Applies systematic tracing and isolation techniques to pinpoint exactly where a bug originates in code. Use when a bug is hard to locate, code is not working as expected, an error or crash appears with unclear cause, a regression was introduced between recent commits, or you need to narrow down which component, function, or line is faulty. Covers binary search debugging, git bisect for regressions, strategic logging with [TRACE] patterns, data and control flow tracing, component isolation, minimal reproduction cases, conditional breakpoints, and watch expressions across TypeScript, SQL, and bash.
79
75%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./packages/core/src/methodology/packs/debugging/trace-and-isolate/SKILL.mdQuality
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 an excellent skill description that hits all the marks. It provides specific concrete techniques, includes a comprehensive 'Use when...' clause with natural trigger scenarios, and carves out a distinct niche around bug localization and tracing. The description is detailed yet focused, using third person voice throughout and covering both the methods and the contexts in which the skill should be selected.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and techniques: binary search debugging, git bisect, strategic logging with [TRACE] patterns, data and control flow tracing, component isolation, minimal reproduction cases, conditional breakpoints, and watch expressions. Also specifies languages covered (TypeScript, SQL, bash). | 3 / 3 |
Completeness | Clearly answers both 'what' (systematic tracing and isolation techniques, with specific methods listed) and 'when' (explicit 'Use when...' clause covering multiple trigger scenarios like hard-to-locate bugs, unclear errors, regressions, and component isolation needs). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'bug', 'not working as expected', 'error', 'crash', 'regression', 'narrow down', 'faulty', 'debugging', 'git bisect', 'breakpoints'. These are terms users naturally use when seeking debugging help. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly carved out niche focused specifically on bug localization and tracing techniques, distinct from general debugging or code review skills. The specific techniques (git bisect, binary search debugging, [TRACE] patterns) and the focus on pinpointing bug origins make it unlikely to conflict with broader coding or testing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a solid catalog of debugging techniques with good structure and a useful quick-reference table. Its main weaknesses are that several sections rely on pseudocode or conceptual diagrams rather than fully executable examples, and the document is somewhat long without leveraging progressive disclosure to external files. Adding an explicit meta-workflow (which technique to try first and how to escalate) and a verification feedback loop after isolation would significantly improve it.
Suggestions
Add an overarching decision workflow at the top: 'Start with X, if that doesn't narrow it down, try Y' — with an explicit verification step ('confirm fix by reverting and re-applying') to close the feedback loop.
Replace pseudocode sections (Code Path Binary Search, Component Isolation flow) with executable or tool-specific examples (e.g., actual debugger commands, actual mock setup code).
Extract the 'Common Isolation Patterns' section (database, network, time) into a separate PATTERNS.md reference file to reduce the main skill's length and improve progressive disclosure.
Add a brief 'after finding the bug' verification step: confirm the hypothesis by applying a fix and running the minimal reproduction to validate, which would strengthen the workflow's feedback loop.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some content Claude already knows (e.g., explaining what binary search debugging is conceptually, the data flow tracing diagram is somewhat obvious). The quick reference table is good, but several sections could be tightened—for instance, the environment isolation checklist and some of the pseudocode-style flow diagrams add bulk without proportional value. | 2 / 3 |
Actionability | The git bisect section provides fully executable commands, and the TypeScript logging examples are concrete and copy-paste ready. However, many sections use pseudocode or conceptual diagrams rather than executable code (e.g., the 'Code Path Binary Search' section, the 'Component Isolation' section with ASCII flow diagrams, and the 'Minimal Reproduction' section which is purely instructional). The breakpoint strategies section describes placement with comments rather than showing tool-specific commands. | 2 / 3 |
Workflow Clarity | The binary search debugging section has a clear sequence, and git bisect has explicit steps. However, there's no overarching workflow tying the techniques together (e.g., 'start here, then try this if that doesn't work'). The 'When to Move On' section is a good exit criterion but there's no validation/verification step after finding the bug—no 'confirm your hypothesis by fixing and testing' feedback loop. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and a useful quick reference table at the top. However, at ~180 lines this is a fairly long monolithic document with no references to external files. Some sections (like the common isolation patterns with database, network, and time examples) could be split into a separate reference file to keep the main skill leaner. | 2 / 3 |
Total | 8 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
a9e5c83
Table of Contents
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.