030-architecture-adr-general

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

Quality

56%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/030-architecture-adr-general/SKILL.md

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 solid description that clearly communicates when to use the skill and what it does. It has strong trigger terms and a distinct niche. The main weakness is that the specific actions/capabilities could be more concrete — listing specific outputs or steps rather than describing the general process abstractly.

Suggestions

Add more concrete actions such as 'creates ADR markdown files', 'generates decision tables', or 'updates ADR log' to improve specificity beyond the general process description.

Dimension	Reasoning	Score
Specificity	The description names the domain (Architecture Decision Records for Java) and describes the general process (interactive, conversational process that gathers context, stakeholders, options, and outcomes), but doesn't list multiple specific concrete actions like 'create ADR files', 'generate templates', 'update ADR index', etc.	2 / 3
Completeness	The description explicitly answers both 'what' (generate ADRs through an interactive process that gathers context, stakeholders, options, and outcomes to produce well-structured ADR documents) and 'when' (starts with 'Use when you need to generate Architecture Decision Records').	3 / 3
Trigger Term Quality	Includes strong natural trigger terms: 'Architecture Decision Records', 'ADRs', 'Java project', 'stakeholders', 'options', 'outcomes', 'ADR documents'. Users asking about ADRs or architecture decisions would naturally use these terms.	3 / 3
Distinctiveness Conflict Risk	Very clear niche: ADR generation specifically for Java projects through an interactive conversational process. This is unlikely to conflict with other skills given the specific combination of ADRs + Java + interactive process.	3 / 3
	Total	11 / 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 but provides almost no actionable content. The actual ADR generation process, conversational flow, template structure, and examples are entirely absent from the skill body, all deferred to a reference file. The 'When to use this skill' section is bloated with trigger keywords that waste tokens without adding value.

Suggestions

Add a concrete step-by-step conversational workflow (e.g., Step 1: Ask about context, Step 2: Identify stakeholders, Step 3: Gather options with pros/cons, etc.) so Claude knows exactly how to conduct the interactive process.

Include the MADR template or at minimum a concrete example of a completed ADR output so the skill is actionable without requiring the reference file.

Remove or drastically reduce the 'When to use this skill' keyword list — Claude doesn't need 17 trigger phrases to understand when to generate an ADR.

Add validation checkpoints within the conversational workflow (e.g., confirm gathered information with user before generating the final ADR document).

Dimension	Reasoning	Score
Conciseness	The 'When to use this skill' section is excessively padded with keyword-like trigger phrases that don't add value for Claude. The constraints section repeats the validation requirement. However, the overall structure is reasonably compact.	2 / 3
Actionability	There is no concrete guidance on how to actually generate an ADR — no template, no example output, no conversational flow steps, no code or commands beyond 'mvnw validate'. The skill describes what it does but doesn't instruct how to do it, deferring everything to a reference file.	1 / 3
Workflow Clarity	The skill mentions a 'conversational process that systematically gathers context' but provides zero sequencing of that conversation — no steps for gathering context, stakeholders, options, or outcomes. The only concrete step is running validation, but the actual ADR generation workflow is entirely absent.	1 / 3
Progressive Disclosure	There is a clear reference to a detailed file (references/030-architecture-adr-general.md), which is good one-level-deep disclosure. However, the SKILL.md itself contains almost no substantive content — it's essentially an empty shell pointing to the reference, with no quick-start or overview of the actual process.	2 / 3
	Total	6 / 12 Passed

Validation

100%

Warnings & errors only

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: 9ec21dd

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.