Use when you need to generate Architecture Decision Records (ADRs) for a Java project through an interactive, conversational process that systematically gathers context, stakeholders, options, and outcomes to produce well-structured ADR documents. Part of the skills-for-java project
59
48%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/030-architecture-adr-general/SKILL.mdQuality
Discovery
75%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 reasonably well-crafted description that clearly establishes when to use the skill and has a distinct niche. Its main weaknesses are moderate specificity in describing concrete actions and limited trigger term coverage for how users might naturally request ADR help.
Suggestions
Add more natural trigger term variations like 'architecture decisions', 'design decisions', 'technical decisions', 'document architecture choices' to improve discoverability
List more specific concrete actions such as 'create ADR templates', 'compare architectural options', 'document trade-offs', 'export to markdown format'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (ADRs for Java projects) and describes the general approach (interactive, conversational process) with some actions (gathers context, stakeholders, options, outcomes), but doesn't list multiple concrete specific actions like 'create templates', 'export to markdown', etc. | 2 / 3 |
Completeness | Explicitly answers both what (generate ADRs through interactive process gathering context, stakeholders, options, outcomes to produce structured documents) and when ('Use when you need to generate Architecture Decision Records') with clear trigger guidance at the start. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'Architecture Decision Records', 'ADRs', and 'Java project', but misses common variations users might say like 'architecture decisions', 'design decisions', 'technical decisions', 'document architecture choices', or file extensions. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche combining ADRs + Java + interactive conversational process. The combination of 'Architecture Decision Records' and 'Java project' creates a distinct trigger unlikely to conflict with general documentation or other Java skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a stub that describes what it should do without actually providing the guidance needed to do it. It lacks any concrete examples of the MADR template, the conversational flow for gathering information, or the actual steps in the ADR generation process. The validation constraint is good but the core functionality is entirely missing from the skill body.
Suggestions
Add a concrete example of the MADR template format that should be generated, showing the expected output structure
Define the actual conversational workflow steps: what questions to ask, in what order, and how to handle responses
Include at least one complete example showing input context and the resulting ADR output
Remove or significantly condense the 'When to use this skill' keyword list which doesn't help Claude execute the skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is relatively brief but includes some unnecessary content like the extensive 'When to use this skill' keyword list that doesn't add actionable value, and the 'What is covered' section that could be more concise. | 2 / 3 |
Actionability | The skill provides no concrete examples, templates, or executable guidance. It describes what the skill does but doesn't show how to actually generate an ADR - no MADR template example, no conversation flow, no sample output. | 1 / 3 |
Workflow Clarity | Despite claiming to be an 'interactive conversational process that systematically gathers' information, no actual workflow steps are defined. The only concrete step is 'run mvnw validate' but the actual ADR generation process is completely absent. | 1 / 3 |
Progressive Disclosure | The skill appropriately references a detailed guide file for examples and constraints, but the main skill file is too sparse - it delegates almost everything to the reference without providing enough actionable content in the overview itself. | 2 / 3 |
Total | 6 / 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.
7772a1b
Table of Contents
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.