root-cause-tracing
Systematically trace bugs backward through call stack to find original trigger. Use when errors occur deep in execution and you need to trace back to find the original trigger.
78
72%
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 ./plugins/root-cause-tracing/skills/root-cause-tracing/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 clear structure with both 'what' and 'when' components, which is its strongest aspect. However, it lacks specificity in concrete actions and could benefit from more natural trigger terms that users would actually say when encountering this type of problem. The description is somewhat repetitive, with the 'when' clause largely restating the 'what' clause.
Suggestions
Add more specific concrete actions like 'analyzes stack traces, identifies error propagation paths, pinpoints root cause functions' to improve specificity.
Include more natural trigger terms users would say, such as 'stack trace', 'exception', 'traceback', 'root cause', 'crash', 'error chain', or 'debugging deep errors'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (debugging/bug tracing) and describes one core action (trace bugs backward through call stack), but doesn't list multiple specific concrete actions like setting breakpoints, analyzing stack frames, identifying root causes in specific contexts, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (systematically trace bugs backward through call stack to find original trigger) and 'when' (use when errors occur deep in execution and you need to trace back to find the original trigger) with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'bugs', 'call stack', 'errors', and 'trace back', but misses common user variations like 'stack trace', 'exception', 'crash', 'root cause analysis', 'debugging', 'traceback', or 'error origin'. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on call stack tracing provides some distinctiveness, but could overlap with general debugging skills, error handling skills, or logging/diagnostics skills. The phrase 'trace bugs backward through call stack' is somewhat specific but the broader framing of 'errors occur deep in execution' is fairly general. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid debugging methodology skill with clear, actionable steps and good workflow structure. Its main weakness is redundancy between the walkthrough example and the 'Real Example' section, which both use the same empty projectDir scenario. The instrumentation guidance is practical and executable, making this genuinely useful for debugging deep call-stack issues.
Suggestions
Merge the 'Real Example: Empty projectDir' section into the main tracing process walkthrough to eliminate redundancy and save tokens
Remove the 'Key Principle' section since it restates the overview's core principle verbatim
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but has some redundancy - the 'Real Example' section largely repeats the walkthrough from 'The Tracing Process' section with the same empty projectDir scenario. The 'Key Principle' section restates what was already said in the overview. Some trimming would improve token efficiency. | 2 / 3 |
Actionability | Provides concrete, executable code examples for instrumentation (stack trace logging), specific bash commands for capturing output, and a clear step-by-step tracing methodology with real code at each level. The debugging instrumentation pattern is copy-paste ready. | 3 / 3 |
Workflow Clarity | The 5-step tracing process is clearly sequenced (Observe → Immediate Cause → Trace Callers → Trace Values → Find Trigger). The defense-in-depth layers provide validation checkpoints. The workflow naturally includes a feedback loop of adding instrumentation, running, and analyzing results. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear headers and logical sections, but it's somewhat monolithic - the real example and the walkthrough example could potentially be separated. For a skill of this length (~100 lines of meaningful content), the inline approach is borderline acceptable but the repetition between sections suggests better organization is possible. | 2 / 3 |
Total | 10 / 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
- secondsky/claude-skills
- Commit
88da5ff
- 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.