 3 |
Actionability | The skill provides a clear workflow sequence and specific constraints (run `date`, read a specific reference file, ask 1-2 questions at a time), but lacks concrete examples of what good discovery questions look like, what the ADR output format should contain, or what 'Quality Metrics & Success Criteria' look like. The actual actionable content is deferred to the reference file. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced (get date → read reference and open → run discovery → generate ADR) with explicit validation checkpoints: validate summary with user before proposing ADR, wait for user confirmation before generating. The feedback loop of 'validate summary → confirm → generate' is well-defined for this interactive conversational skill. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep reference to the detailed guidance file (references/032-architecture-adr-non-functional-requirements.md). The SKILL.md appropriately serves as an overview pointing to detailed materials, though the bundle file wasn't provided for verification of the reference's existence. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- jabrena/cursor-rules-java
- Commit
762cb86
- 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.