java-debug
Safety rules, workflows, and tool reference for debugging applications via IntelliJ debugger: breakpoints, debug sessions, stepping, evaluating expressions, inspecting runtime state. TRIGGER when: user wants to debug, investigate a bug, set breakpoints, inspect runtime behavior, step through code, or understand why code behaves unexpectedly at runtime. Trigger phrases (EN): "debug", "breakpoint", "step through", "step into", "step over", "why does this crash", "why is this null", "launch in debug mode", "trace execution", "run with debugger", "evaluate expression". Trigger phrases (RU): "отладить", "дебаг", "брейкпоинт", "почему падает", "пошагово пройти", "зайти в метод", "посмотреть значение переменной", "запустить в режиме отладки", "почему null", "стектрейс". Also trigger when user wants to understand runtime behavior or investigate incorrect behavior.
72
88%
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 excels across all dimensions. It provides specific capabilities tied to IntelliJ debugging, includes comprehensive trigger terms in two languages covering natural user phrasings, and clearly delineates both what the skill does and when it should be activated. The bilingual trigger phrases are a notable strength for multilingual environments.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: breakpoints, debug sessions, stepping, evaluating expressions, inspecting runtime state. Also references specific workflows like 'launch in debug mode', 'trace execution', and 'evaluate expression'. | 3 / 3 |
Completeness | Clearly answers both 'what' (debugging applications via IntelliJ debugger: breakpoints, debug sessions, stepping, evaluating expressions, inspecting runtime state) and 'when' (explicit TRIGGER clause with detailed trigger phrases and scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms in both English and Russian, including user-natural phrases like 'why does this crash', 'why is this null', 'step through', 'breakpoint', and their Russian equivalents. These are terms users would actually say. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to IntelliJ debugger specifically, with distinct triggers around debugging, breakpoints, and runtime inspection. Unlikely to conflict with general coding skills or other IDE-specific skills due to the specific tool and action focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured debugging skill with excellent actionability and workflow clarity. The safety rules are genuinely valuable and address real pitfalls specific to debugger MCP interaction. The main weakness is moderate verbosity — some explanatory text could be trimmed — and the document is long enough that splitting into referenced files would improve progressive disclosure.
Suggestions
Trim explanatory sentences in the Safety Rules section (e.g., 'This is the single most common mistake', 'They exist because...') — the rules themselves are clear without the rationale.
Consider extracting the Tool Reference tables into a separate TOOLS.md file and the Error Recovery table into a TROUBLESHOOTING.md, keeping SKILL.md as a concise overview with workflow focus.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary elaboration. Phrases like 'This is the single most common mistake' and 'These rules prevent you from hanging indefinitely or losing debugging context' are explanatory padding. The tool reference tables are well-structured but the overall document could be tightened by ~20% without losing information. | 2 / 3 |
Actionability | Provides fully concrete guidance: exact tool names with precise parameter signatures, specific curl flags (--max-time 5), exact field names to check (isSuspended), numbered step-by-step workflows, and an error recovery table with specific actions. Everything is copy-paste ready for MCP tool invocation. | 3 / 3 |
Workflow Clarity | Two distinct workflows are clearly sequenced with explicit validation checkpoints: 'get_current_position' after every step, checking suspension status before network calls, verifying position after resume. Error recovery table provides feedback loops. The safety rules section front-loads critical validation requirements. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections (Safety Rules, Tool Reference, Workflows, Error Recovery), but it's a fairly long monolithic document (~180 lines) with no references to external files. The tool reference tables and detailed workflows could be split into separate files for better progressive disclosure, though for a standalone skill without bundle files this is acceptable. | 2 / 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
- Amplicode/spring-skills
- Commit
1dd96ad
- 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.