debugging-strategies
Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.
64
47%
Does it follow best practices?
Impact
95%
1.01xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/developer-essentials/skills/debugging-strategies/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description has a solid structure with an explicit 'Use when' clause, which is its strongest aspect. However, it relies on abstract category names ('systematic debugging techniques,' 'profiling tools') rather than listing concrete actions, and the scope is overly broad ('any codebase or technology stack'), which reduces both specificity and distinctiveness. The word 'Master' at the beginning reads as aspirational rather than descriptive of what the skill actually does.
Suggestions
Replace abstract categories with concrete actions, e.g., 'Analyze stack traces, set breakpoints, profile memory and CPU usage, inspect logs, and isolate root causes of failures.'
Expand trigger terms in the 'Use when' clause to include natural user language like 'error,' 'crash,' 'slow performance,' 'memory leak,' 'exception,' 'stack trace,' or 'not working.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (debugging) and mentions some actions like 'debugging techniques, profiling tools, and root cause analysis,' but these are still fairly abstract categories rather than concrete specific actions like 'set breakpoints, analyze stack traces, profile memory usage.' | 2 / 3 |
Completeness | Clearly answers both 'what' (systematic debugging techniques, profiling tools, root cause analysis to track down bugs) and 'when' with an explicit 'Use when investigating bugs, performance issues, or unexpected behavior' clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'bugs,' 'performance issues,' 'unexpected behavior,' and 'debugging,' but misses common natural variations users might say such as 'error,' 'crash,' 'stack trace,' 'slow,' 'memory leak,' 'exception,' or 'breakpoint.' | 2 / 3 |
Distinctiveness Conflict Risk | While debugging is a recognizable domain, the phrase 'across any codebase or technology stack' is extremely broad and could overlap with many code-related skills. The triggers 'bugs' and 'unexpected behavior' are somewhat generic and could conflict with testing or code review skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a generic debugging tutorial or blog post than a targeted skill for Claude. It is extremely verbose, explaining well-known concepts (scientific method, rubber duck debugging, 'take breaks') that waste context window tokens. While it contains some useful executable code snippets, the majority of content is abstract checklists and motivational advice rather than actionable, Claude-specific guidance.
Suggestions
Cut at least 60% of the content by removing generic debugging wisdom Claude already knows (scientific method, mindset advice, 'read error messages,' rubber duck debugging) and focus only on concrete tool usage and commands.
Move the language-specific debugging code examples into referenced bundle files (e.g., references/debugging-tools-guide.md) and keep SKILL.md as a concise overview with clear pointers, or actually provide the referenced bundle files.
Replace the abstract markdown checklists (Phase 1-4) with a single concrete workflow that includes explicit validation steps, e.g., 'After applying fix → run failing test → confirm pass → run full suite → confirm no regressions.'
Remove or consolidate the 'Common Debugging Mistakes' and 'Best Practices' sections which overlap heavily and contain only generic advice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and padded with content Claude already knows. Explains basic concepts like 'the scientific method,' 'rubber duck debugging,' and 'read error messages.' The mindset advice ('take breaks,' 'question everything') and common debugging mistakes are generic wisdom that wastes tokens. Much of the content is markdown-within-markdown checklists that restate obvious debugging principles. | 1 / 3 |
Actionability | Contains some executable code examples (pdb, Chrome DevTools, git bisect, VS Code launch.json), but much of the skill is abstract checklists and markdown tables rather than concrete, copy-paste-ready commands. Many sections like 'Debugging Patterns by Issue Type' are vague strategy lists ('add extensive logging,' 'profile first') rather than specific executable guidance. | 2 / 3 |
Workflow Clarity | The four-phase process (Reproduce → Gather Info → Hypothesize → Test) provides a clear sequence, but validation checkpoints are absent. There are no explicit feedback loops for verifying that a fix actually resolves the issue, and the phases themselves are filled with generic checklists rather than concrete verification steps. | 2 / 3 |
Progressive Disclosure | The skill is a monolithic wall of text (~400+ lines) with everything inline. It references six external files (references/debugging-tools-guide.md, scripts/debug-helper.ts, etc.) at the bottom, but no bundle files are provided, making these dead references. The massive inline content should have been split across those referenced files. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (537 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- Dicklesworthstone/pi_agent_rust
- Commit
895269a
- 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.