Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Systematic Debugging · jnmetacode | DecimalAI

codingby jnmetacode

Systematic Debugging

jnmetacode/systematic-debugging

Source jnmetacode/skillet ↗License MIT

Root-cause a bug with a hypothesis-driven loop instead of shotgun edits.

SkillScore87Maintained

Automatic

Coding pack

Last verified 9/8/2026

What it changes

Passed 20 of 23 test cases with the skill, and 15 of 23 without it.

Without skill65%

With skill87%

Checks it passed that the model alone missed

The response refuses to skip the root cause investigation phase despite production urgency.
The response directs to halt fix attempts and return to Stage 1 to collect empirical evidence.
The response directs to discuss or re-evaluate the system architecture before making any new fix attempt.

and 4 more in the full report

5 fixed15 passed either way3 still failing0 broke

Pass-rate lift: +22 pp
Tokens: +105%
Agent turns: 0%
Response time: -11%

Model gemini-3.6-flashMeasured 9/8/2026v320 of 23 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/jnmetacode-systematic-debugging/SKILL.md https://app.decimal.ai/s/jnmetacode-systematic-debugging/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add jnmetacode-systematic-debugging, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/jnmetacode-systematic-debugging/ and pins it in .decimal/skills.lock

decimalai skills add jnmetacode-systematic-debugging

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/jnmetacode-systematic-debugging/SKILL.md https://app.decimal.ai/s/jnmetacode-systematic-debugging/SKILL.md

Raw file: /s/jnmetacode-systematic-debugging/SKILL.md ↗ · machine-readable summary at /s/jnmetacode-systematic-debugging.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 5

Prompt

I am debugging an intermittent API 500 error in our Node.js microservice. I have already applied 3 different fixes to the controller and database layer, but none of them solved the problem. What should my next step be? Should I attempt a 4th fix by rewriting the query builder logic?

What was checked, without and with the skill
Checked	Without skill	With skill
The response instructs to stop attempting further code fixes.	Passed	Passed
The response directs to discuss or re-evaluate the system architecture before making any new fix attempt.	Missed	Passed

case-02 · gemini-3.6-flash · 9/8/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md278 linessingle file

系统化调试

概述

核心原则： 在尝试修复之前，务必先找到根本原因。只修症状就是失败。

敷衍走流程等于违背调试的精神。

铁律

不做根因调查，不许提修复方案

如果你还没完成第一阶段，就不能提出修复方案。

何时使用

用于任何技术问题：

测试失败
生产环境 bug
异常行为
性能问题
构建失败
集成问题

尤其在以下情况必须使用：

时间紧迫（紧急情况最容易让人猜测式修复）
觉得"一个小修改"就能搞定
已经尝试了多种修复
上一次修复没有生效
你没有完全理解问题

以下情况也不要跳过：

问题看起来很简单（简单的 bug 也有根本原因）
你很赶时间（越急越容易返工）
领导要求立刻修好（系统化调试比反复尝试更快）

四个阶段

Track record

Benchmark

20 / 23

test cases passed, vs 15 / 23 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/8/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

jnmetacode / skillet

skills/systematic-debugging/SKILL.md

View on GitHub ↗

License MITImported 9/8/2026Version v3

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.