Ready to supercharge your AI agents?

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

near-recipe — measured AI agent skill | DecimalAI

galelmalah/near-recipe

SkillScore86Maintained

Slightly drifted variant of a baking recipe used to validate that near-duplicate detection clusters skills that share most of their content but not all of it.

by galelmalah

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

Automatic

Personal Assistant pack

decimalai skills pull galelmalah-near-recipe

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/galelmalah-near-recipe/SKILL.md

Raw file: /s/galelmalah-near-recipe/SKILL.md ↗ · machine-readable summary at /s/galelmalah-near-recipe.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 7d ago

Yes — +41% lift-53% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	-63%	0%
case-03	✗→✓	▲ Improved	-66%	0%
case-07	✗→✓	▲ Improved	-77%	0%
case-09	✗→✓	▲ Improved	-67%	0%
case-10	✗→✓	▲ Improved	-46%	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 — 8/1/2026

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

galelmalah / skillview

crates/skillview/tests/fixtures/home/.claude/skills/near-recipe/SKILL.md

View on GitHub ↗

Imported 8/1/2026Version v2

Skill contents

SKILL.md

near-recipe

The body here intentionally overlaps heavily with another skill of the same name so that MinHash clusters them as a near-duplicate while the content hash stays distinct.

Steps

Combine flour, sugar, and softened butter in a mixing bowl.
Whisk together until the dough is smooth and slightly glossy.
Bake at 180 degrees Celsius for twenty-five minutes.
Cool on a wire rack before serving.
Slice into squares for portioning before serving.
Pair with coffee or tea for the best flavor experience overall.

Want to see if galelmalah/near-recipe 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.