Ready to supercharge your AI agents?

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

Get Started Free →

Systematic Debugging — measured AI agent skill | DecimalAI

archive228/systematic-debugging

SkillScore41Maintained

Use for ANY bug, test failure, crash, or unexpected behavior. Forces reproduce-then-isolate before proposing a fix. Stops the agent from guessing.

codingby archive228

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Coding pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/archive228-systematic-debugging/SKILL.md

decimalai skills pull archive228-systematic-debugging --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/archive228-systematic-debugging/SKILL.md https://app.decimal.ai/s/archive228-systematic-debugging/SKILL.md

Raw file: /s/archive228-systematic-debugging/SKILL.md ↗ · machine-readable summary at /s/archive228-systematic-debugging.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 4h ago

—+1% tokens0% turns41% of whole cases pass with skill (9/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-03	✗→✓	▲ Improved	-22%	0%
case-04	✗→✓	▲ Improved	9%	0%
case-05	✗→✓	▲ Improved	11%	0%
case-08	✗→✓	▲ Improved	42%	0%
case-11	✗→✓	▲ Improved	-8%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

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

archive228 / loopkit

skills/systematic-debugging/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Systematic Debugging

The single most expensive agent failure: seeing an error and immediately generating a "fix" based on the error type, without reading what actually happened. Don't.

The loop

Read the whole error. The entire message and stack trace. A TypeError can mean a

hundred different things — the trace tells you which one. Quote the exact line that throws.

Reproduce it first. If you can't reproduce it, you can't verify a fix. Write the

smallest input that triggers it. "I think this fixes it" is gambling, not debugging.

Form one hypothesis, name it. "I think the value is null because the upstream call

returns 204 with no body." State it before you touch anything.

Change one thing. Test. Repeat. If you change three things and it works, you don't

know which one fixed it — and the other two may have added new bugs.

Fix the root cause, not the symptom. A null check that hides a null is not a fix.

Find why it's null. The underlying bug will resurface differently if you only patch the crash.

Stop conditions

If 3 hypotheses fail, STOP and report: what you tried, what you saw, what you suspect.

"I've tried X and Y, here's the output, I think it's Z but I'm not sure" beats 20 silent random attempts.

Never add a workaround you don't understand.

Output

End with: the root cause (one sentence), the minimal fix, and the test that now proves it.

Want to see if archive228/systematic-debugging would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.