[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M799WXPVH5YD582Y06PPCVT4":3,"skill-same:01M799WXPVH5YD582Y06PPCVT4":59},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M799WXPVH5YD582Y06PPCVT4","dispute-respond",null,"Prepare a governed dispute response artifact from a linked charge receipt.","ZachDreamZ\u002Frunx","ZachDreamZ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F22769595?v=4","01M799NTP9N5VYWB4JY50MC7Y3","NexusCore","01M799NTQ1AYT8TZC0XTSEZXDJ",0,"MIT","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdispute-respond\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dispute-respond\ndescription: Prepare a governed dispute response artifact from a linked charge receipt.\nrunx:\n  category: payments\n---\n\n# Dispute Respond\n\nPrepare a profile-local dispute response artifact for a counterparty-initiated\npayment dispute.\n\nThis skill attaches the linked sealed charge receipt, prior refund receipts,\nand provider evidence, then selects a response posture. It does not settle the\ndispute or produce a rail closure receipt.\n\n## What this skill does\n\n1. **Bind the dispute to a charge.** Match the dispute event to the original\n   sealed charge receipt and the provider-side charge identity.\n2. **Collect linked receipts.** Attach prior refund, verification, reversal, or\n   recovery receipts so the response does not hide previous action.\n3. **Classify the posture.** Recommend `accept`, `contest`, `refund_already_sent`,\n   `needs_more_evidence`, or `operator_review` from the evidence and operator\n   posture.\n4. **Prepare the response artifact.** Emit the evidence packet a rail adapter or\n   operator can submit: receipt refs, provider evidence refs, redactions,\n   timeline, posture, and open questions.\n5. **Stop on ambiguity.** Return `needs_agent` when the dispute id, linked charge\n   receipt, prior refunds, evidence posture, or submission authority is unclear.\n\nIt does not submit the response to Stripe, x402, MPP, or another rail; it does\nnot issue a refund; and it does not mark a dispute closed.\n\n## When to use this skill\n\n- A provider receives a chargeback, payment dispute, or counterparty complaint\n  tied to a runx-sealed charge.\n- An operator wants a defensible response packet before deciding whether to\n  contest or accept the dispute.\n- A future rail-specific dispute adapter needs the normalized evidence and\n  posture before submission.\n\n## When not to use this skill\n\n- To silently refund a disputed charge. Disputes and refunds are separate\n  governed actions with separate receipts.\n- To respond without a sealed original charge receipt.\n- To fabricate product, delivery, identity, or consent evidence that is not\n  already present in receipts, provider logs, or operator-supplied refs.\n- To close the rail dispute. This skill prepares the artifact; a rail-specific\n  action submits and later records closure.\n\n## Procedure\n\n1. Validate that `dispute_event` and `original_receipt_ref` are present.\n2. Resolve the original sealed charge receipt. Confirm it matches the dispute\n   amount, currency, provider, counterparty, operation, and settlement family\n   when those fields are available.\n3. Resolve `prior_refund_receipt_refs` and record whether any refund fully or\n   partially covers the disputed amount.\n4. Normalize provider evidence refs into a timeline: price, challenge,\n   verification, service delivery, user consent, prior support contact, refund,\n   and recovery events.\n5. Apply `operator_posture` only as a preference. Evidence still controls the\n   final posture; a contest request without evidence returns `needs_agent`.\n6. Redact raw secrets and personal data that do not need to be submitted.\n7. Emit `dispute_response`, `dispute_evidence`, `linked_receipts`, `posture`,\n   `open_questions`, and a submission readiness decision.\n\n## Edge cases and stop conditions\n\n- **Missing or unsealed original receipt:** return `needs_agent`; do not prepare\n  a contest packet.\n- **Dispute does not match the receipt:** return `needs_agent` with the\n  mismatched fields.\n- **Prior refund exists:** do not recommend a silent second refund. Set posture\n  `refund_already_sent` or `operator_review` and cite the refund receipt.\n- **Evidence is stale or unauthenticated:** include it as low confidence or\n  return `needs_agent` when it is required for the posture.\n- **Operator wants to contest with no delivery or consent evidence:** return\n  `needs_agent`; do not fabricate narrative.\n- **PII or credentials in evidence:** redact before output and list each\n  redaction.\n- **Rail submission authority absent:** prepare the local artifact only and\n  return `needs_agent` for submission.\n\n## Output schema (`dispute_response_artifact`)\n\n```yaml\ndecision: ready | needs_agent\ndispute_response:\n  dispute_id: string\n  posture: accept | contest | refund_already_sent | needs_more_evidence | operator_review\n  amount: string | null\n  currency: string | null\n  counterparty: string | null\n  settlement_family: string | null\ndispute_evidence:\n  timeline:\n    - at: string\n      kind: price | challenge | verify | delivery | refund | support | recovery | dispute\n      ref: string\n      summary: string\n  redactions:\n    - field: string\n      reason: string\nlinked_receipts:\n  original_charge: string\n  verification: [string]\n  refunds: [string]\n  recoveries: [string]\nopen_questions: [string]\nrecommendation: string\n```\n\nA `ready` decision means the artifact is complete for review or downstream rail\nsubmission. It does not mean the dispute has been submitted or closed.\n\n## Worked example\n\nA Stripe test-mode dispute `dp_test_01` references charge receipt `rcpt_charge`.\nThe receipt proves the caller accepted challenge `ch_test_01` for `0.08 USD`,\nverification receipt `rcpt_verify` sealed, and the provider delivery log ref\nshows the paid result was returned. No refund receipts exist. The skill returns\n`decision: ready`, posture `contest`, linked receipts, redacted evidence refs,\nand a recommendation to submit the packet through the Stripe dispute adapter.\n\nIf refund receipt `rcpt_refund` already covers the full disputed amount, the\nskill returns posture `refund_already_sent`, cites the refund receipt, and\nwarns against an untracked second refund.\n\n## Inputs\n\n- `dispute_event` (required): provider-initiated dispute or chargeback event.\n- `original_receipt_ref` (required): linked sealed charge receipt reference.\n- `prior_refund_receipt_refs` (optional): prior refund receipts.\n- `evidence_refs` (optional): provider evidence references.\n- `operator_posture` (optional): requested response posture.\n","# Dispute Respond\n\nPrepare a profile-local dispute response artifact for a counterparty-initiated\npayment dispute.\n\nThis skill attaches the linked sealed charge receipt, prior refund receipts,\nand provider evidence, then selects a response posture. It does not settle the\ndispute or produce a rail closure receipt.\n\n## What this skill does\n\n1. **Bind the dispute to a charge.** Match the dispute event to the original\n   sealed charge receipt and the provider-side charge identity.\n2. **Collect linked receipts.** Attach prior refund, verification, reversal, or\n   recovery receipts so the response does not hide previous action.\n3. **Classify the posture.** Recommend `accept`, `contest`, `refund_already_sent`,\n   `needs_more_evidence`, or `operator_review` from the evidence and operator\n   posture.\n4. **Prepare the response artifact.** Emit the evidence packet a rail adapter or\n   operator can submit: receipt refs, provider evidence refs, redactions,\n   timeline, posture, and open questions.\n5. **Stop on ambiguity.** Return `needs_agent` when the dispute id, linked charge\n   receipt, prior refunds, evidence posture, or submission authority is unclear.\n\nIt does not submit the response to Stripe, x402, MPP, or another rail; it does\nnot issue a refund; and it does not mark a dispute closed.\n\n## When to use this skill\n\n- A provider receives a chargeback, payment dispute, or counterparty complaint\n  tied to a runx-sealed charge.\n- An operator wants a defensible response packet before deciding whether to\n  contest or accept the dispute.\n- A future rail-specific dispute adapter needs the normalized evidence and\n  posture before submission.\n\n## When not to use this skill\n\n- To silently refund a disputed charge. Disputes and refunds are separate\n  governed actions with separate receipts.\n- To respond without a sealed original charge receipt.\n- To fabricate product, delivery, identity, or consent evidence that is not\n  already present in receipts, provider logs, or operator-supplied refs.\n- To close the rail dispute. This skill prepares the artifact; a rail-specific\n  action submits and later records closure.\n\n## Procedure\n\n1. Validate that `dispute_event` and `original_receipt_ref` are present.\n2. Resolve the original sealed charge receipt. Confirm it matches the dispute\n   amount, currency, provider, counterparty, operation, and settlement family\n   when those fields are available.\n3. Resolve `prior_refund_receipt_refs` and record whether any refund fully or\n   partially covers the disputed amount.\n4. Normalize provider evidence refs into a timeline: price, challenge,\n   verification, service delivery, user consent, prior support contact, refund,\n   and recovery events.\n5. Apply `operator_posture` only as a preference. Evidence still controls the\n   final posture; a contest request without evidence returns `needs_agent`.\n6. Redact raw secrets and personal data that do not need to be submitted.\n7. Emit `dispute_response`, `dispute_evidence`, `linked_receipts`, `posture`,\n   `open_questions`, and a submission readiness decision.\n\n## Edge cases and stop conditions\n\n- **Missing or unsealed original receipt:** return `needs_agent`; do not prepare\n  a contest packet.\n- **Dispute does not match the receipt:** return `needs_agent` with the\n  mismatched fields.\n- **Prior refund exists:** do not recommend a silent second refund. Set posture\n  `refund_already_sent` or `operator_review` and cite the refund receipt.\n- **Evidence is stale or unauthenticated:** include it as low confidence or\n  return `needs_agent` when it is required for the posture.\n- **Operator wants to contest with no delivery or consent evidence:** return\n  `needs_agent`; do not fabricate narrative.\n- **PII or credentials in evidence:** redact before output and list each\n  redaction.\n- **Rail submission authority absent:** prepare the local artifact only and\n  return `needs_agent` for submission.\n\n## Output schema (`dispute_response_artifact`)\n\n```yaml\ndecision: ready | needs_agent\ndispute_response:\n  dispute_id: string\n  posture: accept | contest | refund_already_sent | needs_more_evidence | operator_review\n  amount: string | null\n  currency: string | null\n  counterparty: string | null\n  settlement_family: string | null\ndispute_evidence:\n  timeline:\n    - at: string\n      kind: price | challenge | verify | delivery | refund | support | recovery | dispute\n      ref: string\n      summary: string\n  redactions:\n    - field: string\n      reason: string\nlinked_receipts:\n  original_charge: string\n  verification: [string]\n  refunds: [string]\n  recoveries: [string]\nopen_questions: [string]\nrecommendation: string\n```\n\nA `ready` decision means the artifact is complete for review or downstream rail\nsubmission. It does not mean the dispute has been submitted or closed.\n\n## Worked example\n\nA Stripe test-mode dispute `dp_test_01` references charge receipt `rcpt_charge`.\nThe receipt proves the caller accepted challenge `ch_test_01` for `0.08 USD`,\nverification receipt `rcpt_verify` sealed, and the provider delivery log ref\nshows the paid result was returned. No refund receipts exist. The skill returns\n`decision: ready`, posture `contest`, linked receipts, redacted evidence refs,\nand a recommendation to submit the packet through the Stripe dispute adapter.\n\nIf refund receipt `rcpt_refund` already covers the full disputed amount, the\nskill returns posture `refund_already_sent`, cites the refund receipt, and\nwarns against an untracked second refund.\n\n## Inputs\n\n- `dispute_event` (required): provider-initiated dispute or chargeback event.\n- `original_receipt_ref` (required): linked sealed charge receipt reference.\n- `prior_refund_receipt_refs` (optional): prior refund receipts.\n- `evidence_refs` (optional): provider evidence references.\n- `operator_posture` (optional): requested response posture.\n",{"name":5,"runx":24,"description":7},{"category":25},"payments","main","fe90232960df6d9653e72e8d024a9d859e1ae524","skills\u002Fdispute-respond","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx","https:\u002F\u002Frunx.ai","https:\u002F\u002Fgithub.com\u002FZachDreamZ","https:\u002F\u002Fagentapigw.dpdns.org","Building Agent API Gateway — structured web data for AI agents. Consistent until I make it.","2026-07-17 04:21:10",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add ZachDreamZ\u002Frunx --skill dispute-respond",{"tool":41,"command":42},"bunx","bunx skills add ZachDreamZ\u002Frunx --skill dispute-respond",{"tool":44,"command":45},"pnpm","pnpm dlx skills add ZachDreamZ\u002Frunx --skill dispute-respond","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdispute-respond\u002FSKILL.md",true,[49,55],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"fixtures\u002Fdispute-respond-prepares-evidence.yaml","REFERENCE","参考文档",1165,"https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdispute-respond\u002Ffixtures\u002Fdispute-respond-prepares-evidence.yaml",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"X.yaml",1482,"https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdispute-respond\u002FX.yaml",[60,67,74,81,88,95],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M79A3PCWPN0YG6XG3X2YWGY4","zapier-handoff","Validate a runx execution context and hand off a governed payload to a Zapier Catch Hook with scoped auth, idempotency, and receipt expectations.","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fzapier-handoff\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M79A3JPAJVDGX5AGXKHB6M58","x402-pay","Execute a governed x402 payment by delegating to the canonical spend flow with the x402 runtime path selected.","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fx402-pay\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M79A3H7HHAQ5B4QCA0S2PPA3","work-plan","Decompose a build objective into governed runx execution steps.","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fwork-plan\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M79A3ESQDZ6AQ3QASKYGYTNB","web-fetch","Fetch and extract one web source within an explicit allowlist, returning the content by digest with full provenance.","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fweb-fetch\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M79A3C9NE99P24Q2QGG5236D","weather-forecast","Normalize provider weather evidence into an action-safe forecast packet with provenance, uncertainty, and stop conditions for downstream agents.","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fweather-forecast\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M79A38RWEA5NHMYBQZPCVPQP","vuln-triage","Triage dependency or ecosystem vulnerability risk into remediation and advisory packets, grounding on verified CVE evidence when it is supplied.","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002FSKILL.md",[],[]]