clawbench-cli 0.1.2__py3-none-any.whl

clawbench/data/test-cases/625-travel-camping-outdoor-parks-canada-reservations/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 625,
+    "metaclass": "travel",
+    "class": "camping-outdoor",
+    "description": "Register an account on the Parks Canada reservation portal, search for a 3-night campsite at Banff National Park (2 persons, electrical), select an available site and submit the reservation",
+    "sites_involved": [
+      "reservation.pc.gc.ca"
+    ],
+    "platform": "parks-canada-reservations",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "Register an account on the Parks Canada reservation portal, search for a 3-night campsite at Banff National Park (2 persons, electrical), select an available site and submit the reservation",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/626-travel-bus-flixbus/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 626,
+    "metaclass": "travel",
+    "class": "bus",
+    "description": "Book a one-way FlixBus ticket from New York to Washington D.C. departing 2026-08-15, select the cheapest departure, fill in passenger name and email and complete checkout",
+    "sites_involved": [
+      "flixbus.com"
+    ],
+    "platform": "flixbus",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "Book a one-way FlixBus ticket from New York to Washington D.C. departing 2026-08-15, select the cheapest departure, fill in passenger name and email and complete checkout",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/627-travel-flights-momondo/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 627,
+    "metaclass": "travel",
+    "class": "flights",
+    "description": "Search for a one-way economy flight from Toronto to Barcelona departing 2026-09-01 on Momondo, select the cheapest option and proceed to the passenger information page",
+    "sites_involved": [
+      "momondo.com"
+    ],
+    "platform": "momondo",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "Search for a one-way economy flight from Toronto to Barcelona departing 2026-09-01 on Momondo, select the cheapest option and proceed to the passenger information page",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/632-shopping-commerce-beauty-care-olaplex/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 632,
+    "metaclass": "shopping-commerce",
+    "class": "beauty-care",
+    "description": "Complete the Hair Quiz on Olaplex, add any quiz-recommended product to the cart, and proceed to checkout",
+    "sites_involved": [
+      "olaplex.com"
+    ],
+    "platform": "olaplex",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "Complete the Hair Quiz on Olaplex, add any quiz-recommended product to the cart, and proceed to checkout",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/634-shopping-commerce-apparel-dooney-bourke/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 634,
+    "metaclass": "shopping-commerce",
+    "class": "apparel",
+    "description": "Add a Pebble Grain crossbody bag (any color) to the cart on Dooney & Bourke, enter coupon code SAVE10 in the cart and click apply, then proceed to checkout",
+    "sites_involved": [
+      "dooney.com"
+    ],
+    "platform": "dooney-bourke",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "Add a Pebble Grain crossbody bag (any color) to the cart on Dooney & Bourke, enter coupon code SAVE10 in the cart and click apply, then proceed to checkout",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/635-shopping-commerce-gifts-uncommon-goods/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 635,
+    "metaclass": "shopping-commerce",
+    "class": "gifts",
+    "description": "On Uncommon Goods, add one item under $50 from the \"Gifts for Him\" section to cart and enter a shipping address",
+    "sites_involved": [
+      "uncommongoods.com"
+    ],
+    "platform": "uncommon-goods",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "On Uncommon Goods, add one item under $50 from the \"Gifts for Him\" section to cart and enter a shipping address",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/636-shopping-commerce-auto-parts-rockauto/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 636,
+    "metaclass": "shopping-commerce",
+    "class": "auto-parts",
+    "description": "On RockAuto, find a front brake rotor for a 2019 Ford F-150, select an Economy grade option, and add it to cart",
+    "sites_involved": [
+      "rockauto.com"
+    ],
+    "platform": "rockauto",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "On RockAuto, find a front brake rotor for a 2019 Ford F-150, select an Economy grade option, and add it to cart",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/638-shopping-commerce-print-custom-vistaprint/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 638,
+    "metaclass": "shopping-commerce",
+    "class": "print-custom",
+    "description": "On Vistaprint, design 250 standard business cards using a template, enter custom name, job title, and phone number, then add to cart",
+    "sites_involved": [
+      "vistaprint.com"
+    ],
+    "platform": "vistaprint",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "On Vistaprint, design 250 standard business cards using a template, enter custom name, job title, and phone number, then add to cart",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/639-shopping-commerce-luxury-mansur-gavriel/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 639,
+    "metaclass": "shopping-commerce",
+    "class": "luxury",
+    "description": "On Mansur Gavriel, add a Bucket Bag to cart with a selected color and size, then proceed to the checkout page",
+    "sites_involved": [
+      "mansurgavriel.com"
+    ],
+    "platform": "mansur-gavriel",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "On Mansur Gavriel, add a Bucket Bag to cart with a selected color and size, then proceed to the checkout page",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/671-entertainment-gaming-humble-bundle/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 671,
+    "metaclass": "entertainment-hobbies",
+    "class": "gaming",
+    "description": "Register an account on Humble Bundle, add a currently active game bundle to cart, set custom price to $15, and proceed to checkout",
+    "sites_involved": [
+      "humblebundle.com"
+    ],
+    "platform": "humble-bundle",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "Register an account on Humble Bundle, add a currently active game bundle to cart, set custom price to $15, and proceed to checkout",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/672-entertainment-hobbies-anime-streaming-crunchyroll/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 672,
+    "metaclass": "entertainment-hobbies",
+    "class": "anime-streaming",
+    "description": "Create an account on Crunchyroll and select the Mega Fan monthly subscription plan to complete the registration and payment flow",
+    "sites_involved": [
+      "crunchyroll.com"
+    ],
+    "platform": "crunchyroll",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "Create an account on Crunchyroll and select the Mega Fan monthly subscription plan to complete the registration and payment flow",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/674-entertainment-hobbies-masterclass-masterclass/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 674,
+    "metaclass": "entertainment-hobbies",
+    "class": "masterclass",
+    "description": "On MasterClass, select the Annual All-Access Pass plan, create an account, and reach the payment page with account and payment details filled in.",
+    "sites_involved": [
+      "masterclass.com"
+    ],
+    "platform": "masterclass",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "On MasterClass, select the Annual All-Access Pass plan, create an account, and reach the payment page with account and payment details filled in.",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/676-government-civic-legal-docs-legalnature/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 676,
+    "metaclass": "government-civic",
+    "class": "legal-docs",
+    "description": "On LegalNature, select Rental/Lease Agreement, choose California, fill in property address, landlord name, tenant name, monthly rent, and lease term, then generate the agreement",
+    "sites_involved": [
+      "legalnature.com"
+    ],
+    "platform": "legalnature",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "On LegalNature, select Rental/Lease Agreement, choose California, fill in property address, landlord name, tenant name, monthly rent, and lease term, then generate the agreement",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/685-personal-management-budget-mgmt-everydollar/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 685,
+    "metaclass": "personal-management",
+    "class": "budget-mgmt",
+    "description": "Create a monthly budget on EveryDollar: income $5000, add three expense categories \u2014 Housing $1500, Food $400, Transportation $300",
+    "sites_involved": [
+      "everydollar.com"
+    ],
+    "platform": "everydollar",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "Create a monthly budget on EveryDollar: income $5000, add three expense categories \u2014 Housing $1500, Food $400, Transportation $300",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/687-personal-management-vpn-subscription-ipvanish/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 687,
+    "metaclass": "personal-management",
+    "class": "vpn-subscription",
+    "description": "On IPVanish, compare monthly and annual plans, select the annual plan, and fill in the account registration form",
+    "sites_involved": [
+      "ipvanish.com"
+    ],
+    "platform": "ipvanish",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "On IPVanish, compare monthly and annual plans, select the annual plan, and fill in the account registration form",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/688-personal-management-insurance-compare-insurify/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 688,
+    "metaclass": "personal-management",
+    "class": "insurance-compare",
+    "description": "On Insurify, enter basic personal information and auto insurance preferences to receive quotes from at least 3 insurance companies",
+    "sites_involved": [
+      "insurify.com"
+    ],
+    "platform": "insurify",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "On Insurify, enter basic personal information and auto insurance preferences to receive quotes from at least 3 insurance companies",
+  "eval_schema": {
+    "url_pattern": "insurify\\.com/(?!cdn-cgi/)(?!.*static_user_pageview)(?!.*analytics)(?!.*tracking).*(quote|funnel|lead|insurance|compare|application)",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/695-automation-workflows-recurring-order-stumptown-coffee/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 695,
+    "metaclass": "automation-workflows",
+    "class": "recurring-order",
+    "description": "On Stumptown Coffee's website, select a medium roast coffee bean, set up a monthly subscription delivery for 2 bags, and submit the subscription",
+    "sites_involved": [
+      "stumptowncoffee.com"
+    ],
+    "platform": "stumptown-coffee",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "On Stumptown Coffee's website, select a medium roast coffee bean, set up a monthly subscription delivery for 2 bags, and submit the subscription",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/697-automation-workflows-recurring-order-bean-box/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 697,
+    "metaclass": "automation-workflows",
+    "class": "recurring-order",
+    "description": "On Bean Box, select a monthly subscription plan (monthly curated coffee box), choose 6-cup size with ground coffee, and reach the checkout page with shipping and payment details filled in.",
+    "sites_involved": [
+      "beanbox.com"
+    ],
+    "platform": "bean-box",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "On Bean Box, select a monthly subscription plan (monthly curated coffee box), choose 6-cup size with ground coffee, and reach the checkout page with shipping and payment details filled in.",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/699-automation-workflows-recurring-order-mistobox/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 699,
+    "metaclass": "automation-workflows",
+    "class": "recurring-order",
+    "description": "On Mistobox, complete a coffee subscription signup: select preferences (roast=medium-dark, grind=whole bean), choose a biweekly delivery plan, fill in shipping info, and submit",
+    "sites_involved": [
+      "mistobox.com"
+    ],
+    "platform": "mistobox",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "On Mistobox, complete a coffee subscription signup: select preferences (roast=medium-dark, grind=whole bean), choose a biweekly delivery plan, fill in shipping info, and submit",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/700-deletion-revocation-data-deletion-deleteme/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 700,
+    "metaclass": "deletion-revocation",
+    "class": "data-deletion",
+    "description": "On DeleteMe's website, select the Individual (1 person) subscription plan, submit personal information for data removal, and complete checkout",
+    "sites_involved": [
+      "joindeleteme.com"
+    ],
+    "platform": "deleteme",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "On DeleteMe's website, select the Individual (1 person) subscription plan, submit personal information for data removal, and complete checkout",
+  "eval_schema": {
+    "url_pattern": "__PLACEHOLDER_WILL_NOT_MATCH__",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/705-rating-voting-wine-review-vivino/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 705,
+    "metaclass": "rating-voting",
+    "class": "wine-review",
+    "description": "Submit a 4-star rating for a Pinot Noir on Vivino with exactly this tasting note: \"Light body, cherry notes, smooth finish.\"",
+    "sites_involved": [
+      "vivino.com"
+    ],
+    "platform": "vivino",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "Submit a 4-star rating for a Pinot Noir on Vivino with exactly this tasting note: \"Light body, cherry notes, smooth finish.\"",
+  "eval_schema": {
+    "url_pattern": "vivino\\.com/api/vintages/\\d+/reviews",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/706-rating-voting-beer-review-beeradvocate/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 706,
+    "metaclass": "rating-voting",
+    "class": "beer-review",
+    "description": "Submit a review for an Imperial Stout on BeerAdvocate with all dimension scores filled and exactly this comment: \"Rich malt, roasty aroma, full body.\"",
+    "sites_involved": [
+      "beeradvocate.com"
+    ],
+    "platform": "beeradvocate",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "Submit a review for an Imperial Stout on BeerAdvocate with all dimension scores filled and exactly this comment: \"Rich malt, roasty aroma, full body.\"",
+  "eval_schema": {
+    "url_pattern": "beeradvocate\\.com/beer/rate/\\d+",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/707-rating-voting-social-wine-untappd/task.json

@@ -0,0 +1,25 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 707,
+    "metaclass": "rating-voting",
+    "class": "social-wine",
+    "description": "Check in an IPA on Untappd with the highest star rating, and check out",
+    "sites_involved": [
+      "untappd.com"
+    ],
+    "platform": "untappd",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "Check in an IPA on Untappd with the highest star rating, and check out",
+  "eval_schema": {
+    "url_pattern": "^https://untappd\\.com/api/v2/shop/summaries/\\d+",
+    "method": "POST"
+  },
+  "time_limit": 30,
+  "extra_info": []
+}

clawbench/data/test-cases/708-rating-voting-professor-review-ratemyprofessors/task.json

@@ -0,0 +1,28 @@
+{
+  "$schema": "../task.schema.json",
+  "metadata": {
+    "task_id": 708,
+    "metaclass": "rating-voting",
+    "class": "professor-review",
+    "description": "Submit a rating for a Computer Science professor on RateMyProfessors: quality 4, difficulty 3, would take again Yes, with exactly this comment: \"Clear lectures, fair exams.\"",
+    "sites_involved": [
+      "ratemyprofessors.com"
+    ],
+    "platform": "ratemyprofessors",
+    "common_info": {
+      "email_credentials": "credentials to use the assigned disposable email account",
+      "user_info": "alex_green_personal_info.json; the dummy user's personal information",
+      "user_resume": "PDF resume with disposable email account injected"
+    }
+  },
+  "instruction": "Submit a rating for a Computer Science professor on RateMyProfessors: quality 4, difficulty 3, would take again Yes, with exactly this comment: \"Clear lectures, fair exams.\"",
+  "eval_schema": {
+    "url_pattern": "ratemyprofessors\\.com/graphql",
+    "method": "POST",
+    "body": {
+      "operationName": "RateTeacherMutation"
+    }
+  },
+  "time_limit": 30,
+  "extra_info": []
+}