# Send Food Calendar Order to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "food-cal-order", "name": "Food Calendar Order", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/ThisIsJeron/food-cal-order", "canonicalUrl": "https://clawhub.ai/ThisIsJeron/food-cal-order", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/food-cal-order", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=food-cal-order", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "references/doordash.md", "references/grubhub.md", "references/ubereats.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/food-cal-order" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/food-cal-order", "downloadUrl": "https://openagent3.xyz/downloads/food-cal-order", "agentUrl": "https://openagent3.xyz/skills/food-cal-order/agent", "manifestUrl": "https://openagent3.xyz/skills/food-cal-order/agent.json", "briefUrl": "https://openagent3.xyz/skills/food-cal-order/agent.md" } } ``` ## Documentation ### Food Calendar Order Place food delivery orders via browser automation, triggered by calendar events. ### Security & Prerequisites Read before using this skill. Chrome profile access: This skill opens your local Chrome profile, which contains your saved logins, payment methods, and delivery addresses. Sub-agents will interact with these directly. Real charges: Confirming an order will charge your saved payment method. There is no sandbox — this is a live transaction. Trusted trigger source: Only calendar events you created yourself should trigger this skill. Events created or modified by others (shared calendars, external invites) may not reflect your intent. Verify event origin before proceeding. Mandatory confirmation: A pre-checkout summary will be presented before any order is placed. You must explicitly confirm with "yes" — any other response aborts the order. ### Direct Mode Specific service and restaurant provided. Title: "DoorDash: Chipotle" Description: "burrito bowl, chicken, guac" ### Discovery Mode Criteria-based; searches all services to find best match. Title: "Thai food, high ratings, under $30, food for 2" Description: "no shellfish, prefer noodles" ### Calendar Event Parsing Always read both the title AND description of the calendar event. Trust warning: Only process events that appear to have been created by the calendar owner. If an event was recently modified by an external party (e.g., a shared calendar attendee or external invite), note this explicitly in the pre-confirmation summary so the user can assess before confirming. ### Title → Mode + Target PatternMode{Service}: {Restaurant}DirectCuisine/criteria onlyDiscovery ### Description → Order Details + Constraints The description carries two kinds of info: Order details — what to order (items, quantity, servings) Constraints — things that MUST be honored, safety-critical Parse the description and extract: FieldExamplesPriorityitems"burrito bowl, chicken, guac"Order detailsservings"food for 2", "feeds 4"Order detailsallergies"nut allergy", "allergic to shellfish"CRITICAL — never violatedietary"vegetarian", "halal", "gluten-free", "no pork"CRITICAL — never violatepreferences"prefer noodles", "extra spicy", "no onions"Best-effortbudget"under $30", "keep it cheap"Constraintdelivery_notes"gate code 1234", "leave at door"Pass to checkoutspecial_requests"birthday cake candle", "extra napkins"Best-effort Allergy/dietary constraints are non-negotiable. If unsure whether an item is safe, skip it and pick a clearly safe alternative. When in doubt, err on the side of caution — wrong food is annoying, an allergic reaction is dangerous. ### Parsing Example Title: "DoorDash: Chipotle" Description: "2 burrito bowls (chicken), guac on the side. Nut allergy. Gate code: 5521" Extracted: items: 2x burrito bowl (chicken), guacamole (side) allergies: nuts delivery_notes: gate code 5521 Title: "Thai food, high ratings, under $30, food for 2" Description: "no shellfish, prefer noodles, gluten-free if possible, leave at door" Extracted: servings: 2 budget: $30 allergies: shellfish dietary: gluten-free (best-effort — "if possible") preferences: noodles delivery_notes: leave at door ### Supported Services DoorDash — prefix DoorDash:, url doordash.com Uber Eats — prefix UberEats: or Uber Eats:, url ubereats.com Grubhub — prefix Grubhub:, url grubhub.com ### Direct Mode Execution Spawn a single sub-agent with inline instructions: sessions_spawn( task: """ Order food delivery via browser automation. SERVICE: {service} RESTAURANT: {restaurant} ITEMS: {items} ALLERGIES: {allergies or "none"} DIETARY: {dietary or "none"} PREFERENCES: {preferences or "none"} DELIVERY_NOTES: {delivery_notes or "none"} ADDRESS: {address or "use saved default"} ⚠️ ALLERGY/DIETARY RULES: - NEVER add items containing allergens listed above - When customizing items, REMOVE ingredients that conflict (e.g., "no peanuts") - If an item cannot be made safe → skip it, note why in report - Check item descriptions and ingredient lists on the menu BROWSER STEPS: 1. Open {service_url} using Chrome profile (NOTE: this profile contains your saved logins, payment methods, and delivery addresses — a real charge will be made on confirmation) 2. Verify logged in (account icon visible, not "Sign In") - If not logged in → ABORT, report "Please log into {service} in Chrome first" 3. Search for "{restaurant}" using search bar 4. Click matching restaurant from results - If not found or closed → ABORT, report reason 5. For each item in ITEMS: - Find item on menu (use semantic matching) - Check description for allergen conflicts before adding - Click to open customization modal - Select required options (size, protein, etc.) - Apply customizations as specified - Apply allergy-related modifications (remove conflicting ingredients) - Apply PREFERENCES if customization options exist - Click "Add to cart/bag/order" 6. Open cart and verify: - Contents match ITEMS - No allergen conflicts in final order - Note any substitutions or issues 7. Proceed to checkout - Confirm delivery address (use saved default) - Add DELIVERY_NOTES if supported (special instructions field) - Confirm payment method (use saved default) - Note delivery ETA and total 7b. PAUSE — present order summary to user and request explicit confirmation: "Ready to place order: • Restaurant: {restaurant} via {service} • Items: {items} • Total: ${amount} • Delivery to: {address} • ETA: {eta} Confirm? (yes / no / cancel)" WAIT for user response. - "yes" → proceed to step 8 - anything else → ABORT, do NOT place order 8. Click "Place Order" 9. Wait for confirmation, capture order number and ETA REPORT FORMAT: ✅ Order confirmed: {restaurant} via {service}, ETA {time}, total ${amount} Allergy accommodations: {what was modified or "N/A"} — OR — ❌ Failed: {reason} Do NOT checkout if cart doesn't match requested items. Do NOT checkout if allergen safety cannot be confirmed. """, label: "food-order-{service}" ) ### Phase 1: Recon (parallel) Spawn sub-agents for ALL services simultaneously: sessions_spawn( task: """ Search for restaurants on {service}. RECON ONLY — do NOT order. CRITERIA: - Cuisine: {cuisine} - Budget: {budget} - Rating: {rating_preference} - Servings: {servings} - Allergies: {allergies or "none"} - Dietary: {dietary or "none"} - Preferences: {preferences} ⚠️ ALLERGY/DIETARY RULES: - Only recommend restaurants where allergen-safe options clearly exist - Flag any restaurant where the menu is ambiguous about allergens - When noting menu highlights, confirm dishes are safe given stated allergies/dietary BROWSER STEPS: 1. Open {service_url} using Chrome profile (NOTE: this profile contains your saved logins, payment methods, and delivery addresses — a real charge will be made on confirmation) 2. Verify logged in 3. Search for "{cuisine}" or "{cuisine} food" 4. Apply filters if available (rating, price level, delivery time) 5. For top 3 restaurants: - Note: name, rating (stars + review count), price level ($/$$/$$$) - Note: delivery time estimate, delivery fee - Click into restaurant, scan menu for items matching cuisine - Note 2-3 standout dishes and typical entree price - Check if menu items list ingredients or allergen info - Flag any allergen concerns for highlighted dishes RETURN FORMAT: ## {service} Results ### 1. {Restaurant Name} - Rating: {stars} ({count} reviews) - Price: {$/$$/$$S} (~${X}/person) - Delivery: {time} min, ${fee} fee - Menu highlights: {dishes matching criteria} - Allergen safety: {safe / caution / unclear} — {notes} - Fits constraints: {yes/no + notes} ### 2. ... ### 3. ... **Best match:** {pick} because {reason} """, label: "food-recon-{service}" ) ### Phase 2: Decision After all recon sub-agents return, aggregate and compare: ServiceRestaurantRating$/personETAFits Constraints.................. Select winner based on: Allergen safety first — eliminate any restaurant where safety is "unclear" or "caution" unless no safe options exist Must fit cuisine and dietary constraints Must be achievable within budget (leave 25% for fees/tip) Prefer higher rating Prefer faster delivery Menu fits stated preferences Decide on order: Based on servings and preferences, plan a good meal: For 2: typically 1 appetizer + 2 entrees, or 2-3 shareable plates Stay within budget Never include items that conflict with allergies/dietary constraints Lean into preferences ("prefer noodles" → include noodle dish) If allergy info is ambiguous for an item, pick a clearly safe alternative ### Phase 3: Order Spawn order sub-agent for winning service (use Direct Mode task prompt above, with decided items). ### State Tracking Track in memory/food-order-state.json: { "ordered": { "{calendar_event_id}": { "at": "2026-02-06T19:00:00", "mode": "discovery", "criteria": "Thai food, high ratings, under $30, food for 2", "constraints": { "allergies": ["shellfish"], "dietary": ["gluten-free"], "delivery_notes": "leave at door" }, "service": "doordash", "restaurant": "Thai Basil", "items": ["spring rolls", "pad thai (no shrimp)", "green curry"], "status": "confirmed", "eta": "7:35 PM", "total": 28.47 } } } Prune entries older than 24h on each check. ### Error Handling ErrorActionNot logged inAbort, notify user to log in via ChromeRestaurant closedDirect: abort. Discovery: use next-best from reconNo matches foundNotify user, suggest broadening criteriaOver budgetPick cheaper option or reduce order, note adjustmentItem unavailableClosest substitute, note in confirmationAllergen conflictNever order the item. Pick safe alternative or skip. Flag in reportAllergen info unclearSkip item, pick clearly safe alternative. Note uncertainty in report ### Reference Files Service-specific gotchas and UI element locations in references/: doordash.md ubereats.md grubhub.md These document service quirks (promo modals, tip screens, etc.). Key steps are inlined in task prompts above for sub-agent self-sufficiency. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: ThisIsJeron - Version: 1.1.0 ## Source health - Status: healthy - Source download looks usable. - Yavira can redirect you to the upstream package for this source. - Health scope: source - Reason: direct_download_ok - Checked at: 2026-04-23T16:43:11.935Z - Expires at: 2026-04-30T16:43:11.935Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/food-cal-order) - [Send to Agent page](https://openagent3.xyz/skills/food-cal-order/agent) - [JSON manifest](https://openagent3.xyz/skills/food-cal-order/agent.json) - [Markdown brief](https://openagent3.xyz/skills/food-cal-order/agent.md) - [Download page](https://openagent3.xyz/downloads/food-cal-order)