Ready to supercharge your AI agents?

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

Get Started Free →

Systematic Debugging · hashgraph-online | DecimalAI

codingby hashgraph-online

Systematic Debugging

hashgraph-online/systematic-debugging

Source hashgraph-online/awesome-codex-plugins ↗License Apache-2.0

提供系统化根因定位流程，避免在复杂缺陷里靠猜测叠加修补。当问题难复现、跨模块、连续修错或需要先证明根因再改代码时使用。

SkillScore87Maintained

Automatic

Coding pack

Last verified 8/17/2026

What it changes

Passed 20 of 23 test cases with the skill, and 11 of 23 without it.

Without skill48%

With skill87%

Checks it passed that the model alone missed

The strategy limits active testing to 1 to 3 specific hypotheses.
The response emphasizes never fixing what has not been reproduced.
The response requires obtaining a minimal reproduction case first.

and 10 more in the full report

9 fixed11 passed either way3 still failing0 broke

Pass-rate lift: +39 pp
Tokens: -31%
Agent turns: 0%
Response time: -41%

Model gemini-3.6-flashMeasured 8/17/2026v220 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/hashgraph-online-systematic-debugging/SKILL.md https://app.decimal.ai/s/hashgraph-online-systematic-debugging/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add hashgraph-online-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/hashgraph-online-systematic-debugging/ and pins it in .decimal/skills.lock

decimalai skills add hashgraph-online-systematic-debugging

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

We have finished fixing a critical deadlock in our C++ thread pool manager. The reproduction test passes reliably and all regression suites passed. What tool command should be invoked before completing the workflow?

What was checked, without and with the skill
Checked	Without skill	With skill
The response specifies invoking `hotl:verification-before-completion`.	Missed	Passed

case-14 · gemini-3.6-flash · 8/17/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md29 linessingle file

Systematic Debugging

Four Phases

Phase 1: Reproduce

Get a minimal, reliable reproduction
Never fix what you can't reproduce

Phase 2: Understand

Read the error message fully — the answer is often there
Trace the call path from symptom to root cause
Check: recent changes, environment differences, assumptions about inputs

Phase 3: Hypothesize

Form 1-3 specific hypotheses about root cause
Test each hypothesis with the smallest possible change
Never change multiple things at once

Phase 4: Fix and Verify

Fix the root cause, not the symptom
Run the reproduction case — confirm fixed
Run full test suite — confirm no regressions
Invoke hotl:verification-before-completion

Red Flags

"Let me try X and see what happens" without a hypothesis
Changing multiple things before verifying
Marking done without running full tests

Track record

Benchmark

20 / 23

test cases passed, vs 11 / 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 — 8/17/2026

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

hashgraph-online / awesome-codex-plugins

plugins/Colin4k1024/tsp/skills/systematic-debugging/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/17/2026Version v2

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.

Ready to supercharge your AI agents?

See it in action

What's inside

Systematic Debugging

Four Phases

Phase 1: Reproduce

Phase 2: Understand

Phase 3: Hypothesize

Phase 4: Fix and Verify

Red Flags

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills