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-debugging

What are skills?

Overall
score

84%

Review — 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/skill

Learn more

Evaluation — 92%

↑ 1.16x

Agent success when using this skill

Validation — 13 / 16 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

94%

34%

Data Pipeline Producing Incorrect Totals

Multi-component diagnostic instrumentation

Criteria

Without context

With context

Pre-fix instrumentation

87%

Boundary data logging

33%

83%

Layer identification from evidence

70%

100%

Root cause not symptom

100%

No symptom-layer fix

100%

Single focused fix

100%

Evidence-first run

86%

Investigate-then-fix sequence

38%

92%

Fix verification

100%

Single component changed

100%

81%

Fix Incorrect Day-of-Week Calculation

Test-first hypothesis-driven fix

Criteria

Without context

With context

Test file exists

100%

Test targets the bug

100%

Test written before fix

29%

57%

Single documented hypothesis

100%

Hypothesis identifies root cause

100%

Bun as test runner

Minimal single fix

92%

100%

countBusinessDays unchanged

100%

No bundled improvements

100%

Fix verified

70%

100%

Fix a Retry Decorator to Match the Reference Implementation

Complete reference reading and difference listing

Criteria

Without context

With context

Comparison document exists

100%

Loop boundary difference found

100%

Sleep-after-last-failure found

100%

Both differences documented

100%

Behavioral impact explained

100%

Analysis precedes fix

100%

Loop boundary fixed

100%

Sleep guard fixed

100%

No extra changes

100%

Fix matches reference

100%

Evaluated: 11 days ago
Agent: Claude Code

Table of Contents

Data Pipeline Producing Incorrect Totals Fix Incorrect Day-of-Week Calculation Fix a Retry Decorator to Match the Reference Implementation

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.