[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79A24GAW513CJCSDYY4QGPN":3,"skill-same:01M79A24GAW513CJCSDYY4QGPN":74},{"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},"01M79A24GAW513CJCSDYY4QGPN","spend",null,"Execute one governed outbound payment across a selected runtime path, with quote, reservation, approval, rail evidence, recovery, and receipt-before-success.","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\u002Fspend\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: spend\ndescription: Execute one governed outbound payment across a selected runtime path, with quote, reservation, approval, rail evidence, recovery, and receipt-before-success.\nrunx:\n  category: payments\n---\n\n# Spend\n\nExecute one governed outbound payment.\n\nThis skill is the public buyer-side payment verb. It turns a payment-required\nsignal into a quote, reserves a child payment authority under the parent grant,\npasses an approval gate when required, fulfills exactly one runtime path, and\nreturns rail evidence that must seal before the paid action can be treated as\nsuccessful.\n\nThe runtime path is not a separate authority model. Stripe SPT, x402, MPP, and\nmock are selectable paths inside the same governed spend. Some paths also have\nbranded catalog facades (`x402-pay`, `stripe-pay`) because those names help\nusers discover and invoke the capability, but those facades still execute this\nsame quote -> reserve -> approve -> fulfill -> seal flow.\n\n## What this skill does\n\n1. **Normalize the payment signal.** Use `pay-quote` to bind amount, currency,\n   operation, counterparty, candidate runtime paths, realm, expiry, and\n   idempotency material.\n2. **Reserve authority.** Use `pay-reserve` to prove the child spend authority is\n   a subset of the parent payment grant and to mint a single-use spend\n   capability reference.\n3. **Gate the mutation.** Require approval when policy or realm demands it. A\n   rail runner must not receive spend authority until the gate records an\n   approved decision.\n4. **Fulfill exactly one runtime path.** Use `pay-fulfill-rail` with the selected\n   runner (`mock`, `x402`, `mpp`, or `stripe-spt`) and carry only scoped\n   capability references, never raw funding material.\n5. **Preserve recovery evidence.** If the rail response is ambiguous, report the\n   idempotency state and recovery hint instead of retrying under a new key.\n6. **Seal before success.** The spend is successful only when the receipt carries\n   quote, reservation, approval, rail proof, redaction notes, and finality.\n\nIt does not decide provider-side pricing, verify inbound customer credentials,\nsettle a refund, answer a dispute, or expose unrestricted rail credentials.\n\n## When to use this skill\n\n- A tool, service, or counterparty returns a payment-required signal and the\n  caller has a parent payment authority grant.\n- A harness needs to exercise the same governed spend flow over multiple\n  runtime paths.\n- An operator wants one receipt chain that proves quote, reservation, approval,\n  rail fulfillment, and recovery posture for an outbound payment.\n- A future real-rail demo needs to swap a deterministic mock path for x402,\n  Stripe SPT, MPP, or CDP without changing the canonical spend semantics.\n\n## When not to use this skill\n\n- To price an inbound service that runx exposes to another agent. Use\n  `charge-price` and `charge-verify`.\n- To issue or reverse a refund. Use the refund verb when it lands, preserving\n  the original charge\u002Fspend receipt link.\n- To run a rail directly because credentials are available. Runtime paths are\n  children of this skill and must receive only scoped spend capability refs.\n- To retry after a timeout with a new idempotency key. Recover under the same\n  reservation first.\n- To accept raw API keys, card numbers, unrestricted provider tokens, seed\n  phrases, webhook secrets, or bearer tokens as skill inputs.\n\n## Procedure\n\n1. Validate `payment_signal`, `parent_payment_authority`, and\n   `rail_profile_ref`.\n2. Select the runtime path from the signal and allowed policy. If more than one\n   path is possible, select by policy preference; if policy cannot decide,\n   return `needs_agent`.\n3. Run `pay-quote` with the signal, realm, and idempotency seed. Stop when the\n   quote is missing amount, currency, counterparty, operation, runtime path, or\n   stable idempotency material.\n4. Run `pay-reserve` with the quote and parent authority. The child authority\n   must be a subset of the parent grant and must not broaden amount, currency,\n   operation, counterparty, realm, period, runtime path, or capability.\n5. If approval is required, pause at the spend gate and record the operator\n   decision in the receipt. A denied or missing approval prevents fulfillment.\n6. Run `pay-fulfill-rail` for the selected runtime path. Pass the payment\n   challenge, reserved authority, spend capability ref, rail profile ref,\n   idempotency packet, and quote packet.\n7. Redact secret-bearing rail material. The receipt may contain proof refs,\n   provider event refs, credential refs, hashes, and redaction notes; it must not\n   contain raw funding material.\n8. If fulfillment is ambiguous, return a recovery status and require\n   `pay-recover` before any retry. If fulfillment is proven, seal the spend\n   receipt before reporting success.\n\n## Runtime paths\n\n| Path | Use when | Required proof\u002Fevidence | Secret handling |\n|---|---|---|---|\n| `mock` | Deterministic local fixtures, CI, and docs. | Mock proof ref, amount, currency, counterparty, idempotency key. | No real funding material; still redact rail session material. |\n| `x402` | A paid resource returns an x402-compatible challenge. | x402 payment proof ref, facilitator or receipt proof ref when available, challenge id, idempotency key. | Do not print wallet private keys, bearer tokens, or raw payment payloads. |\n| `mpp` | An MPP profile is configured for the selected counterparty. | MPP settlement proof ref, profile ref, amount, currency, idempotency key. | Treat profile\u002Fsession material as secret; output refs only. |\n| `stripe-spt` | An explicit test profile is selected locally, or a hosted Stripe payment provider owns live credential custody. | Stripe charge id, payment intent id when present, provider event id, scoped SPT ref, idempotency key. | The local adapter refuses live profiles; never accept or emit Stripe secret keys, webhook secrets, card data, PANs, or unrestricted tokens. |\n\nFuture paths such as CDP must fit this table before they become runnable: named\nauthority bounds, scoped credential reference, verifier evidence, redaction\nrules, idempotency behavior, and recovery behavior.\n\n## Edge cases and stop conditions\n\n- **Missing or ambiguous runtime path:** return `needs_agent`; do not guess a\n  rail from available credentials.\n- **Quote drift:** stop when the challenge, amount, currency, operation,\n  counterparty, or runtime path changes after quote.\n- **Parent grant too broad or too narrow:** reserve only a child subset. If the\n  child cannot cover the quoted spend without widening, return `needs_agent`.\n- **Approval denied or absent:** do not call the rail runner.\n- **Raw credential material appears in input:** refuse or redact and return\n  `needs_agent`; the rail runner accepts scoped references only.\n- **Ambiguous rail response:** do not retry under a new idempotency key. Return\n  recovery-required evidence.\n- **Proofless success claim:** return `escalated`; a paid action cannot be\n  marked successful without rail proof and a sealed receipt.\n- **Fixture path used in production:** refuse unless the realm is explicitly\n  `local` or `test`.\n\n## Output schema (`payment_execution`)\n\n```yaml\ndecision: sealed | denied | needs_agent | escalated\nruntime_path: mock | x402 | mpp | stripe-spt\npayment_quote_packet:\n  payment_quote: object\n  requested_payment_authority: object\n  challenge_evidence: object | null\npayment_reservation_packet:\n  payment_decision: object\n  reserved_payment_authority: object\n  spend_capability_ref: object\n  idempotency: object\npayment_admission: object | null\npayment_approval:\n  approved: boolean\n  gate_id: string\n  decided_by: string | null\neffect_evidence_packet:\n  rail_result: object\n  rail_proof: object\n  credential_envelope: object\n  redactions: [string]\n  recovery_hint: object\nsealed_receipt_ref: string | null\nopen_questions: [string]\n```\n\nA `sealed` decision requires a selected runtime path, subset reservation proof,\napproved gate when required, rail proof, redaction notes for secret-bearing\nfields, and a sealed receipt ref.\n\n## Worked example\n\nAn x402-compatible paid search endpoint returns a challenge for `1.25 USD`,\ncounterparty `merchant:demo`, and operation `search.paid`. The parent grant\nallows `payment` commits up to `1.25 USD` for that counterparty in realm `test`.\n`spend` quotes the challenge, reserves a child authority with the same amount,\ncurrency, operation, counterparty, and path `x402`, records the approval gate,\nfulfills through `pay-fulfill-rail` runner `x402`, redacts rail session\nmaterial, and seals a receipt containing the x402 proof ref and idempotency key.\nThe result is `decision: sealed`.\n\nIf the same endpoint changes the amount after quote, the skill returns\n`decision: needs_agent` or `escalated` depending on where drift is detected. It\ndoes not silently re-quote and spend under the old approval.\n\n## Inputs\n\n- `payment_signal` (required): payment-required signal or challenge.\n- `parent_payment_authority` (required): parent payment authority term or\n  authority reference.\n- `rail_profile_ref` (required): configured runtime-path profile reference.\n- `payment_admission` (optional): hosted payment admission token and settlement\n  identity. When present, it must be passed unchanged to the rail fulfillment\n  stage so the sealed supervisor evidence can prove hosted settlement identity.\n- `realm` (optional): authority realm such as `local`, `test`, or `prod`.\n- `spend_policy` (optional): policy limits and approval thresholds.\n- `approval_context` (optional): prior approval evidence.\n- `idempotency_seed` (optional): stable idempotency material.\n","# Spend\n\nExecute one governed outbound payment.\n\nThis skill is the public buyer-side payment verb. It turns a payment-required\nsignal into a quote, reserves a child payment authority under the parent grant,\npasses an approval gate when required, fulfills exactly one runtime path, and\nreturns rail evidence that must seal before the paid action can be treated as\nsuccessful.\n\nThe runtime path is not a separate authority model. Stripe SPT, x402, MPP, and\nmock are selectable paths inside the same governed spend. Some paths also have\nbranded catalog facades (`x402-pay`, `stripe-pay`) because those names help\nusers discover and invoke the capability, but those facades still execute this\nsame quote -> reserve -> approve -> fulfill -> seal flow.\n\n## What this skill does\n\n1. **Normalize the payment signal.** Use `pay-quote` to bind amount, currency,\n   operation, counterparty, candidate runtime paths, realm, expiry, and\n   idempotency material.\n2. **Reserve authority.** Use `pay-reserve` to prove the child spend authority is\n   a subset of the parent payment grant and to mint a single-use spend\n   capability reference.\n3. **Gate the mutation.** Require approval when policy or realm demands it. A\n   rail runner must not receive spend authority until the gate records an\n   approved decision.\n4. **Fulfill exactly one runtime path.** Use `pay-fulfill-rail` with the selected\n   runner (`mock`, `x402`, `mpp`, or `stripe-spt`) and carry only scoped\n   capability references, never raw funding material.\n5. **Preserve recovery evidence.** If the rail response is ambiguous, report the\n   idempotency state and recovery hint instead of retrying under a new key.\n6. **Seal before success.** The spend is successful only when the receipt carries\n   quote, reservation, approval, rail proof, redaction notes, and finality.\n\nIt does not decide provider-side pricing, verify inbound customer credentials,\nsettle a refund, answer a dispute, or expose unrestricted rail credentials.\n\n## When to use this skill\n\n- A tool, service, or counterparty returns a payment-required signal and the\n  caller has a parent payment authority grant.\n- A harness needs to exercise the same governed spend flow over multiple\n  runtime paths.\n- An operator wants one receipt chain that proves quote, reservation, approval,\n  rail fulfillment, and recovery posture for an outbound payment.\n- A future real-rail demo needs to swap a deterministic mock path for x402,\n  Stripe SPT, MPP, or CDP without changing the canonical spend semantics.\n\n## When not to use this skill\n\n- To price an inbound service that runx exposes to another agent. Use\n  `charge-price` and `charge-verify`.\n- To issue or reverse a refund. Use the refund verb when it lands, preserving\n  the original charge\u002Fspend receipt link.\n- To run a rail directly because credentials are available. Runtime paths are\n  children of this skill and must receive only scoped spend capability refs.\n- To retry after a timeout with a new idempotency key. Recover under the same\n  reservation first.\n- To accept raw API keys, card numbers, unrestricted provider tokens, seed\n  phrases, webhook secrets, or bearer tokens as skill inputs.\n\n## Procedure\n\n1. Validate `payment_signal`, `parent_payment_authority`, and\n   `rail_profile_ref`.\n2. Select the runtime path from the signal and allowed policy. If more than one\n   path is possible, select by policy preference; if policy cannot decide,\n   return `needs_agent`.\n3. Run `pay-quote` with the signal, realm, and idempotency seed. Stop when the\n   quote is missing amount, currency, counterparty, operation, runtime path, or\n   stable idempotency material.\n4. Run `pay-reserve` with the quote and parent authority. The child authority\n   must be a subset of the parent grant and must not broaden amount, currency,\n   operation, counterparty, realm, period, runtime path, or capability.\n5. If approval is required, pause at the spend gate and record the operator\n   decision in the receipt. A denied or missing approval prevents fulfillment.\n6. Run `pay-fulfill-rail` for the selected runtime path. Pass the payment\n   challenge, reserved authority, spend capability ref, rail profile ref,\n   idempotency packet, and quote packet.\n7. Redact secret-bearing rail material. The receipt may contain proof refs,\n   provider event refs, credential refs, hashes, and redaction notes; it must not\n   contain raw funding material.\n8. If fulfillment is ambiguous, return a recovery status and require\n   `pay-recover` before any retry. If fulfillment is proven, seal the spend\n   receipt before reporting success.\n\n## Runtime paths\n\n| Path | Use when | Required proof\u002Fevidence | Secret handling |\n|---|---|---|---|\n| `mock` | Deterministic local fixtures, CI, and docs. | Mock proof ref, amount, currency, counterparty, idempotency key. | No real funding material; still redact rail session material. |\n| `x402` | A paid resource returns an x402-compatible challenge. | x402 payment proof ref, facilitator or receipt proof ref when available, challenge id, idempotency key. | Do not print wallet private keys, bearer tokens, or raw payment payloads. |\n| `mpp` | An MPP profile is configured for the selected counterparty. | MPP settlement proof ref, profile ref, amount, currency, idempotency key. | Treat profile\u002Fsession material as secret; output refs only. |\n| `stripe-spt` | An explicit test profile is selected locally, or a hosted Stripe payment provider owns live credential custody. | Stripe charge id, payment intent id when present, provider event id, scoped SPT ref, idempotency key. | The local adapter refuses live profiles; never accept or emit Stripe secret keys, webhook secrets, card data, PANs, or unrestricted tokens. |\n\nFuture paths such as CDP must fit this table before they become runnable: named\nauthority bounds, scoped credential reference, verifier evidence, redaction\nrules, idempotency behavior, and recovery behavior.\n\n## Edge cases and stop conditions\n\n- **Missing or ambiguous runtime path:** return `needs_agent`; do not guess a\n  rail from available credentials.\n- **Quote drift:** stop when the challenge, amount, currency, operation,\n  counterparty, or runtime path changes after quote.\n- **Parent grant too broad or too narrow:** reserve only a child subset. If the\n  child cannot cover the quoted spend without widening, return `needs_agent`.\n- **Approval denied or absent:** do not call the rail runner.\n- **Raw credential material appears in input:** refuse or redact and return\n  `needs_agent`; the rail runner accepts scoped references only.\n- **Ambiguous rail response:** do not retry under a new idempotency key. Return\n  recovery-required evidence.\n- **Proofless success claim:** return `escalated`; a paid action cannot be\n  marked successful without rail proof and a sealed receipt.\n- **Fixture path used in production:** refuse unless the realm is explicitly\n  `local` or `test`.\n\n## Output schema (`payment_execution`)\n\n```yaml\ndecision: sealed | denied | needs_agent | escalated\nruntime_path: mock | x402 | mpp | stripe-spt\npayment_quote_packet:\n  payment_quote: object\n  requested_payment_authority: object\n  challenge_evidence: object | null\npayment_reservation_packet:\n  payment_decision: object\n  reserved_payment_authority: object\n  spend_capability_ref: object\n  idempotency: object\npayment_admission: object | null\npayment_approval:\n  approved: boolean\n  gate_id: string\n  decided_by: string | null\neffect_evidence_packet:\n  rail_result: object\n  rail_proof: object\n  credential_envelope: object\n  redactions: [string]\n  recovery_hint: object\nsealed_receipt_ref: string | null\nopen_questions: [string]\n```\n\nA `sealed` decision requires a selected runtime path, subset reservation proof,\napproved gate when required, rail proof, redaction notes for secret-bearing\nfields, and a sealed receipt ref.\n\n## Worked example\n\nAn x402-compatible paid search endpoint returns a challenge for `1.25 USD`,\ncounterparty `merchant:demo`, and operation `search.paid`. The parent grant\nallows `payment` commits up to `1.25 USD` for that counterparty in realm `test`.\n`spend` quotes the challenge, reserves a child authority with the same amount,\ncurrency, operation, counterparty, and path `x402`, records the approval gate,\nfulfills through `pay-fulfill-rail` runner `x402`, redacts rail session\nmaterial, and seals a receipt containing the x402 proof ref and idempotency key.\nThe result is `decision: sealed`.\n\nIf the same endpoint changes the amount after quote, the skill returns\n`decision: needs_agent` or `escalated` depending on where drift is detected. It\ndoes not silently re-quote and spend under the old approval.\n\n## Inputs\n\n- `payment_signal` (required): payment-required signal or challenge.\n- `parent_payment_authority` (required): parent payment authority term or\n  authority reference.\n- `rail_profile_ref` (required): configured runtime-path profile reference.\n- `payment_admission` (optional): hosted payment admission token and settlement\n  identity. When present, it must be passed unchanged to the rail fulfillment\n  stage so the sealed supervisor evidence can prove hosted settlement identity.\n- `realm` (optional): authority realm such as `local`, `test`, or `prod`.\n- `spend_policy` (optional): policy limits and approval thresholds.\n- `approval_context` (optional): prior approval evidence.\n- `idempotency_seed` (optional): stable idempotency material.\n",{"name":5,"runx":24,"description":7},{"category":25},"payments","main","fe90232960df6d9653e72e8d024a9d859e1ae524","skills\u002Fspend","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 spend",{"tool":41,"command":42},"bunx","bunx skills add ZachDreamZ\u002Frunx --skill spend",{"tool":44,"command":45},"pnpm","pnpm dlx skills add ZachDreamZ\u002Frunx --skill spend","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fspend\u002FSKILL.md",true,[49,55,59,63,67,70],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"fixtures\u002Fspend-accept-ceiling.yaml","REFERENCE","参考文档",8902,"https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fspend\u002Ffixtures\u002Fspend-accept-ceiling.yaml",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"fixtures\u002Fspend-mock-path.yaml",7301,"https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fspend\u002Ffixtures\u002Fspend-mock-path.yaml",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"fixtures\u002Fspend-mpp-path.yaml",7283,"https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fspend\u002Ffixtures\u002Fspend-mpp-path.yaml",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"fixtures\u002Fspend-stripe-spt-path.yaml",7930,"https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fspend\u002Ffixtures\u002Fspend-stripe-spt-path.yaml",{"path":68,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":69},"fixtures\u002Fspend-x402-path.yaml","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fspend\u002Ffixtures\u002Fspend-x402-path.yaml",{"path":71,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":72,"sourceHtmlUrl":73},"X.yaml",19157,"https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fspend\u002FX.yaml",[75,82,89,96,103,110],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"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",[],[]]