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.

Install with Tessl CLI

npx tessl i github:wshobson/agents --skill debugging-strategies

What are skills?

Review — 66%

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 — 95%

Agent success when using this skill

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

96%

-4%

Slow Report Aggregation Investigation

Python performance profiling

Criteria

Without context

With context

cProfile used

100%

90%

pstats Stats used

100%

75%

sort_stats cumulative

100%

print_stats called

100%

87%

Profile output included

100%

Measurement before fix

100%

Measurement after fix

100%

Root cause identified

100%

Root cause fixed

100%

Findings documented

100%

Without context: $0.3556 · 2m 1s · 10 turns · 11 in / 6,461 out tokens

With context: $0.7724 · 3m 39s · 22 turns · 71 in / 12,157 out tokens

91%

Order Processing Service Bug

Systematic bug investigation

Criteria

Without context

With context

Observations documented

100%

Hypotheses stated

30%

50%

Experiment described

80%

90%

Analysis included

100%

Root cause identified

100%

Root cause fixed

100%

Single targeted change

75%

62%

No debug artifacts

100%

Information gathered

90%

100%

Findings documented

100%

Without context: $0.3584 · 1m 47s · 13 turns · 13 in / 5,493 out tokens

With context: $0.7233 · 2m 57s · 23 turns · 419 in / 9,467 out tokens

99%

Payment Checkout Failure Investigation

Production incident investigation

Criteria

Without context

With context

No production changes

100%

Evidence gathering first

100%

Staging before prod

100%

Differential table

33%

100%

Recent changes checked

100%

Hypotheses formed

100%

Failure modes covered

100%

Local reproduction steps

87%

git bisect commands

100%

Bisect test described

100%

Without context: $0.2930 · 2m · 8 turns · 9 in / 5,849 out tokens

With context: $0.5396 · 2m 57s · 16 turns · 304 in / 8,384 out tokens

Evaluated: 3 days ago
Agent: Claude Code

Table of Contents

Slow Report Aggregation Investigation Order Processing Service Bug Payment Checkout Failure Investigation

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.