common-debugging
Troubleshoot systematically using the Scientific Method. Use when debugging crashes, tracing errors, diagnosing unexpected behavior, or investigating exceptions.
61
73%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.github/skills/common/common-debugging/SKILL.mdQuality
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 a clear 'Use when' clause and good trigger terms that developers would naturally use. Its main weakness is that the 'what' portion is somewhat abstract—'troubleshoot systematically using the Scientific Method' doesn't enumerate the concrete steps or actions the skill performs. It could also be more distinctive to reduce potential overlap with other debugging-related skills.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Forms hypotheses, designs targeted tests, isolates root causes through systematic elimination' to improve specificity.
Consider adding distinguishing scope or constraints (e.g., 'for software/code issues' or 'across any programming language') to reduce conflict risk with more specialized debugging skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (troubleshooting/debugging) and mentions the approach (Scientific Method), but doesn't list specific concrete actions like 'analyze stack traces', 'reproduce issues', 'isolate variables', etc. The actions listed (debugging crashes, tracing errors) are more like trigger scenarios than concrete capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' (troubleshoot systematically using the Scientific Method) and 'when' (explicit 'Use when' clause covering debugging crashes, tracing errors, diagnosing unexpected behavior, investigating exceptions). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'debugging', 'crashes', 'tracing errors', 'unexpected behavior', 'exceptions'. These are terms developers naturally use when seeking help with problems. | 3 / 3 |
Distinctiveness Conflict Risk | The debugging/troubleshooting domain is fairly broad and could overlap with language-specific debugging skills or error-handling skills. The 'Scientific Method' framing adds some distinctiveness, but terms like 'debugging' and 'errors' are common across many potential skills. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a concise, well-structured debugging methodology skill that effectively avoids verbosity and covers key concepts. However, it reads more like a philosophical framework than an actionable skill—it lacks concrete code examples, specific debugging commands, or executable demonstrations. The workflow would benefit from explicit feedback loops and the referenced bug report template should actually exist in the bundle.
Suggestions
Add concrete, executable debugging examples (e.g., a Python traceback with step-by-step diagnosis following the scientific method, or specific debugger commands like `pdb.set_trace()` or `git bisect` for binary search).
Add an explicit feedback loop in the scientific method: 'If experiment disproves hypothesis, return to OBSERVE with new data and form a new hypothesis.'
Either include the referenced `references/bug-report-template.md` file in the bundle or remove the broken reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every section adds value without explaining concepts Claude already knows. No unnecessary preamble or padding—just structured, actionable guidance. | 3 / 3 |
Actionability | The skill provides clear conceptual guidance (scientific method steps, anti-patterns, techniques like binary search and minimal repro) but lacks concrete, executable examples. There are no code snippets, specific commands, or copy-paste-ready debugging workflows—it describes strategies rather than demonstrating them. | 2 / 3 |
Workflow Clarity | The 5-step scientific method provides a clear sequence, but validation checkpoints are implicit rather than explicit. There's no feedback loop for when a hypothesis is disproven (e.g., 'if experiment fails, return to step 2'), and the VERIFY step lacks concrete criteria for what constitutes successful verification. | 2 / 3 |
Progressive Disclosure | The skill references a bug report template in a references directory, but the bundle confirms no such file exists. The content is well-organized with clear sections, but the broken reference and lack of any supporting files undermines the progressive disclosure structure. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- Repository
- HoangNguyen0403/agent-skills-standard
- Commit
3df717f
- 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.