Ready to supercharge your AI agents?

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

Get Started Free →

Schema Diff — measured AI agent skill | DecimalAI

archive228/schema-diff

SkillScore91Maintained

Compare two schema states and surface the risky changes. Use before applying migrations or after a model change.

Databy archive228

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

Automatic

Data Engineer pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/archive228-schema-diff/SKILL.md

decimalai skills pull archive228-schema-diff --out .claude/skills/

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

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

Raw file: /s/archive228-schema-diff/SKILL.md ↗ · machine-readable summary at /s/archive228-schema-diff.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 6h ago

Yes — +18% lift-9% tokens0% turns91% of whole cases pass with skill (20/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-3%	0%
case-03	✗→✓	▲ Improved	-25%	0%
case-10	✗→✓	▲ Improved	-13%	0%
case-19	✗→✓	▲ Improved	-4%	0%
case-13	✗→✓	▲ Improved	-38%	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/schema-diff/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Schema Diff

Diff old vs new schema. Flag by risk:

Destructive (high): dropped column/table, narrowed type, new NOT NULL on existing rows, dropped index a query relies on.
Locking (high at scale): index without CONCURRENTLY, type change that rewrites the table.
Safe: new nullable column, new table, new index CONCURRENTLY.

For each destructive change: is data lost? is it reversible? is there a backfill? Output a risk-ranked list and a go/no-go with the safe rollout order.

Want to see if archive228/schema-diff 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.