Ready to supercharge your AI agents?

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

Get Started Free →

Amazon · vellum-ai | DecimalAI

productivityby vellum-ai

Amazon

amazon

Source vellum-ai/vellum-assistant ↗License MIT

Shop on Amazon and Amazon Fresh through your browser

SkillScore55Maintained

Automatic

Personal Assistant pack

Last verified 7/28/2026

What it changes

Passed 9 of 17 test cases with the skill, and 1 of 17 without it.

Without skill5%

With skill55%

11 fixed1 passed either way10 still failing0 broke

Pass-rate lift: +50 pp
Tokens: -6%
Agent turns: 0%
Response time: -72%

Model gemini-3.6-flashMeasured 7/28/2026v112 of 22 cases passed with skill · 17 comparable

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/amazon/SKILL.md https://app.decimal.ai/s/amazon/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add amazon, 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/amazon/ and pins it in .decimal/skills.lock

decimalai skills add amazon

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

What's inside

The instructions your model reads when the skill loads.

SKILL.md140 lines7 filesincludes scripts

Use browser automation for all Amazon actions. All browser operations are executed through the assistant browser CLI, invoked via host_bash. Use helper scripts with host_bash to normalize extraction results and decide the next step.

Required tools

host_bash for assistant browser CLI commands and deterministic helper scripts under scripts/.

Hard constraints

Do not call assistant browser chrome relay.
Do not use legacy relay-backed scripts.
Always require explicit user confirmation before final order submission.

Step graph (state machine)

Step 1: Classify workflow state

Run this early in each turn when intent is unclear:

bun {baseDir}/scripts/amazon-intent.ts --request "<latest user request>" --checkout-reviewed <true|false> --has-cart-items <true|false>

Use the returned step to route to one of: search, variant_select, cart_review, checkout_review, fresh_slot, place_order.

Step 2: Product discovery (`search`)

Navigate to search results page:

assistant browser --session amazon navigate --url "https://www.amazon.com/s?k=<urlencoded query>"

Capture current state:

assistant browser --session amazon --json snapshot
assistant browser --session amazon --json extract --include-links

Parse candidates deterministically:

Track record

Benchmark

9 / 17

test cases passed, vs 1 / 17 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 v4 — 7/30/2026

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

vellum-ai / vellum-assistant

skills/amazon/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1Bundled 6 files · scripts

More skills from the same source and nearby in the registry, with their headline benchmark lift.