CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

76

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable debugging guide with explicit safety rules, validation checkpoints, and concrete MCP tool signatures; its only slack is minor reinforcement redundancy and the absence of any split-out reference material.

Suggestions

Consolidate the --max-time 5 / run_in_background safety guidance into one stated rule and reference it from the workflows instead of repeating the literal flag each time, to tighten conciseness.

If the tool reference table grows, move the per-tool parameter details into a references/REFERENCE.md and link to it from a trimmed inline summary, adding a clear one-level-deep reference for progressive disclosure.

Add a short 'Cleanup checklist' at the end of each workflow (remove_breakpoint, stop_debug_session) as an explicit terminal validation step rather than a prose reminder.

DimensionReasoningScore

Conciseness

Largely lean and assumes debugger knowledge, explaining only the non-obvious suspended-process trap; minor redundancy (the --max-time 5 / run_in_background guidance recurs across rules and workflows) keeps it just below fully efficient.

4 / 5

Actionability

Tool reference tables give exact parameter signatures and the two workflows are concrete copy-paste-ready tool-call sequences covering the common debug-investigation cases, with a specific error-recovery table.

5 / 5

Workflow Clarity

Both workflows are numbered with explicit validation checkpoints ('After each step, call get_current_position', 'confirm the breakpoint was hit') and supported by Rules 3/4 and an error-recovery section that provides fix-and-retry feedback loops.

5 / 5

Progressive Disclosure

Single well-organized file with clear section headers (Preflight, Safety, Tool Reference, Workflows, Error Recovery, Limitations) and no bundle files; the inline tool reference is appropriate for a focused single-domain skill, though there are no one-level-deep references to signal.

4 / 5

Total

18

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that names concrete debugger actions, provides comprehensive bilingual trigger phrases, and clearly separates capability statements from explicit trigger guidance in third-person voice.

DimensionReasoningScore

Specificity

Lists multiple concrete debugging actions — 'breakpoints, debug sessions, stepping, evaluating expressions, inspecting runtime state' — giving comprehensive coverage of the skill's capabilities rather than vague abstractions.

5 / 5

Completeness

Explicitly answers 'what' (safety rules, workflows, tool reference for IntelliJ debugging) and 'when' via a dedicated 'TRIGGER when' clause with concrete trigger phrases, in third-person voice.

5 / 5

Trigger Term Quality

Comprehensive natural-language triggers including synonyms ('debug', 'run with debugger', 'trace execution') and user-style phrasing ('why does this crash', 'why is this null'), plus a full Russian equivalent set.

5 / 5

Distinctiveness Conflict Risk

Scoped tightly to 'debugging applications via IntelliJ debugger' with tooling-specific triggers, giving it a clear niche and minimal overlap with other skills.

5 / 5

Total

20

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Amplicode/spring-skills
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.