adr
Generate Architecture Decision Records that capture the reasoning behind technical decisions. Use when the user asks to "create an ADR", "document a decision", "record why we chose X", or discusses architectural trade-offs worth preserving.
85
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 with excellent trigger terms and completeness. The 'Use when' clause provides multiple natural language triggers that users would actually say. The main area for improvement is listing more specific concrete actions beyond just 'generate' to better convey the full range of capabilities.
Suggestions
Add more specific actions to improve specificity, e.g., 'Generate Architecture Decision Records with context, options considered, trade-off analysis, and final rationale sections.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Architecture Decision Records) and the core action (generate/capture reasoning behind technical decisions), but it doesn't list multiple specific concrete actions like listing templates, formatting sections, or comparing alternatives. | 2 / 3 |
Completeness | Clearly answers both 'what' (generate Architecture Decision Records capturing reasoning behind technical decisions) and 'when' (explicit 'Use when' clause with multiple trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'create an ADR', 'document a decision', 'record why we chose X', 'architectural trade-offs'. These are phrases users would naturally say when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | ADRs are a very specific document type with distinct terminology ('ADR', 'architectural trade-offs', 'document a decision'). This is unlikely to conflict with general documentation or code generation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, practical skill that provides a complete ADR template and clear instructions for generating architecture decision records. Its main strengths are the actionable, copy-paste-ready template and good progressive disclosure with cross-references. Weaknesses include some verbosity in the template's placeholder text and a lack of validation steps in the workflow (e.g., confirming the ADR directory and number with the user before writing).
Suggestions
Add a validation step such as 'Confirm the ADR number and target directory with the user before writing the file' to strengthen the workflow.
Trim the template's placeholder questions (e.g., 'What is the issue...') to brief labels or remove them entirely, since Claude understands what each section requires.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The template itself is useful but takes up significant space. The placeholder text in the template (e.g., 'What is the issue that we're seeing that is motivating this decision or change?') is somewhat verbose and could be trimmed. The instructions section is reasonably lean but includes some obvious guidance like 'Capture the why' that Claude would naturally do. | 2 / 3 |
Actionability | Provides a complete, copy-paste-ready markdown template with clear structure. The instructions give concrete steps: where to find/create ADR directories, how to number them, and what to extract from conversation context. This is fully actionable guidance. | 3 / 3 |
Workflow Clarity | Steps are listed and sequenced (extract context → find location → number → write → capture reasoning), but there are no validation checkpoints. For a document-generation task, there's no step to verify the ADR is complete or to confirm the chosen directory/numbering with the user before writing. | 2 / 3 |
Progressive Disclosure | The skill is appropriately self-contained for its scope, with a clear 'See Also' section pointing to related skills one level deep. The template and instructions are well-organized with clear section headers, and the content doesn't need to be split further. | 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
- tslateman/duet
- Commit
c3b1fc2
- 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.