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.
90
Quality
88%
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 explicit 'Use when' clause with quoted user phrases makes it highly actionable for skill selection. The only weakness is that the capability description could be more specific about what actions the skill performs beyond 'generate'.
Suggestions
Consider adding 2-3 more specific actions beyond 'generate', such as 'create from templates', 'update existing ADRs', or 'link related decisions' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Architecture Decision Records) and the general action (capture reasoning behind technical decisions), but doesn't list multiple specific concrete actions like 'create templates', 'track decision history', or 'link related decisions'. | 2 / 3 |
Completeness | Clearly answers both what (generate ADRs that capture reasoning behind technical decisions) and when (explicit 'Use when' clause with multiple trigger scenarios including quoted user phrases). | 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 | Very distinct niche with specific triggers like 'ADR', 'Architecture Decision Records', and 'architectural trade-offs'. Unlikely to conflict with general documentation or code skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that provides a complete, actionable ADR template with efficient instructions. The content respects Claude's intelligence by avoiding unnecessary explanation of ADR concepts. Minor improvement could be made by adding a validation step to ensure the captured decision accurately reflects stakeholder intent.
Suggestions
Add a brief validation step after writing (e.g., 'Confirm with the user that the Context and Decision sections accurately capture their intent before finalizing')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, providing only the template structure and essential instructions without explaining what ADRs are or why they matter—Claude already knows this. | 3 / 3 |
Actionability | Provides a complete, copy-paste ready markdown template with all sections filled with placeholder guidance, plus concrete instructions for locating existing ADRs and numbering conventions. | 3 / 3 |
Workflow Clarity | Steps are listed clearly (extract, find location, number, write, capture why) but lacks validation checkpoints—no guidance on verifying the ADR captures the decision accurately or reviewing with stakeholders before finalizing. | 2 / 3 |
Progressive Disclosure | Appropriate structure for a focused skill—concise main content with clear 'See Also' references to related skills, keeping references one level deep and well-signaled. | 3 / 3 |
Total | 11 / 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
96a72fa
- 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.