common-debugging
Troubleshoot systematically using the Scientific Method. Use when debugging crashes, tracing errors, diagnosing unexpected behavior, or investigating exceptions. (triggers: debug, fix bug, crash, error, exception, troubleshooting)
86
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
82%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 with excellent trigger term coverage and clear completeness (both what and when are addressed). Its main weaknesses are the lack of specific concrete actions beyond the high-level 'troubleshoot systematically' and potential overlap with other debugging-related skills. Adding more specific capabilities (e.g., 'form hypotheses, isolate variables, analyze logs') would strengthen it.
Suggestions
Add specific concrete actions the skill performs, e.g., 'form hypotheses, isolate variables, analyze stack traces, reproduce issues, and verify fixes'
Differentiate from other potential debugging skills by clarifying what makes the Scientific Method approach unique, e.g., 'structured hypothesis-driven debugging as opposed to ad-hoc fixes'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (troubleshooting/debugging) and mentions the approach (Scientific Method), but does not list multiple specific concrete actions like 'analyze stack traces, reproduce errors, isolate variables, test hypotheses'. The actions are more about when to use it than what it concretely does. | 2 / 3 |
Completeness | Clearly answers both 'what' (troubleshoot systematically using the Scientific Method) and 'when' (debugging crashes, tracing errors, diagnosing unexpected behavior, investigating exceptions) with an explicit 'Use when' clause and explicit trigger terms. | 3 / 3 |
Trigger Term Quality | Includes a strong set of natural trigger terms that users would actually say: 'debug', 'fix bug', 'crash', 'error', 'exception', 'troubleshooting'. Also uses natural phrases like 'debugging crashes', 'tracing errors', 'diagnosing unexpected behavior' in the body text. | 3 / 3 |
Distinctiveness Conflict Risk | While the Scientific Method angle is somewhat distinctive, debugging/error/crash triggers are quite broad and could overlap with language-specific debugging skills, logging skills, or error-handling skills. The description doesn't narrow to a specific technology or unique niche. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
85%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-structured, concise debugging methodology skill that effectively communicates a systematic approach. Its main weakness is the lack of concrete, executable examples—the techniques described (binary search, minimal repro, diff diagnosis) would benefit from brief code demonstrations. The workflow is clear and the content respects Claude's intelligence without over-explaining.
Suggestions
Add a brief concrete example showing the scientific method applied to a real bug (e.g., a short code snippet with a bug, hypothesis, experiment, and fix)
Include executable code examples for techniques like 'Binary Search' debugging (e.g., showing how to comment out sections systematically) to move from description to demonstration
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every section earns its place—no unnecessary explanations of what debugging is or how programming works. The anti-patterns and best practices are terse and actionable. | 3 / 3 |
Actionability | The guidance is concrete in principle (scientific method steps, specific techniques like binary search and minimal repro) but lacks executable code examples or specific commands. It describes techniques rather than demonstrating them with concrete code snippets. | 2 / 3 |
Workflow Clarity | The 5-step scientific method provides a clear, well-sequenced workflow with an implicit validation loop (VERIFY step). The emphasis on 'prove root cause before changing code' and 'change one variable at a time' serves as validation checkpoints. For a debugging methodology skill, this level of workflow clarity is appropriate. | 3 / 3 |
Progressive Disclosure | The skill is well-organized with clear sections (method, anti-patterns, best practices) and references a separate bug report template via a one-level-deep link. For a skill of this size and scope, the structure is appropriate and navigable. | 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
- HoangNguyen0403/agent-skills-standard
- Commit
19a1140
- 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.