[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A2DR61CE3WPKQEBG1PEGSV":3,"skill-same:01M7A2DR61CE3WPKQEBG1PEGSV":55},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7A2DR61CE3WPKQEBG1PEGSV","author-spec",null,"Create, adopt, or revise a specification or scoping document before decomposing work into briefs, including useful delivery milestones and their acceptance criteria. Use for requirements, system design, architecture proposals, and reviewing an existing spec for decision readiness. Use author-brief for execution decomposition.","medici-finance\u002Fassay","medici-finance","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F298844171?v=4","01M7A2655EZBRV4HA62GMGC7KK","Medici","01M7A26562DY5FSYQMXSHM5EJ6",7,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmedici-finance\u002Fassay\u002Fblob\u002Fmain\u002Fplugins\u002Fassay\u002Fskills\u002Fauthor-spec\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: author-spec\ndescription: >-\n  Create, adopt, or revise a specification or scoping document before decomposing work\n  into briefs, including useful delivery milestones and their acceptance criteria.\n  Use for requirements, system design, architecture proposals, and reviewing\n  an existing spec for decision readiness. Use author-brief for execution decomposition.\n---\n\n# Author Spec\n\nProduce a sufficient, evidence-backed source of intent that downstream briefs can cite.\nSpecify outcomes, boundaries and consequential decisions; leave execution scheduling to\n`author-brief`. This skill chooses no product architecture, taxonomy or technology for an\nadopter. Read applicable project guidance for preferred techniques and actual constraints;\nan absent local profile is valid. Do not turn a preference into a binding constraint.\n\n## Bind implementation pickup to current context\n\nRead the [implementation pickup procedure](..\u002F..\u002Freferences\u002Fimplementation-pickup.md).\nSpecs and briefs identify the selected target\u002Ftransition, semantic contracts and\napplicable project engineering guidelines by canonical pointer. Include their\npickup\u002Fresume assessment in the implementation handoff; record revisions, coverage\nand continue\u002Fadapt\u002Fhold rather than assume the authoring snapshot is still current.\nUse the shipped context operation where the installed version supports it (see the\nsupported version below); otherwise use the explicit manual bootstrap.\nDo not rewrite completed Evidence or let a draft proposal veto approved work.\n\n## Hand changed planned work over as a context receipt\n\nWhen a spec changes planned work (a contract, owner, transition or approved target that\nexisting briefs consume), hand it to `author-brief` as a record, not prose alone:\n\n1. Write the target record (declaring brief, target state and revision, approval and\n   contract changes) into the context snapshot the project assembles, then run\n   `statusgen context discover --snapshot DIR --json > receipt.json`.\n2. The receipt is a `context-handoff-v1` record (`context-handoff-v2` when an impact is\n   withdrawn, `context-handoff-v3` when the snapshot carries product targets). Record each\n   actionable impact's disposition and each amendment obligation in it. An impact left\n   `unresolved` is an open question for the brief author, never a silent pass.\n3. Keep product and architecture bindings separate. A brief's `outcome` and\n   `outcome-revision` bind it to a product target revision, and the receipt keeps the\n   revision the work was first selected against when a brief rebinds. Never drop or rewrite\n   that revision to make an assessment read aligned. A receipt without a product section\n   covers architecture only and says product alignment is unchecked.\n4. Exit 3 is a hold: coverage is partial. Name the could-not-check sources in the handoff;\n   never report the receipt complete.\n\n**Supported version.** `statusgen context discover`, `statusgen context recheck` and\n`statusgen context check`, with the `context-handoff-v1` and `context-handoff-v2` receipts and\nthe `amendment-manifest-v1` file, ship in Assay v1.0.55 and later. The product-binding\nextension, `context-handoff-v3`, ships in v1.0.63 and later. `statusgen context --help`\nlists the verbs an install has.\n\n**Manual bootstrap.** When the installed statusgen lacks the verb, or lacks the\nproduct-binding extension while briefs bind `outcome-revision`, follow the\n[implementation pickup procedure](..\u002F..\u002Freferences\u002Fimplementation-pickup.md) by hand: record\nthe impacted briefs, their revisions, coverage and each amendment obligation in the handoff,\nand say that it is a manual bootstrap. Never invent a receipt or a schema version the\ninstall does not ship.\n\n## Start from the controlling source\n\nFind the existing spec, relevant decisions, affected consumers and current implementation.\nChoose **create** only when no sufficient source exists, **adopt** when an existing artifact\nalready settles the needed questions, or **revise** for a bounded change to that source.\nKeep adequate formats and content. Adoption may need only citations and a short gap note;\ndo not manufacture a parallel spec or reformat an approved one to satisfy this skill.\n\nPin material source revisions or dates. Distinguish observed behaviour, approved intent,\nproposals, assumptions and unresolved decisions. Inspect relevant code\u002Ftests for brownfield\nwork; a completed brief or incident report alone is not evidence of current behaviour.\nUnavailable evidence stays explicit. Do not substitute absence of access for absence of a\nconstraint. For a revision, preserve completed implementation and Evidence; identify which\nunfinished work and consumers the delta affects.\n\nConsider available quality evidence for the affected area and relevant seams: complexity,\nchange churn, coupling, recurring defects, test weaknesses and existing investigations or\nbrittle marks. Record the source revision\u002Fwindow and its relevance to this change; stale\nor unavailable measurements remain gaps, not evidence of good quality. A metric nominates\nan area for investigation; a high score alone neither proves a defect nor mandates a rewrite.\nUse the project's instruments and thresholds without inventing universal cutoffs.\n\nChoose a proportionate disposition: remediate first when safe delivery or verification\ndepends on it; include a bounded improvement when it removes the mechanism this change\nwould extend; route broader remediation separately with its dependency or independence\nmade explicit; or proceed with a reason and residual risk when evidence does not justify\nexpansion. Touching a file is not blanket authority to refactor it. For included work,\nname the expected improvement, behaviour to preserve, and an observable acceptance check.\nJudge safer delivery and reduced recurring complexity, not a lower score in isolation.\n\n## Capture delivery milestones\n\nFor stream scoping, staged delivery or a requested milestone revision, read the\n[shared milestone authoring procedure](..\u002F..\u002Freferences\u002Fmilestone-authoring.md),\nincluding its support check and **Author-spec** section. Capture useful outcomes as\n`\u003Ccell>:\u003Crepo>:\u003Cstream>:m-\u003CNN>`; identify proposed briefs as\n`\u003Ccell>:\u003Crepo>:\u003Cstream>:b-\u003CNN>` per brief\n§3.8, allowing `:b-\u003CNN>@\u003Cversion>` references and preserving legacy aliases\nand reader compatibility. Full record IDs include cell\u002Frepo; colon elisions use context. Capture supported scope, acceptance criteria\u002Fevidence and authority,\nversioned prerequisite capabilities and open decisions. Preserve existing promises;\ndo not infer milestone order from wave numbers or decompose the execution work here.\nCarry these records into the brief-authoring handoff. While readers lack support,\ncapture proposals in the scoping document rather than operational milestone YAML.\nWhen a useful outcome includes simulated or temporarily absent dependencies, apply the\nshared procedure's **Outcomes delivered with simulated dependencies** section. Capture\nreal\u002Fsubstitute boundaries, evidence limits and real-service replacement requirements\nbefore decomposition; use existing scope and acceptance sections rather than a new\nuniversal spec template.\n\n## Resolve the consequential questions\n\nScale depth to uncertainty and impact: a small change may take a paragraph and examples;\nan architectural change needs the boundaries below; exploration may end in a bounded spike\nwith an unanswered question and discriminating observation. These are questions to answer\nwhere relevant, not required headings or a section-count gate.\n\n- **Outcome and scope.** Whose problem is supported by what evidence? Name the workflow,\n  success observable, exclusions and domain terms whose ambiguity changes behaviour.\n- **Existing obligations.** Identify inherited decisions and the semantic owner of each\n  affected meaning. Link the canonical contract or record the gap. A theme, plane,\n  substrate, directory or stream label does not confer ownership or authority. Surface a\n  conflict with a controlling decision; do not silently override it in a local design.\n- **Behaviour and boundaries.** Describe inputs, outputs, states and relevant failure,\n  recovery and partial-success paths. Identify producers and consumers across seams, the\n  authority to act, and capabilities that must not cross a boundary, including transitively.\n  Name reusable library\u002FAPI entrypoints when they exist. Justify an additional process by\n  a concrete isolation, custody, deployment or lifecycle need; do not assume every logical\n  layer needs a service or that sharing code transfers authority to its callers.\n  Check proposed reuse from the consumer's actual module\u002Fpackage and version boundary;\n  code existing somewhere is not proof it is importable or compatible. If extraction is\n  needed, identify its owner and the prerequisite before promising reuse.\n- **Design and alternatives.** Separate required outcomes from the proposed mechanism and\n  incidental implementation choices. Record consequential alternatives and tradeoffs.\n  For a recurring defect, identify the hypothesised mechanism and owning layer; consider\n  removing the hazard or reusing its owner before adding another guard or exception.\n  State what the proposal retires and what added complexity remains justified. Apply the\n  project's existing design-fit procedure rather than creating another register or gate.\n- **Quality attributes.** Use the [quality prompts](references\u002Fquality-requirements.md) to\n  select material concerns, prioritize tradeoffs and express verifiable scenarios with\n  conditions, targets, provenance and evidence owners. Reuse inherited obligations;\n  unknown targets stay explicit. Identify costly paths and scaling risks before decomposition.\n  Keep this proportionate: no mandatory category checklist or invented budgets.\n- **Change and compatibility.** Explain migration, version compatibility, affected callers,\n  rollback or recovery, and retirement of the previous path where applicable. Distinguish\n  the desired end state from a transition that intentionally carries two implementations.\n- **Proof and decisions.** Map conditions to independently verifiable acceptance examples, including a relevant\n  failure or boundary case, and the evidence that could falsify the design. State what can\n  be checked now versus after implementation. Separate facts from hypotheses; do not claim\n  a metric or retrospective comparison proves causation. For each check that needs a\n  database or another service, name the NON-PRODUCTION instance it runs against and what\n  reaching it requires (network, a credential); briefs carry that name into the Verify\n  table's `Env` column as `service:\u003Cname>`, and such a check is never hermetic CI. Name remaining decisions and\n  their authorized owner, with options and a recommendation. Continue independent work\n  while a decision is pending; do not silently choose on that owner's behalf.\n\nKeep the minimum durable rationale needed to prevent independent implementers choosing\nincompatible meanings. Reuse existing decision records, contracts and evidence references.\nUse [review prompts](references\u002Freview-prompts.md) when a brownfield redesign or a\nspec-quality review needs a deeper check; do not load it for every small edit.\n\n## Review and hand off\n\nReview coverage, contradictions and plausible counterexamples against actual sources. On\nrevisions, include unchanged criteria, inherited constraints and accepted decisions. Report\ngaps with their source and consequence; formatting preferences are not defects.\nAn adequate spec needs no change. Separate changed intent from implementation defects;\ndo not weaken correct intent to fit a bug. Use the linked review prompts as needed.\n\nFollow the existing [spec lifecycle](https:\u002F\u002Fgithub.com\u002Fmedici-finance\u002Fassay\u002Fblob\u002Fmain\u002Fspec\u002Flifecycle-v1.md#8-spec-and-scoping-doc-lifecycle)\nfor Assay-tracked specs: draft, approved, routed; the ruling and citing briefs establish\nthe transitions. A review by this skill grants no approval or implementation authority.\nWhen authorized to decompose, use `author-brief`, whose\n[Context contract](https:\u002F\u002Fgithub.com\u002Fmedici-finance\u002Fassay\u002Fblob\u002Fmain\u002Fspec\u002Fbrief-v1.md#4-body-structure)\nowns `design-fit`, layering and architectural-contract references. Carry the controlling\nsource and unsettled obligations into briefs; do not duplicate that schema here or invent\na second task\u002Fstatus system. If this task is only spec authoring, deliver the spec, its\nmaterial open decisions and the next authorized step without auto-starting implementation.\n","# Author Spec\n\nProduce a sufficient, evidence-backed source of intent that downstream briefs can cite.\nSpecify outcomes, boundaries and consequential decisions; leave execution scheduling to\n`author-brief`. This skill chooses no product architecture, taxonomy or technology for an\nadopter. Read applicable project guidance for preferred techniques and actual constraints;\nan absent local profile is valid. Do not turn a preference into a binding constraint.\n\n## Bind implementation pickup to current context\n\nRead the [implementation pickup procedure](..\u002F..\u002Freferences\u002Fimplementation-pickup.md).\nSpecs and briefs identify the selected target\u002Ftransition, semantic contracts and\napplicable project engineering guidelines by canonical pointer. Include their\npickup\u002Fresume assessment in the implementation handoff; record revisions, coverage\nand continue\u002Fadapt\u002Fhold rather than assume the authoring snapshot is still current.\nUse the shipped context operation where the installed version supports it (see the\nsupported version below); otherwise use the explicit manual bootstrap.\nDo not rewrite completed Evidence or let a draft proposal veto approved work.\n\n## Hand changed planned work over as a context receipt\n\nWhen a spec changes planned work (a contract, owner, transition or approved target that\nexisting briefs consume), hand it to `author-brief` as a record, not prose alone:\n\n1. Write the target record (declaring brief, target state and revision, approval and\n   contract changes) into the context snapshot the project assembles, then run\n   `statusgen context discover --snapshot DIR --json > receipt.json`.\n2. The receipt is a `context-handoff-v1` record (`context-handoff-v2` when an impact is\n   withdrawn, `context-handoff-v3` when the snapshot carries product targets). Record each\n   actionable impact's disposition and each amendment obligation in it. An impact left\n   `unresolved` is an open question for the brief author, never a silent pass.\n3. Keep product and architecture bindings separate. A brief's `outcome` and\n   `outcome-revision` bind it to a product target revision, and the receipt keeps the\n   revision the work was first selected against when a brief rebinds. Never drop or rewrite\n   that revision to make an assessment read aligned. A receipt without a product section\n   covers architecture only and says product alignment is unchecked.\n4. Exit 3 is a hold: coverage is partial. Name the could-not-check sources in the handoff;\n   never report the receipt complete.\n\n**Supported version.** `statusgen context discover`, `statusgen context recheck` and\n`statusgen context check`, with the `context-handoff-v1` and `context-handoff-v2` receipts and\nthe `amendment-manifest-v1` file, ship in Assay v1.0.55 and later. The product-binding\nextension, `context-handoff-v3`, ships in v1.0.63 and later. `statusgen context --help`\nlists the verbs an install has.\n\n**Manual bootstrap.** When the installed statusgen lacks the verb, or lacks the\nproduct-binding extension while briefs bind `outcome-revision`, follow the\n[implementation pickup procedure](..\u002F..\u002Freferences\u002Fimplementation-pickup.md) by hand: record\nthe impacted briefs, their revisions, coverage and each amendment obligation in the handoff,\nand say that it is a manual bootstrap. Never invent a receipt or a schema version the\ninstall does not ship.\n\n## Start from the controlling source\n\nFind the existing spec, relevant decisions, affected consumers and current implementation.\nChoose **create** only when no sufficient source exists, **adopt** when an existing artifact\nalready settles the needed questions, or **revise** for a bounded change to that source.\nKeep adequate formats and content. Adoption may need only citations and a short gap note;\ndo not manufacture a parallel spec or reformat an approved one to satisfy this skill.\n\nPin material source revisions or dates. Distinguish observed behaviour, approved intent,\nproposals, assumptions and unresolved decisions. Inspect relevant code\u002Ftests for brownfield\nwork; a completed brief or incident report alone is not evidence of current behaviour.\nUnavailable evidence stays explicit. Do not substitute absence of access for absence of a\nconstraint. For a revision, preserve completed implementation and Evidence; identify which\nunfinished work and consumers the delta affects.\n\nConsider available quality evidence for the affected area and relevant seams: complexity,\nchange churn, coupling, recurring defects, test weaknesses and existing investigations or\nbrittle marks. Record the source revision\u002Fwindow and its relevance to this change; stale\nor unavailable measurements remain gaps, not evidence of good quality. A metric nominates\nan area for investigation; a high score alone neither proves a defect nor mandates a rewrite.\nUse the project's instruments and thresholds without inventing universal cutoffs.\n\nChoose a proportionate disposition: remediate first when safe delivery or verification\ndepends on it; include a bounded improvement when it removes the mechanism this change\nwould extend; route broader remediation separately with its dependency or independence\nmade explicit; or proceed with a reason and residual risk when evidence does not justify\nexpansion. Touching a file is not blanket authority to refactor it. For included work,\nname the expected improvement, behaviour to preserve, and an observable acceptance check.\nJudge safer delivery and reduced recurring complexity, not a lower score in isolation.\n\n## Capture delivery milestones\n\nFor stream scoping, staged delivery or a requested milestone revision, read the\n[shared milestone authoring procedure](..\u002F..\u002Freferences\u002Fmilestone-authoring.md),\nincluding its support check and **Author-spec** section. Capture useful outcomes as\n`\u003Ccell>:\u003Crepo>:\u003Cstream>:m-\u003CNN>`; identify proposed briefs as\n`\u003Ccell>:\u003Crepo>:\u003Cstream>:b-\u003CNN>` per brief\n§3.8, allowing `:b-\u003CNN>@\u003Cversion>` references and preserving legacy aliases\nand reader compatibility. Full record IDs include cell\u002Frepo; colon elisions use context. Capture supported scope, acceptance criteria\u002Fevidence and authority,\nversioned prerequisite capabilities and open decisions. Preserve existing promises;\ndo not infer milestone order from wave numbers or decompose the execution work here.\nCarry these records into the brief-authoring handoff. While readers lack support,\ncapture proposals in the scoping document rather than operational milestone YAML.\nWhen a useful outcome includes simulated or temporarily absent dependencies, apply the\nshared procedure's **Outcomes delivered with simulated dependencies** section. Capture\nreal\u002Fsubstitute boundaries, evidence limits and real-service replacement requirements\nbefore decomposition; use existing scope and acceptance sections rather than a new\nuniversal spec template.\n\n## Resolve the consequential questions\n\nScale depth to uncertainty and impact: a small change may take a paragraph and examples;\nan architectural change needs the boundaries below; exploration may end in a bounded spike\nwith an unanswered question and discriminating observation. These are questions to answer\nwhere relevant, not required headings or a section-count gate.\n\n- **Outcome and scope.** Whose problem is supported by what evidence? Name the workflow,\n  success observable, exclusions and domain terms whose ambiguity changes behaviour.\n- **Existing obligations.** Identify inherited decisions and the semantic owner of each\n  affected meaning. Link the canonical contract or record the gap. A theme, plane,\n  substrate, directory or stream label does not confer ownership or authority. Surface a\n  conflict with a controlling decision; do not silently override it in a local design.\n- **Behaviour and boundaries.** Describe inputs, outputs, states and relevant failure,\n  recovery and partial-success paths. Identify producers and consumers across seams, the\n  authority to act, and capabilities that must not cross a boundary, including transitively.\n  Name reusable library\u002FAPI entrypoints when they exist. Justify an additional process by\n  a concrete isolation, custody, deployment or lifecycle need; do not assume every logical\n  layer needs a service or that sharing code transfers authority to its callers.\n  Check proposed reuse from the consumer's actual module\u002Fpackage and version boundary;\n  code existing somewhere is not proof it is importable or compatible. If extraction is\n  needed, identify its owner and the prerequisite before promising reuse.\n- **Design and alternatives.** Separate required outcomes from the proposed mechanism and\n  incidental implementation choices. Record consequential alternatives and tradeoffs.\n  For a recurring defect, identify the hypothesised mechanism and owning layer; consider\n  removing the hazard or reusing its owner before adding another guard or exception.\n  State what the proposal retires and what added complexity remains justified. Apply the\n  project's existing design-fit procedure rather than creating another register or gate.\n- **Quality attributes.** Use the [quality prompts](references\u002Fquality-requirements.md) to\n  select material concerns, prioritize tradeoffs and express verifiable scenarios with\n  conditions, targets, provenance and evidence owners. Reuse inherited obligations;\n  unknown targets stay explicit. Identify costly paths and scaling risks before decomposition.\n  Keep this proportionate: no mandatory category checklist or invented budgets.\n- **Change and compatibility.** Explain migration, version compatibility, affected callers,\n  rollback or recovery, and retirement of the previous path where applicable. Distinguish\n  the desired end state from a transition that intentionally carries two implementations.\n- **Proof and decisions.** Map conditions to independently verifiable acceptance examples, including a relevant\n  failure or boundary case, and the evidence that could falsify the design. State what can\n  be checked now versus after implementation. Separate facts from hypotheses; do not claim\n  a metric or retrospective comparison proves causation. For each check that needs a\n  database or another service, name the NON-PRODUCTION instance it runs against and what\n  reaching it requires (network, a credential); briefs carry that name into the Verify\n  table's `Env` column as `service:\u003Cname>`, and such a check is never hermetic CI. Name remaining decisions and\n  their authorized owner, with options and a recommendation. Continue independent work\n  while a decision is pending; do not silently choose on that owner's behalf.\n\nKeep the minimum durable rationale needed to prevent independent implementers choosing\nincompatible meanings. Reuse existing decision records, contracts and evidence references.\nUse [review prompts](references\u002Freview-prompts.md) when a brownfield redesign or a\nspec-quality review needs a deeper check; do not load it for every small edit.\n\n## Review and hand off\n\nReview coverage, contradictions and plausible counterexamples against actual sources. On\nrevisions, include unchanged criteria, inherited constraints and accepted decisions. Report\ngaps with their source and consequence; formatting preferences are not defects.\nAn adequate spec needs no change. Separate changed intent from implementation defects;\ndo not weaken correct intent to fit a bug. Use the linked review prompts as needed.\n\nFollow the existing [spec lifecycle](https:\u002F\u002Fgithub.com\u002Fmedici-finance\u002Fassay\u002Fblob\u002Fmain\u002Fspec\u002Flifecycle-v1.md#8-spec-and-scoping-doc-lifecycle)\nfor Assay-tracked specs: draft, approved, routed; the ruling and citing briefs establish\nthe transitions. A review by this skill grants no approval or implementation authority.\nWhen authorized to decompose, use `author-brief`, whose\n[Context contract](https:\u002F\u002Fgithub.com\u002Fmedici-finance\u002Fassay\u002Fblob\u002Fmain\u002Fspec\u002Fbrief-v1.md#4-body-structure)\nowns `design-fit`, layering and architectural-contract references. Carry the controlling\nsource and unsettled obligations into briefs; do not duplicate that schema here or invent\na second task\u002Fstatus system. If this task is only spec authoring, deliver the spec, its\nmaterial open decisions and the next authorized step without auto-starting implementation.\n",{"name":5,"description":7},"main","7b56c62e2c2dc6a597a6b41ccdd43c72c70fe0ca","plugins\u002Fassay\u002Fskills\u002Fauthor-spec",5,"https:\u002F\u002Fgithub.com\u002Fmedici-finance\u002Fassay","https:\u002F\u002Fgithub.com\u002Fmedici-finance","2026-11-15 00:52:35",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add medici-finance\u002Fassay --skill author-spec",{"tool":37,"command":38},"bunx","bunx skills add medici-finance\u002Fassay --skill author-spec",{"tool":40,"command":41},"pnpm","pnpm dlx skills add medici-finance\u002Fassay --skill author-spec","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmedici-finance\u002Fassay\u002Fblob\u002Fmain\u002Fplugins\u002Fassay\u002Fskills\u002Fauthor-spec\u002FSKILL.md",true,[45,51],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Fquality-requirements.md","REFERENCE","参考文档",11738,"https:\u002F\u002Fgithub.com\u002Fmedici-finance\u002Fassay\u002Fblob\u002Fmain\u002Fplugins\u002Fassay\u002Fskills\u002Fauthor-spec\u002Freferences\u002Fquality-requirements.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Freview-prompts.md",7289,"https:\u002F\u002Fgithub.com\u002Fmedici-finance\u002Fassay\u002Fblob\u002Fmain\u002Fplugins\u002Fassay\u002Fskills\u002Fauthor-spec\u002Freferences\u002Freview-prompts.md",[56,63,69,76,82,89],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7A2KDJHD3C240974C8CHEK0","Bad--Name","A valid description.","https:\u002F\u002Fgithub.com\u002Fmedici-finance\u002Fassay\u002Fblob\u002Fmain\u002Ftools\u002Fskillslint\u002Ftestdata\u002Fconformance\u002Fname-pattern\u002FBad--Name\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7A2KCG3W4TB4ZTKK9NC3TX5","not-the-desk","https:\u002F\u002Fgithub.com\u002Fmedici-finance\u002Fassay\u002Fblob\u002Fmain\u002Ftools\u002Fskillslint\u002Ftestdata\u002Fconformance\u002Fname-mismatch\u002Fthe-desk\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7A2K70T9HZHH43ARFZP6P0A","skill","abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde abcde","https:\u002F\u002Fgithub.com\u002Fmedici-finance\u002Fassay\u002Fblob\u002Fmain\u002Ftools\u002Fskillslint\u002Ftestdata\u002Fconformance\u002Fdesc-1025\u002Fskill\u002FSKILL.md",[],[],{"skillNo":77,"name":71,"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},"01M7A2JYP6F7FCZK539GA01MFQ","字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字字 字字字字","https:\u002F\u002Fgithub.com\u002Fmedici-finance\u002Fassay\u002Fblob\u002Fmain\u002Ftools\u002Fskillslint\u002Ftestdata\u002Fconformance\u002Fdesc-1024-multibyte\u002Fskill\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},"01M7A2JSBQENV3BBQZ3FQNSJ5E","skill-9","This is a filler sentence used only to push the summed bundle description character budget over its threshold for the fixture. This is a filler sentence used only to push the summed bundle description character budget over its threshold for the fixture. This is a filler sentence used only to push the summed bundle description character budget over its threshold for the fixture. This is a filler sentence used only to push the summed bundle description character budget over its threshold for the fixture. This is a filler sentence used only to push the summed bundle description character budget over its threshold for the fixture. This is a filler sentence used only to push the summed bundle description character budget over its threshold for the fixture. This is a filler sentence used only to push the summed bundle description character budget over its threshold for the fixture. This is a f","https:\u002F\u002Fgithub.com\u002Fmedici-finance\u002Fassay\u002Fblob\u002Fmain\u002Ftools\u002Fskillslint\u002Ftestdata\u002Fconformance\u002Fbudget-over\u002Fskill-9\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"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":92,"categories":93,"keywords":94,"publishedAt":19},"01M7A2JKR0EGK44TQVGZ1EWCW4","skill-8","https:\u002F\u002Fgithub.com\u002Fmedici-finance\u002Fassay\u002Fblob\u002Fmain\u002Ftools\u002Fskillslint\u002Ftestdata\u002Fconformance\u002Fbudget-over\u002Fskill-8\u002FSKILL.md",[],[]]