[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BXKDEXFX5F9EF6AVDR05H8":3,"skill-same:01M7BXKDEXFX5F9EF6AVDR05H8":51},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7BXKDEXFX5F9EF6AVDR05H8","ramp-complete-tasks",null,"Find and complete items in the Ramp attention feed. Use when: 'what needs my\nattention', 'show my tasks', 'overdue tasks', 'complete my Ramp tasks', 'why\nis my card locked', or a card is locked until required tasks are completed.\nFor approval-only queues, use ramp-approval-dashboard.","CognitionAI\u002Fdevin-marketplace","CognitionAI","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F163493330?v=4","01M7BVSRD98NC4FG8T3EZS6V5M","Cognition","01M7BVSRDX111C2XPWJ0E6MY26",29,"MIT","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Framp\u002Fskills\u002Framp-complete-tasks\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ramp-complete-tasks\narea: Cards and Spend\nsupported_surfaces: [cli, mcp]\ndescription: |-\n  Find and complete items in the Ramp attention feed. Use when: 'what needs my\n  attention', 'show my tasks', 'overdue tasks', 'complete my Ramp tasks', 'why\n  is my card locked', or a card is locked until required tasks are completed.\n  For approval-only queues, use ramp-approval-dashboard.\n---\n\n# Complete Ramp Tasks\n\nUse this skill to inspect the authenticated user's Ramp attention feed, route\neach outstanding task to the correct workflow, and prove that completed tasks\nand task-sanction card locks are actually cleared.\n\n## Non-Negotiables\n\n- Start from the live attention feed. Use the MCP tool `GetAttentionFeed` or\n  `ramp tasks list`; do not infer outstanding tasks from an email, a prior\n  response, or a card's lifecycle state.\n- Pass a non-empty `rationale` on every Ramp tool call or CLI command.\n- Show the task and proposed changes before any write, then get the user's\n  explicit confirmation. Never mark a task complete merely to remove a card\n  sanction.\n- Treat `TRANSACTION_REVISION_REQUESTED` and other task types as routing keys.\n  Satisfy the underlying task with its owning skill; do not dismiss, mutate, or\n  relabel an unfamiliar task to make it disappear.\n- A card whose underlying lifecycle state is `ACTIVE` can still be unspendable.\n  `is_spendable`, `active_locks`, and `blocking_task_count` are authoritative;\n  lifecycle state alone is not.\n- Never report a task complete or a card unlocked from a successful write call\n  alone. Poll the attention feed and, for a card sanction, `ListCards` with a\n  finite retry bound. Success requires the task to disappear and the exact card\n  to report `is_spendable: true`.\n\n## 1. Read the Attention Feed\n\nMCP:\n\n```text\nGetAttentionFeed(rationale=\"Find the user's outstanding Ramp tasks\")\n```\n\nCLI:\n\n```bash\nramp tasks list --rationale \"Find the user's outstanding Ramp tasks\" --agent\n```\n\nInspect every returned section. Preserve `task_snapshot_uuid`, `task_type`, the\ntask's entity UUIDs, due date, revision reason, required fields, and any Ramp\nlink returned in `context`. For each section, accumulate unique\n`task_snapshot_uuid` values across its complete cursor chain until\n`next_cursor` is null before claiming the feed is complete:\n\n```bash\nramp tasks list --json '{\n  \"rationale\": \"Continue reading the user's outstanding Ramp tasks\",\n  \"sections\": [{\n    \"section_type\": \"{section_type}\",\n    \"cursor\": \"{next_cursor}\",\n    \"limit\": 20\n  }]\n}' --agent\n```\n\nAfter pagination, compare the number of unique hydrated items collected for\neach section with that section's `total_count`. If the counts differ, hydration\nsilently omitted one or more outstanding tasks: treat the feed as incomplete,\nretry the bounded read, and never interpret the missing context as completion.\nIf `total_count` changes while traversing the cursor chain, restart that bounded\nattempt from the first page rather than combining two snapshots. Likewise, if\nan item or section contains an error, say that the feed is incomplete and retry\nthat bounded item. Summarize work by task type and urgency only from a fully\naccounted feed.\n\n## 2. Dispatch by Task Type\n\n| Task type | Workflow |\n|---|---|\n| `TRANSACTION_REVISION_REQUESTED` | Load `ramp-complete-expenses`. Review the revision request, correct the requested transaction fields, call `CompleteTransactionRevision` \u002F `ramp transactions complete-revision` with the user's accepted nonblank reason, then perform both postcondition checks below. |\n| `TRANSACTION_MISSING_ITEMS` | Load `ramp-complete-expenses`; fill only the missing receipt, memo, accounting, fund, trip, or attendee requirements. |\n| Transaction, reimbursement, bill, or non-procurement request approval | Load `ramp-approval-dashboard`; show details and confirm before approving or rejecting. |\n| Procurement approval, submitted request, PO status, or follow-up | Load `ramp-manage-procurement`. For a change request, require its `original_request` and complete `change_request_diff` old\u002Fnew values before confirmation. |\n| Procurement draft | Load `ramp-submit-procurement-request`. |\n| Vendor document or onboarding task | Load `ramp-manage-vendors`. |\n| Physical-card activation task | Load `ramp-card-management`. |\n| Unknown or unsupported task type | Present the task context and returned Ramp link. Ask the user to complete it in Ramp; do not guess a mutation. |\n\nOne item can require multiple corrections. Keep its `task_snapshot_uuid` and\ntransaction\u002Fentity UUID attached to the workflow so a similarly named task is\nnot changed by mistake.\n\n## 3. Handle a Task-Sanctioned Card\n\nWhen a user asks why a card is locked or asks to unlock it:\n\n1. Call `ListCards` before taking action. Identify the exact card by card UUID,\n   cardholder, display name, and last four digits.\n2. If `is_spendable` is true, report that live state. Do not call an unlock\n   tool.\n3. Inspect every entry in `active_locks`. When `remediation_action` is\n   `GET_ATTENTION_FEED`, do not call manual card unlock. Read the attention feed\n   and resolve its outstanding tasks through this workflow. Use\n   `blocking_task_count` to report how many tasks still block spending.\n4. For any other remediation action, return to `ramp-card-management`, which\n   routes `LOCK_OR_UNLOCK_CARD`, `UNLOCK_FRAUD_LOCKED_CARD`, and `CONTACT_RAMP`.\n\nThe underlying `card_state` may be `ACTIVE` while a sanction lock is present.\nNever use `card_state == ACTIVE` by itself as evidence that the card can spend.\n\n## 4. Verify Postconditions\n\nAfter the owning workflow reports success, use bounded polling (at most three\nrechecks in the current run) with `GetAttentionFeed` \u002F `ramp tasks list`. On\nevery attempt, traverse every returned section's complete cursor chain until\n`next_cursor` is null, accumulate unique `task_snapshot_uuid` values, and\nrequire the accumulated count to equal each section's `total_count` before\nchecking for the completed task's UUID or entity UUID.\n\n- The task postcondition passes only when the completed item is absent from the\n  outstanding feed (or the live response explicitly reports it completed).\n- If a section's hydrated-item count differs from `total_count`, the attempt is\n  incomplete and cannot prove absence.\n- If a section's `total_count` changes between pages, restart that bounded\n  attempt rather than combining pages from different feed snapshots.\n- If the task is still present, report it as outstanding and include any newly\n  returned reason or missing field. Do not claim success.\n\nFor a task-sanctioned card, poll `ListCards` within the same finite bound for the\nsame cardholder and card UUID. The combined postcondition passes only when the\ntask is absent and that exact card reports `is_spendable: true`. A successful\ntask write, `PENDING_VERIFICATION`, an absent lifecycle transition,\n`is_locked: false`, or `card_state: ACTIVE` alone is insufficient.\n\nIf the task disappears but the card remains locked, report the remaining lock\nstate and reason. Do not loop manual unlock calls or say the card is spendable.\n\n## Gotchas\n\n| Issue | Required response |\n|---|---|\n| Empty first page with a section cursor | Follow the returned per-section pagination contract before concluding there are no tasks. |\n| Task write returned success but item remains | Treat the task as outstanding; re-read its live context and report what remains. |\n| `card_state` is `ACTIVE` while `is_spendable` is false | The card cannot spend; inspect `active_locks` and follow each `remediation_action`. |\n| Task disappeared but `is_spendable` remains false | Report `active_locks` and `blocking_task_count`; do not claim the card was unlocked. |\n| Unknown task type | Present its context and Ramp link for a user handoff; do not invent a completion call. |\n","# Complete Ramp Tasks\n\nUse this skill to inspect the authenticated user's Ramp attention feed, route\neach outstanding task to the correct workflow, and prove that completed tasks\nand task-sanction card locks are actually cleared.\n\n## Non-Negotiables\n\n- Start from the live attention feed. Use the MCP tool `GetAttentionFeed` or\n  `ramp tasks list`; do not infer outstanding tasks from an email, a prior\n  response, or a card's lifecycle state.\n- Pass a non-empty `rationale` on every Ramp tool call or CLI command.\n- Show the task and proposed changes before any write, then get the user's\n  explicit confirmation. Never mark a task complete merely to remove a card\n  sanction.\n- Treat `TRANSACTION_REVISION_REQUESTED` and other task types as routing keys.\n  Satisfy the underlying task with its owning skill; do not dismiss, mutate, or\n  relabel an unfamiliar task to make it disappear.\n- A card whose underlying lifecycle state is `ACTIVE` can still be unspendable.\n  `is_spendable`, `active_locks`, and `blocking_task_count` are authoritative;\n  lifecycle state alone is not.\n- Never report a task complete or a card unlocked from a successful write call\n  alone. Poll the attention feed and, for a card sanction, `ListCards` with a\n  finite retry bound. Success requires the task to disappear and the exact card\n  to report `is_spendable: true`.\n\n## 1. Read the Attention Feed\n\nMCP:\n\n```text\nGetAttentionFeed(rationale=\"Find the user's outstanding Ramp tasks\")\n```\n\nCLI:\n\n```bash\nramp tasks list --rationale \"Find the user's outstanding Ramp tasks\" --agent\n```\n\nInspect every returned section. Preserve `task_snapshot_uuid`, `task_type`, the\ntask's entity UUIDs, due date, revision reason, required fields, and any Ramp\nlink returned in `context`. For each section, accumulate unique\n`task_snapshot_uuid` values across its complete cursor chain until\n`next_cursor` is null before claiming the feed is complete:\n\n```bash\nramp tasks list --json '{\n  \"rationale\": \"Continue reading the user's outstanding Ramp tasks\",\n  \"sections\": [{\n    \"section_type\": \"{section_type}\",\n    \"cursor\": \"{next_cursor}\",\n    \"limit\": 20\n  }]\n}' --agent\n```\n\nAfter pagination, compare the number of unique hydrated items collected for\neach section with that section's `total_count`. If the counts differ, hydration\nsilently omitted one or more outstanding tasks: treat the feed as incomplete,\nretry the bounded read, and never interpret the missing context as completion.\nIf `total_count` changes while traversing the cursor chain, restart that bounded\nattempt from the first page rather than combining two snapshots. Likewise, if\nan item or section contains an error, say that the feed is incomplete and retry\nthat bounded item. Summarize work by task type and urgency only from a fully\naccounted feed.\n\n## 2. Dispatch by Task Type\n\n| Task type | Workflow |\n|---|---|\n| `TRANSACTION_REVISION_REQUESTED` | Load `ramp-complete-expenses`. Review the revision request, correct the requested transaction fields, call `CompleteTransactionRevision` \u002F `ramp transactions complete-revision` with the user's accepted nonblank reason, then perform both postcondition checks below. |\n| `TRANSACTION_MISSING_ITEMS` | Load `ramp-complete-expenses`; fill only the missing receipt, memo, accounting, fund, trip, or attendee requirements. |\n| Transaction, reimbursement, bill, or non-procurement request approval | Load `ramp-approval-dashboard`; show details and confirm before approving or rejecting. |\n| Procurement approval, submitted request, PO status, or follow-up | Load `ramp-manage-procurement`. For a change request, require its `original_request` and complete `change_request_diff` old\u002Fnew values before confirmation. |\n| Procurement draft | Load `ramp-submit-procurement-request`. |\n| Vendor document or onboarding task | Load `ramp-manage-vendors`. |\n| Physical-card activation task | Load `ramp-card-management`. |\n| Unknown or unsupported task type | Present the task context and returned Ramp link. Ask the user to complete it in Ramp; do not guess a mutation. |\n\nOne item can require multiple corrections. Keep its `task_snapshot_uuid` and\ntransaction\u002Fentity UUID attached to the workflow so a similarly named task is\nnot changed by mistake.\n\n## 3. Handle a Task-Sanctioned Card\n\nWhen a user asks why a card is locked or asks to unlock it:\n\n1. Call `ListCards` before taking action. Identify the exact card by card UUID,\n   cardholder, display name, and last four digits.\n2. If `is_spendable` is true, report that live state. Do not call an unlock\n   tool.\n3. Inspect every entry in `active_locks`. When `remediation_action` is\n   `GET_ATTENTION_FEED`, do not call manual card unlock. Read the attention feed\n   and resolve its outstanding tasks through this workflow. Use\n   `blocking_task_count` to report how many tasks still block spending.\n4. For any other remediation action, return to `ramp-card-management`, which\n   routes `LOCK_OR_UNLOCK_CARD`, `UNLOCK_FRAUD_LOCKED_CARD`, and `CONTACT_RAMP`.\n\nThe underlying `card_state` may be `ACTIVE` while a sanction lock is present.\nNever use `card_state == ACTIVE` by itself as evidence that the card can spend.\n\n## 4. Verify Postconditions\n\nAfter the owning workflow reports success, use bounded polling (at most three\nrechecks in the current run) with `GetAttentionFeed` \u002F `ramp tasks list`. On\nevery attempt, traverse every returned section's complete cursor chain until\n`next_cursor` is null, accumulate unique `task_snapshot_uuid` values, and\nrequire the accumulated count to equal each section's `total_count` before\nchecking for the completed task's UUID or entity UUID.\n\n- The task postcondition passes only when the completed item is absent from the\n  outstanding feed (or the live response explicitly reports it completed).\n- If a section's hydrated-item count differs from `total_count`, the attempt is\n  incomplete and cannot prove absence.\n- If a section's `total_count` changes between pages, restart that bounded\n  attempt rather than combining pages from different feed snapshots.\n- If the task is still present, report it as outstanding and include any newly\n  returned reason or missing field. Do not claim success.\n\nFor a task-sanctioned card, poll `ListCards` within the same finite bound for the\nsame cardholder and card UUID. The combined postcondition passes only when the\ntask is absent and that exact card reports `is_spendable: true`. A successful\ntask write, `PENDING_VERIFICATION`, an absent lifecycle transition,\n`is_locked: false`, or `card_state: ACTIVE` alone is insufficient.\n\nIf the task disappears but the card remains locked, report the remaining lock\nstate and reason. Do not loop manual unlock calls or say the card is spendable.\n\n## Gotchas\n\n| Issue | Required response |\n|---|---|\n| Empty first page with a section cursor | Follow the returned per-section pagination contract before concluding there are no tasks. |\n| Task write returned success but item remains | Treat the task as outstanding; re-read its live context and report what remains. |\n| `card_state` is `ACTIVE` while `is_spendable` is false | The card cannot spend; inspect `active_locks` and follow each `remediation_action`. |\n| Task disappeared but `is_spendable` remains false | Report `active_locks` and `blocking_task_count`; do not claim the card was unlocked. |\n| Unknown task type | Present its context and Ramp link for a user handoff; do not invent a completion call. |\n",{"area":24,"name":5,"description":7,"supported_surfaces":25},"Cards and Spend",[26,27],"cli","mcp","main","9836d94e88404aabb682086405c2aa9cba7657ac","plugins\u002Framp\u002Fskills\u002Framp-complete-tasks",156,"https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace","https:\u002F\u002Fgithub.com\u002FCognitionAI","https:\u002F\u002Fcognition.ai\u002F","Makers of Devin, the AI software engineer.","2026-11-13 07:08:23",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add CognitionAI\u002Fdevin-marketplace --skill ramp-complete-tasks",{"tool":43,"command":44},"bunx","bunx skills add CognitionAI\u002Fdevin-marketplace --skill ramp-complete-tasks",{"tool":46,"command":47},"pnpm","pnpm dlx skills add CognitionAI\u002Fdevin-marketplace --skill ramp-complete-tasks","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Framp\u002Fskills\u002Framp-complete-tasks\u002FSKILL.md",true,[],[52,58,65,71,78,85],{"skillNo":53,"name":54,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M7BYC4AJGM98P2G9JH7QS24Z","business-data","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fwindsor-ai\u002Fskills\u002Fbusiness-data\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7BYBZ0CD4CBCPZHRZ551BNK","workflow","Creates durable, resumable workflows using Vercel's Workflow SDK. Use when building workflows that need to survive restarts, pause for external events, retry on failure, or coordinate multi-step operations over time. Triggers on mentions of \"workflow\", \"durable functions\", \"resumable\", \"workflow sdk\", \"queue\", \"event\", \"push\", \"subscribe\", or step-based orchestration.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fworkflow\u002Fupstream\u002FSKILL.md",[],[],{"skillNo":66,"name":60,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7BYB1XSZHKHD8JZTQJ62JN0","Vercel Workflow SDK expert guidance. Use when building durable workflows, long-running tasks, API routes or agents that need pause\u002Fresume, retries, step-based execution, or crash-safe orchestration with Vercel Workflow.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fworkflow\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7BYASGMK935J33E21N5WTW0","verification","Full-story verification — infers what the user is building, then verifies the complete flow end-to-end: browser → API → data → response. Triggers on dev server start and 'why isn't this working' signals.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fverification\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7BY9WJERKSKEH9HK6E71GW2","vercel-storage","Vercel storage expert guidance — Blob, Global Config (formerly Edge Config), and Marketplace storage (Neon Postgres, Upstash Redis). Use when choosing, configuring, or using data storage with Vercel applications.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fvercel-storage\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7BY9N034894YV2J9DCRZHYS","vercel-services","Configure and troubleshoot Vercel Services for multiple frontends and backends in one project. Use when composing a polyglot or multi-service application on one Vercel deployment; defining the `services` key, service-targeted rewrites, or service bindings in `vercel.json`; or running all services with `vercel dev`.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fvercel-services\u002FSKILL.md",[],[]]