Ready to supercharge your AI agents?

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

Get Started Free →

Bisect the Regression — measured AI agent skill | DecimalAI

archive228/bisect-regression

NewSkillScoreMaintained

Find the exact commit that introduced a bug. Use when something worked before and broke, and you don't know which change did it.

Testingby 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-bisect-regression/SKILL.md

decimalai skills pull archive228-bisect-regression --out .claude/skills/

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

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

Raw file: /s/archive228-bisect-regression/SKILL.md ↗ · machine-readable summary at /s/archive228-bisect-regression.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

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 2h ago

—-35% tokens0% turns83% of whole cases pass with skill (19/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-07	✗→✓	▲ Improved	-53%	0%
case-10	✗→✓	▲ Improved	-49%	0%
case-17	✓→✗	▼ Worse	4%	0%
case-04	✓→✓	＝ Same ✓	-55%	0%
case-05	✓→✓	＝ Same ✓	-40%	0%

Showing 5 of 23 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/bisect-regression/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Bisect the Regression

Find a known-good commit and a known-bad one. Confirm both by actually checking out and testing.
git bisect start; git bisect bad <bad>; git bisect good <good>.
At each step, run the SMALLEST test that distinguishes good from bad. Mark git bisect good/bad.
When git names the first bad commit, read its diff. The bug is in those lines — don't guess elsewhere.
git bisect reset. Report: the commit, the line, the one-sentence cause.

Automate it: git bisect run ./repro.sh if you have a script that exits non-zero on the bug.

Want to see if archive228/bisect-regression 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.