systematic-debugging
Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions. Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
Install with Tessl CLI
npx tessl i github:secondsky/claude-skills --skill systematic-debuggingOverall
score
84%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 92%
↑ 1.16xAgent success when using this skill
Validation for skill structure
Discovery
90%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 well-structured description with explicit 'Use when' guidance and good trigger terms that developers would naturally use. The main weakness is that it doesn't specify what the four phases actually are, leaving the concrete capabilities somewhat abstract. The methodological focus ('Never jump to solutions') effectively distinguishes it from other debugging or coding skills.
Suggestions
Add brief mention of what the four phases are (e.g., 'reproduce, isolate, diagnose, verify') to increase specificity of capabilities
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (debugging) and mentions 'four-phase framework' and 'root cause investigation', but doesn't list the specific concrete actions or what the four phases actually are. | 2 / 3 |
Completeness | Clearly answers both what ('Four-phase debugging framework that ensures root cause investigation before attempting fixes') and when ('Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'bug', 'test failure', 'unexpected behavior', and 'fixes' - these are common terms developers use when encountering issues. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on debugging methodology with emphasis on 'before proposing fixes' - distinguishes it from general coding skills or fix-oriented skills. | 3 / 3 |
Total | 11 / 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 well-structured debugging framework with strong actionability and workflow clarity. The four-phase approach with explicit checkpoints and the '3+ fixes means architectural problem' rule are particularly valuable. However, the content is somewhat verbose with redundant sections (red flags, rationalizations, quick reference all covering similar ground) that could be consolidated for better token efficiency.
Suggestions
Consolidate the 'Red Flags', 'Common Rationalizations', and 'Quick Reference' sections - they repeat similar concepts and could be merged into a single concise reference
Consider moving the detailed multi-component diagnostic example to a separate EXAMPLES.md file, keeping just a brief inline example in the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy (multiple tables restating similar concepts, repeated 'STOP' warnings) and could be tightened. The rationalizations table and red flags section overlap significantly. | 2 / 3 |
Actionability | Provides concrete, executable guidance with specific bash examples for diagnostics, test commands (bun test, npm test), and clear step-by-step instructions. The multi-component diagnostic example is copy-paste ready. | 3 / 3 |
Workflow Clarity | Excellent four-phase workflow with explicit validation checkpoints, clear sequencing (must complete each phase before proceeding), and explicit feedback loops (Phase 4.4-4.5 for when fixes fail). The 3+ fixes threshold for architectural questioning is a strong validation checkpoint. | 3 / 3 |
Progressive Disclosure | References other skills appropriately (root-cause-tracing, defense-in-depth-validation, verification-before-completion) but the main content is somewhat monolithic. The skill could benefit from splitting detailed examples or the rationalizations table into separate reference files. | 2 / 3 |
Total | 10 / 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 — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 13 / 16 Passed | |
- 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.