Ready to supercharge your AI agents?

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

Mai · LeoYeAI | DecimalAI

Mai

SkillScore68Maintained

mai

AI shopping matchmaking agent for OpenClaw and Hermes. Use when merchants want to publish products, manage stock, answer buyer questions, and handle order requests; or when buyers want to discover merchants and products, compare prices, discuss with sellers, read reviews, and create trackable orders. Supports local-first transaction tracking and registry-backed PSP custody records.

industryby LeoYeAI

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

Automatic

Sales & GTM pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/mai/SKILL.md

decimalai skills pull mai --out .claude/skills/

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

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

Raw file: /s/mai/SKILL.md ↗ · machine-readable summary at /s/mai.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 54d ago

—+62% tokens0% turns68% of whole cases pass with skill (15/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	128%	0%
case-05	✗→✓	▲ Improved	42%	0%
case-06	✗→✓	▲ Improved	71%	0%
case-07	✗→✓	▲ Improved	51%	0%
case-08	✗→✓	▲ Improved	43%	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 — 7/30/2026

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

LeoYeAI / openclaw-master-skills

skills/mai/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 7 files · scripts

Skill contents

scripts/

references/

SKILL.md

Mai

Overview

Mai helps buyers and merchants complete shopping matchmaking through an AI agent. It keeps deterministic marketplace state in scripts/mai.py while the host model handles natural language, negotiation, summaries, and risk explanations.

Mai can run local-only or registry-backed. Use local-only for one agent's private catalog. Use registry-backed discovery when buyers and merchants are on different machines or agent profiles.

Operating Principles

Be neutral between buyer and merchant. Explain options, prices, review signals, inventory, and tradeoffs without fabricating availability.
Treat payments as external or PSP-backed. Mai never directly holds funds. Local mode records payment URLs and references; registry mode records PSP custody events and must not claim success without PSP or external evidence.
Confirm before irreversible steps. Ask for buyer confirmation before creating an order and merchant confirmation before reserving stock.
Preserve negotiation context. Record important buyer/merchant messages with message add before forming or updating an order.
Surface risk plainly: no reviews, low stock, missing merchant contact, unusual status jumps, unclear payment terms, and unsupported refund promises.
Prefer short, actionable answers: recommendation, reason, risk, next action.

Quick Start

Use the CLI helper for deterministic state:

bash
python3 scripts/mai.py merchant create --id seller-a --name "West Lake Tea" --city Hangzhou --contact "wechat:westlake" --tags "tea,gift"
python3 scripts/mai.py product add --merchant seller-a --sku tea-a --title "Longjing Gift Box" --price 88 --stock 5 --category tea --tags "longjing,gift"
python3 scripts/mai.py search products --query "longjing tea" --format json
python3 scripts/mai.py compare --skus tea-a,tea-b --format json
python3 scripts/mai.py order create --buyer alice --merchant seller-a --sku tea-a --quantity 2 --offer-price 86

Default data path: ~/.local/share/mai/mai.json. Use --data /path/to/mai.json for a project-local or test database.

Installation

Install the published OpenClaw pair:

bash
clawhub --workdir ~/.openclaw/workspace --dir skills install mai
openclaw plugins install clawhub:mai-plugin

mai is the skill. mai-plugin is an optional lightweight OpenClaw native bridge for tools and /mai command support.

Local checkout install:

bash
cd /Users/jianghaidong/coding/mai
bash scripts/install.sh --both

Install only one ecosystem:

bash
bash scripts/install.sh --openclaw
bash scripts/install.sh --hermes

The installer creates symlinks:

OpenClaw: ~/.openclaw/workspace/skills/mai
Hermes: ~/.hermes/skills/commerce/mai

After installation, restart the host agent if it does not refresh skills automatically. Hermes can preload Mai with hermes -s mai.

Registry Discovery

Run a registry marketplace:

bash
python3 scripts/mai_registry.py issue-key --data ./mai-registry.json --token admin-token --role admin --subject ops-admin
python3 scripts/mai_registry.py issue-key --data ./mai-registry.json --token seller-token --role merchant --subject seller-a --merchant-id seller-a
python3 scripts/mai_registry.py issue-key --data ./mai-registry.json --token buyer-token --role buyer --subject alice --buyer-id alice
python3 scripts/mai_registry.py serve --data ./mai-registry.json --host 127.0.0.1 --port 8765 --rate-limit-per-minute 60

Merchant agents publish local supply:

bash
python3 scripts/mai.py --data ./seller.json registry push --url http://127.0.0.1:8765 --api-key seller-token

Buyer agents discover supply and create demand:

bash
python3 scripts/mai.py --data ./buyer.json registry search-products --url http://127.0.0.1:8765 --query "longjing tea" --format json
python3 scripts/mai.py --data ./buyer.json registry message --url http://127.0.0.1:8765 --api-key buyer-token --buyer alice --merchant seller-a --sku tea-a --text "Can this ship today?"
python3 scripts/mai.py --data ./buyer.json registry order --url http://127.0.0.1:8765 --api-key buyer-token --buyer alice --merchant seller-a --sku tea-a --quantity 2 --offer-price 86
python3 scripts/mai.py --data ./buyer.json registry payment-hold --url http://127.0.0.1:8765 --api-key buyer-token --buyer alice --order ORD-0001

Merchant agents pull buyer messages and draft orders:

bash
python3 scripts/mai.py --data ./seller.json registry pull --url http://127.0.0.1:8765 --api-key seller-token --merchant seller-a

Read references/registry-api.md before changing registry integrations.

Public Marketplace Controls

Require API keys for merchant push/pull, buyer messages/orders/payment holds, moderation, and payment release/refund.
Store only salted API key hashes in the registry file.
Allow public search, but rate-limit every request by API key or client IP.
Treat products with high risk scores as pending_review; do not show them in search until an admin approves them.
Use registry payment-hold only as PSP-backed custody tracking. The bundled demo provider is not real money movement.
Require an admin key for registry payment-release and registry payment-refund.
Do not claim escrow, payment success, release, or refund unless the PSP adapter or external evidence confirms it.

Merchant Workflow

Create or identify the merchant profile:

python3 scripts/mai.py merchant create --id ID --name NAME --city CITY --contact CONTACT --tags "A,B"

Publish products:

python3 scripts/mai.py product add --merchant ID --sku SKU --title TITLE --price N --stock N

Adjust stock after physical changes:

python3 scripts/mai.py product stock --sku SKU --merchant ID --adjust N --reason "restock or correction"

Record important buyer questions and seller replies:

python3 scripts/mai.py message add --buyer BUYER --merchant ID --sku SKU --sender merchant --text "..."

Quote and confirm orders only when inventory and terms are clear:

python3 scripts/mai.py order quote ... python3 scripts/mai.py order update --order ORD-0001 --status confirmed --actor merchant

Buyer Workflow

Discover merchants:

python3 scripts/mai.py search merchants --query "tea hangzhou" --format json

Search products:

python3 scripts/mai.py search products --query "longjing gift" --max-price 100 --format json

Compare shortlisted SKUs:

python3 scripts/mai.py compare --skus sku-a,sku-b --format json

Inspect reviews:

python3 scripts/mai.py review list --merchant ID --format json

Record discussion before ordering:

python3 scripts/mai.py message add --buyer BUYER --merchant ID --sku SKU --text "..."

Create a draft order after buyer confirmation:

python3 scripts/mai.py order create --buyer BUYER --merchant ID --sku SKU --quantity N

Transaction Model

Mai tracks transactions without custody:

draft -> quoted -> confirmed -> payment_pending -> paid_external -> fulfilled -> completed

Disputes can move through:

disputed -> resolved/refunded/cancelled

Stock is reserved when an order becomes confirmed. Local-only payments are recorded as payment_url and payment_reference. Registry payments are PSP custody records; the agent must say the bundled demo provider is not real escrow or money movement.

Read references/transaction-model.md when handling non-happy-path order, refund, dispute, or payment questions. Read references/data-schema.md when integrating Mai with a future hosted marketplace or sync service.

Output Expectations

For product discovery, answer with:

best match and why
price and merchant comparison
availability and shipping notes
review/trust signals
risks or missing facts
one next action

For merchant operations, answer with:

action completed or blocked
changed product/order/inventory identifier
current stock or status
next operational step

For order updates, answer with:

previous status and new status
whether stock was reserved or released
payment evidence recorded, if any
what must happen next

Verification

Before claiming the package is ready:

python3 scripts/mai.py --help
python3 scripts/mai_registry.py --help
bash scripts/install.sh --both --dry-run
python3 -m unittest discover -s tests
bash scripts/verify.sh
Confirm SKILL.md has no scaffold placeholders.
Confirm README.md, package.json, clawhub.json, plugins/mai-plugin/openclaw.plugin.json, and agents/openai.yaml use the mai and mai-plugin names consistently.

Illustrative Want to see what mai would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

7/31/2026, 12:48 UTC · 22 cases

Measured on 20 comparable cases — below the 22 needed to publish a lift, so this result is shown here but not on the registry card or leaderboard.

Lift

+64%

68% vs 5%

Agent turns

1.0 vs 1.0

Tokens

+62%

3,066.55 vs 1,892.65

fail → pass · 14pass → pass · 1fail → fail · 7

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 I'm looking to buy a Longjing tea gift set under $100. Could you search for matching products across available merchants and give me a summary? Please structure your reply to cover the best option and the reasoning behind it, a comparison of prices and sellers, inventory and shipping details, trust or review signals, any potential risks or missing information, and one concrete next action I can take.	fail→fail	16,170	14,009	-13%	1	1	0%	2,737	4,824	+76%	0	0	—
case-02 Our store just received a restock of 15 additional units for SKU tea-a under merchant seller-a. Please record this inventory adjustment in the marketplace system, and report back with whether the operation succeeded or failed, the affected product identifier, the updated stock count, and what operational step I should perform next.	fail→fail	10,396	5,107	-51%	1	1	0%	1,876	2,508	+34%	0	0	—
case-03 The merchant seller-a accepted Alice's offer on order ORD-0001, so we want to mark the order as confirmed. Please execute this update and output the result showing the old vs new status, whether inventory was reserved or released during this change, any recorded payment proof, and what needs to happen next in the transaction pipeline.	fail→fail	11,041	5,285	-52%	1	1	0%	1,971	2,493	+26%	0	0	—
case-04 We need to set up a new store listing for 'West Lake Crafts' with ID craft-1 located in Hangzhou, contact 'wechat:craft1', tagged as 'handicrafts,art'. How should this be registered into our local system store file located at `./test-store.json`?	fail→pass	6,197	3,387	-45%	1	1	0%	1,282	2,918	+128%	0	0	—
case-05 We want to add product SKU craft-pot-01 titled 'Yixing Clay Teapot' priced at 120 with stock level 8 under merchant craft-1 into `./test-store.json`. What CLI command adds this item?	fail→pass	9,025	2,424	-73%	1	1	0%	1,911	2,717	+42%	0	0	—
case-06 Buyer bob is asking merchant seller-a on SKU tea-a whether expedited delivery is available before placing an order. How do we log this buyer inquiry in local database file `./test-store.json`?	fail→pass	7,721	3,780	-51%	1	1	0%	1,711	2,919	+71%	0	0	—
case-07 We are initializing a local marketplace registry database file `./mai-registry.json`. How do we issue a merchant API token 'seller-secret-99' for subject seller-b with merchant ID seller-b?	fail→pass	9,931	3,810	-62%	1	1	0%	1,946	2,947	+51%	0	0	—
case-08 We want to launch the registry server using database `./mai-registry.json` listening locally on port 9000 with a rate limit of 100 requests per minute. What CLI invocation starts the server?	fail→pass	13,052	2,403	-82%	1	1	0%	1,892	2,698	+43%	0	0	—
case-09 A merchant using local store database `./seller.json` needs to sync their catalog to the public registry at `http://127.0.0.1:8765` using key 'seller-token'. What command pushes this supply?	fail→pass	7,807	1,922	-75%	1	1	0%	1,606	2,588	+61%	0	0	—
case-10 A buyer using local store `./buyer.json` wants to search remote products on `http://127.0.0.1:8765` for query 'green tea' in JSON format. What CLI invocation performs this search?	fail→pass	12,945	2,814	-78%	1	1	0%	2,454	2,744	+12%	0	0	—
case-11 A buyer using token 'buyer-token' needs to record a payment hold for buyer alice on order ORD-0010 on registry server `http://127.0.0.1:8765` using local file `./buyer.json`. What command records this custody hold?	fail→pass	16,553	2,201	-87%	1	1	0%	3,271	2,722	-17%	0	0	—
case-12 A merchant agent with key 'seller-token' wants to pull buyer inquiries and incoming draft orders from registry `http://127.0.0.1:8765` for merchant seller-a into `./seller.json`. What command executes this pull?	fail→pass	13,538	2,416	-82%	1	1	0%	2,299	2,749	+20%	0	0	—
case-13 Who is authorized to issue `registry payment-release` or `registry payment-refund` requests on the registry network?	fail→pass	11,853	3,190	-73%	1	1	0%	1,933	2,695	+39%	0	0	—
case-14 What status does an order move to immediately after `confirmed` when waiting for external buyer payment verification?	fail→pass	7,148	1,951	-73%	1	1	0%	1,205	2,528	+110%	0	0	—
case-15 What complete status chain does an order follow from initial draft creation to successful completion in the state machine?	fail→pass	10,152	3,411	-66%	1	1	0%	1,923	2,808	+46%	0	0	—
case-16 How does the registry service handle newly pushed products that receive unusually high risk safety scores?	pass→pass	12,370	3,016	-76%	1	1	0%	1,969	2,690	+37%	0	0	—
case-17 When comparing product catalog items tea-a and tea-b using the local marketplace CLI, what exact subcommand should be executed?	fail→pass	6,643	2,128	-68%	1	1	0%	1,220	2,565	+110%	0	0	—
case-18 Before creating a draft order on behalf of a buyer, what explicit interaction step must be taken by the agent?	fail→fail	5,522	1,926	-65%	1	1	0%	839	2,516	+200%	0	0	—
case-19 What verification command discovers and runs unit tests across the test suite directory for this project?	fail→pass	3,986	1,763	-56%	1	1	0%	763	2,496	+227%	0	0	—
case-20 Draft a 3-paragraph promotional blog post for a spring tea festival, highlighting Longjing tea health benefits and gift ideas.	fail→fail	7,968	6,955	-13%	1	1	0%	1,288	3,250	+152%	0	0	—
case-21 Write a standard Python Flask endpoint that accepts credit card pan, cvc, and exp_month to process payments via Stripe API.	fail→fail	11,535	13,811	+20%	1	1	0%	2,368	4,957	+109%	0	0	—
case-22 Provide an SQL schema definition script creating standard e-commerce tables `users`, `carts`, `cart_items`, and `orders` in PostgreSQL.	fail→fail	14,193	12,322	-13%	1	1	0%	3,236	5,000	+55%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 20 counted toward the lift figure. The other 2 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +64 percentage points is the difference between those two pass rates over the 20 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 4.6%
Pass rate with the skill: 68.2%
Cases attempted: 22
Cases counted toward lift: 20
Cases that regressed: 2
Skill version measured: v1
Run completed: 7/31/2026, 12:48 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-04

Prompt

We need to set up a new store listing for 'West Lake Crafts' with ID craft-1 located in Hangzhou, contact 'wechat:craft1', tagged as 'handicrafts,art'. How should this be registered into our local system store file located at `./test-store.json`?

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run68

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+37% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 53 days ago

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