[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M699GW9CKSGP7NGQ6RHST9ZK":3,"skill-same:01M699GW9CKSGP7NGQ6RHST9ZK":69},{"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":23,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M699GW9CKSGP7NGQ6RHST9ZK","behavior-preserving-refactor",null,"Preserve observable behavior when splitting files, moving members, consolidating helpers, or simplifying TestFx code. Use for structural refactors and file-diet implementation; inventory baseline semantics and consumers, then run focused equivalence checks.","microsoft\u002Ftestfx","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M699C71CJ91B5WZ3AXG3GG2M",1059,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ftestfx\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fbehavior-preserving-refactor\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"refactor","behavior","behavior preserving refactor","use","helpers","when","preserve","for","diet","structural","files","implementation","inventory","baseline","file","code","run","2026-11-10 10:12:30",false,"---\nname: behavior-preserving-refactor\ndescription: Preserve observable behavior when splitting files, moving members, consolidating helpers, or simplifying TestFx code. Use for structural refactors and file-diet implementation; inventory baseline semantics and consumers, then run focused equivalence checks.\n---\n\n# Behavior-Preserving Refactors\n\nUse this recipe for the specific code being refactored, not a repository-wide\naudit. Read `.github\u002Fcopilot-instructions.md` and applicable directory rules.\nPreserve existing behavior, including surprising reachable cases; a bug fix or\nmodernization needs separate authorization and validation.\n\nAn issue-generation workflow's bounded inspection is not implementation\npreflight. For example, Daily File Diet inspects only the first 100 lines and up\nto 50 declaration lines of one file. Keep that budget when proposing work, label\nunverified assumptions, and include this recipe for the later implementer.\nDo not claim equivalence, tested behavior, or complete consumer coverage from\nthat sample.\n\n## 1. Establish the baseline before editing\n\nIdentify the exact methods or declarations to move or extract, their callers,\nexisting focused tests, and owning projects. Read the complete affected bodies\nand relevant context, not just signatures or similar-looking helpers. For each\nexisting implementation that might share a helper, record:\n\n| Boundary | What must remain unchanged |\n| --- | --- |\n| Selection | Iteration order, first versus last match, first matching name versus first matching typed value, exact type tests, casts, defaults, and missing-value handling. |\n| Evaluation | Short-circuit operand order, which callbacks run and how often, enumeration count, laziness, mutation, and side effects before return or failure. |\n| Results and failures | Return values, diagnostics and locations, output ordering, exception type and timing, cancellation, and cleanup\u002Fdisposal order where affected. |\n| Compilation | Namespaces, accessibility, attributes, overload binding, target-framework guards, and native interop signatures and marshalling. |\n| Cost | Allocations, materialization, boxing, repeated scans, and algorithmic complexity on affected hot paths. |\n\nInventory reachable empty, duplicate, malformed, null, and wrong-type inputs.\nDo not add support for impossible states, but do not assume compiler or user\ninput is always valid: analyzer inputs can be incomplete or contain errors.\nName the existing guard that makes a case unreachable if excluding it.\nUse existing behavior as the oracle, not the intended behavior of a new helper.\n\n## 2. Trace the actual consumers and constraints\n\n- Find all partial declarations and call sites of the affected type or member.\n  Check initialization order if moving fields between partial files.\n- Inspect owning project files and imports for linked `Compile` items, shared\n  source, globs, explicit includes, and packaging rules. Find every consuming\n  project, including source-only packages; a build of the original owner does\n  not prove that a new file is included by another consumer.\n- Keep target frameworks, conditional compilation, supported platforms, and\n  package layout intact. A native interop file move is not permission to replace\n  `DllImport`, change marshalling, or adopt APIs unavailable on older targets.\n- Check applicable `PublicAPI` and `InternalAPI` shipped\u002Funshipped baselines.\n  Prefer unchanged signatures and accessibility; do not expose a helper just\n  to share it. Record required newly tracked declarations without rewriting\n  shipped API history.\n\n## 3. Make the structural change, not adjacent cleanup\n\nMove existing bodies unchanged first, preserving attributes, guards, resource\naccess, and file encoding. Keep unrelated renaming, formatting, LINQ rewrites,\ninterop modernization, new validation, and behavior fixes out of the change.\n\nBefore consolidating helpers, compare every caller's baseline. Similar names\nor happy-path outputs do not establish equivalence. If callers differ in\nselection, evaluation, or failure behavior, keep separate implementations or\nuse the smallest explicit helper that preserves each contract; do not invent\na configurable abstraction merely to eliminate duplication.\n\nDo not replace a loop with a dictionary, eager projection, sort, or single-match\noperator without proving duplicate handling, enumeration, and failure behavior.\nOn hot paths, preserve allocation and complexity characteristics. Use existing\nallocation\u002Fperformance checks when the extraction could change them; do not\nintroduce a benchmark project for a pure move.\n\nIf the size target requires behavior changes or unsafe fragmentation, stop that\npart of the refactor and report the remaining line count and concrete constraint.\nDo not alter semantics just to meet a file-size goal.\n\n## 4. Use distinguishing equivalence cases\n\nThese are examples to adapt to the actual baseline, not new product semantics:\n\n| Baseline | Focused case | Required observation |\n| --- | --- | --- |\n| A loop overwrites its result for every matching name. | Matching values `1`, then `2`. | Result remains `2`; returning the first match is not equivalent. |\n| A loop returns the first matching name whose value is an `int`. | Same-name string `\"bad\"`, integer `7`, then integer `9`. | Result remains `7`; taking the first name then casting, or taking the last integer, is not equivalent. |\n| Exact `int` type matching. | Same-name `long` value `7L`, followed by `int` value `8`. | Result remains `8`; numeric conversion changes type selection. |\n| `ShouldRun() && Execute()`. | `ShouldRun` returns false; `Execute` records a call or throws. | Only `ShouldRun` runs; reordering operands or evaluating both eagerly is not equivalent. |\n| A guarded interop declaration moves to another file. | Build every source-linked consumer and affected supported TFM\u002Fplatform path. | Declaration, guards, accessibility, and marshalling remain unchanged; no new runtime API requirement. |\n\nAlso cover the actual missing\u002Fempty and malformed-only outcomes, not just\nmalformed input followed by a valid value. Assert observable values, diagnostic\nlocations, exception behavior, and ordered side-effect traces where applicable.\nPin expectations to the baseline; comparing two paths that both call the new\nhelper is not an equivalence test.\n\n## 5. Validate the smallest relevant surface\n\nBefore editing, run the existing focused checks when feasible and add any\nnecessary distinguishing cases against the original implementation. After the\nchange, rerun the same checks. Explain pre-existing failures or unavailable\nchecks; do not report unrun checks as passed.\n\nUse the repo-local toolchain and documented filtered build\u002Ftest commands from\n`.github\u002Fcopilot-instructions.md`. Build the owning and linked consuming\nprojects for affected target frameworks. Run directly related tests, escalating\nonly when dependencies or failures justify it. A pure file move needs inclusion\nand compilation checks plus relevant existing tests, not the full solution.\nIf shipping package\u002Fsource inclusion changes, validate the packed consumer\nlayout using existing acceptance infrastructure.\n\nReview the final diff for changed expressions, ordering, signatures, attributes,\nguards, includes, tracked APIs, and unintended adjacent edits. Measure resulting\nfile sizes rather than assuming the split meets its target.\n\n## Completion evidence\n\nReport the moved\u002Fextracted responsibility, baseline invariants and distinguishing\ncases, affected consumers\u002FTFMs and API surfaces, exact checks and outcomes, and\nresulting line counts when size is the goal. Identify any remaining uncertainty\nor blocked target explicitly. Compilation alone does not prove runtime\nequivalence, and passing happy-path tests does not settle first\u002Flast selection\nor short-circuit behavior.\n","# Behavior-Preserving Refactors\n\nUse this recipe for the specific code being refactored, not a repository-wide\naudit. Read `.github\u002Fcopilot-instructions.md` and applicable directory rules.\nPreserve existing behavior, including surprising reachable cases; a bug fix or\nmodernization needs separate authorization and validation.\n\nAn issue-generation workflow's bounded inspection is not implementation\npreflight. For example, Daily File Diet inspects only the first 100 lines and up\nto 50 declaration lines of one file. Keep that budget when proposing work, label\nunverified assumptions, and include this recipe for the later implementer.\nDo not claim equivalence, tested behavior, or complete consumer coverage from\nthat sample.\n\n## 1. Establish the baseline before editing\n\nIdentify the exact methods or declarations to move or extract, their callers,\nexisting focused tests, and owning projects. Read the complete affected bodies\nand relevant context, not just signatures or similar-looking helpers. For each\nexisting implementation that might share a helper, record:\n\n| Boundary | What must remain unchanged |\n| --- | --- |\n| Selection | Iteration order, first versus last match, first matching name versus first matching typed value, exact type tests, casts, defaults, and missing-value handling. |\n| Evaluation | Short-circuit operand order, which callbacks run and how often, enumeration count, laziness, mutation, and side effects before return or failure. |\n| Results and failures | Return values, diagnostics and locations, output ordering, exception type and timing, cancellation, and cleanup\u002Fdisposal order where affected. |\n| Compilation | Namespaces, accessibility, attributes, overload binding, target-framework guards, and native interop signatures and marshalling. |\n| Cost | Allocations, materialization, boxing, repeated scans, and algorithmic complexity on affected hot paths. |\n\nInventory reachable empty, duplicate, malformed, null, and wrong-type inputs.\nDo not add support for impossible states, but do not assume compiler or user\ninput is always valid: analyzer inputs can be incomplete or contain errors.\nName the existing guard that makes a case unreachable if excluding it.\nUse existing behavior as the oracle, not the intended behavior of a new helper.\n\n## 2. Trace the actual consumers and constraints\n\n- Find all partial declarations and call sites of the affected type or member.\n  Check initialization order if moving fields between partial files.\n- Inspect owning project files and imports for linked `Compile` items, shared\n  source, globs, explicit includes, and packaging rules. Find every consuming\n  project, including source-only packages; a build of the original owner does\n  not prove that a new file is included by another consumer.\n- Keep target frameworks, conditional compilation, supported platforms, and\n  package layout intact. A native interop file move is not permission to replace\n  `DllImport`, change marshalling, or adopt APIs unavailable on older targets.\n- Check applicable `PublicAPI` and `InternalAPI` shipped\u002Funshipped baselines.\n  Prefer unchanged signatures and accessibility; do not expose a helper just\n  to share it. Record required newly tracked declarations without rewriting\n  shipped API history.\n\n## 3. Make the structural change, not adjacent cleanup\n\nMove existing bodies unchanged first, preserving attributes, guards, resource\naccess, and file encoding. Keep unrelated renaming, formatting, LINQ rewrites,\ninterop modernization, new validation, and behavior fixes out of the change.\n\nBefore consolidating helpers, compare every caller's baseline. Similar names\nor happy-path outputs do not establish equivalence. If callers differ in\nselection, evaluation, or failure behavior, keep separate implementations or\nuse the smallest explicit helper that preserves each contract; do not invent\na configurable abstraction merely to eliminate duplication.\n\nDo not replace a loop with a dictionary, eager projection, sort, or single-match\noperator without proving duplicate handling, enumeration, and failure behavior.\nOn hot paths, preserve allocation and complexity characteristics. Use existing\nallocation\u002Fperformance checks when the extraction could change them; do not\nintroduce a benchmark project for a pure move.\n\nIf the size target requires behavior changes or unsafe fragmentation, stop that\npart of the refactor and report the remaining line count and concrete constraint.\nDo not alter semantics just to meet a file-size goal.\n\n## 4. Use distinguishing equivalence cases\n\nThese are examples to adapt to the actual baseline, not new product semantics:\n\n| Baseline | Focused case | Required observation |\n| --- | --- | --- |\n| A loop overwrites its result for every matching name. | Matching values `1`, then `2`. | Result remains `2`; returning the first match is not equivalent. |\n| A loop returns the first matching name whose value is an `int`. | Same-name string `\"bad\"`, integer `7`, then integer `9`. | Result remains `7`; taking the first name then casting, or taking the last integer, is not equivalent. |\n| Exact `int` type matching. | Same-name `long` value `7L`, followed by `int` value `8`. | Result remains `8`; numeric conversion changes type selection. |\n| `ShouldRun() && Execute()`. | `ShouldRun` returns false; `Execute` records a call or throws. | Only `ShouldRun` runs; reordering operands or evaluating both eagerly is not equivalent. |\n| A guarded interop declaration moves to another file. | Build every source-linked consumer and affected supported TFM\u002Fplatform path. | Declaration, guards, accessibility, and marshalling remain unchanged; no new runtime API requirement. |\n\nAlso cover the actual missing\u002Fempty and malformed-only outcomes, not just\nmalformed input followed by a valid value. Assert observable values, diagnostic\nlocations, exception behavior, and ordered side-effect traces where applicable.\nPin expectations to the baseline; comparing two paths that both call the new\nhelper is not an equivalence test.\n\n## 5. Validate the smallest relevant surface\n\nBefore editing, run the existing focused checks when feasible and add any\nnecessary distinguishing cases against the original implementation. After the\nchange, rerun the same checks. Explain pre-existing failures or unavailable\nchecks; do not report unrun checks as passed.\n\nUse the repo-local toolchain and documented filtered build\u002Ftest commands from\n`.github\u002Fcopilot-instructions.md`. Build the owning and linked consuming\nprojects for affected target frameworks. Run directly related tests, escalating\nonly when dependencies or failures justify it. A pure file move needs inclusion\nand compilation checks plus relevant existing tests, not the full solution.\nIf shipping package\u002Fsource inclusion changes, validate the packed consumer\nlayout using existing acceptance infrastructure.\n\nReview the final diff for changed expressions, ordering, signatures, attributes,\nguards, includes, tracked APIs, and unintended adjacent edits. Measure resulting\nfile sizes rather than assuming the split meets its target.\n\n## Completion evidence\n\nReport the moved\u002Fextracted responsibility, baseline invariants and distinguishing\ncases, affected consumers\u002FTFMs and API surfaces, exact checks and outcomes, and\nresulting line counts when size is the goal. Identify any remaining uncertainty\nor blocked target explicitly. Compilation alone does not prove runtime\nequivalence, and passing happy-path tests does not settle first\u002Flast selection\nor short-circuit behavior.\n",{"name":5,"description":7},"main","f8f2bfd77819bb789d4736ce7db4a567a37fcf7e",".github\u002Fskills\u002Fbehavior-preserving-refactor",315,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ftestfx","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-14 14:01:43",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add microsoft\u002Ftestfx --skill behavior-preserving-refactor",{"tool":61,"command":62},"bunx","bunx skills add microsoft\u002Ftestfx --skill behavior-preserving-refactor",{"tool":64,"command":65},"pnpm","pnpm dlx skills add microsoft\u002Ftestfx --skill behavior-preserving-refactor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ftestfx\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fbehavior-preserving-refactor\u002FSKILL.md",true,[],[70,96,122,142,161,186],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":41},"01M70GYY0AV0JGMTHE2CN6TNYK","dotnet-breaking-changes","Use before changing .NET\u002FC# code whose callers you do not control: a NuGet library, or a repo with PublicAPI.Shipped\u002FUnshipped.txt, ApiCompat, multiple TargetFrameworks, InternalsVisibleTo, or generated (.g.cs) partials. Green builds miss silent breaks from optional parameters, parameter names, sealing, const values, nullability, and #if. USE FOR: \"without breaking existing callers\"; adding a public method, overload, optional parameter, or interface member to a shipped library; renaming a public method or an internal helper a friend assembly uses; consolidating duplicated logic; changing a signature, nullability, default, or attribute; adding a target framework; RS0016\u002FRS0017 or ApiCompat errors; \"is this PR breaking?\". For a rename, extract, or merge, also invoke csharp-refactoring. DO NOT USE FOR: an executable whose callers all live in one project; renaming a local variable or private member, even in a shipped library; formatting; framework\u002FSDK\u002FNuGet upgrades (use dotnet-upgrade).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ftestfx\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdotnet-breaking-changes\u002FSKILL.md",[],[77,78,79,80,81,82,83,84,85,86,87,88,89,39,90,91,92,93,94,95],"dotnet","dotnet breaking changes","changes","green","project","default","local","errors","interface","generated","upgrade","invoke","you","refactoring","merge","rename","library","live","assembly",{"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":105,"publishedAt":41},"01M699HHE9DTZWAMPB1ZR7ZKSW","testfx-test-value-evidence","Apply the vendored test-value-evidence skill with TestFx toolchain, assertion, parallel-safety, packed-consumer, and review conventions. Use when implementing or reviewing behavior-changing TestFx PRs or commits, including source-only changes.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ftestfx\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ftestfx-test-value-evidence\u002FSKILL.md",[102],{"categoryNo":103,"categoryName":104,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[106,107,108,109,110,111,112,113,114,115,116,117,27,29,118,119,79,25,120,121],"test","testfx test value evidence","test value evidence","evidence","value","review","parallel","toolchain","commits","implementing","prs","only","apply","with","Safety","conventions",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":41},"01M699HEYWH1B9XGNBFY8J2FZS","testfx-parallel-safety-preflight","Check concurrency and isolation before implementing or refactoring TestFx tests, lifecycle code, helpers, shared-state declarations, or production paths those tests exercise. Use before narrowing DoNotParallelize or ResourceLock, changing parallelization settings, or introducing asynchronous workers; repeat against the final diff.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ftestfx\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ftestfx-parallel-safety-preflight\u002FSKILL.md",[],[129,120,130,112,131,132,115,133,39,134,90,135,136,28,137,138,139,140,27,141],"testfx parallel safety preflight","preflight","shared","asynchronous","exercise","concurrency","paths","isolation","diff","parallelization","lifecycle","tests","workers",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":41},"01M699HC61ZV9GJ2C8JV03951G","testfx-localization-validation","Validate generated TestFx localization catalogs, resource IDs, placeholders and locked tokens. Use for RESX\u002FXLF changes, OneLoc PRs, localization build failures, duplicate targets or units, and orphaned translation entries.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ftestfx\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ftestfx-localization-validation\u002FSKILL.md",[],[149,150,151,152,153,154,31,155,156,116,86,27,157,158,79,159,160],"testfx localization validation","validation","localization","validate","translation","ids","tokens","entries","units","duplicate","targets","build",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":168,"publishedAt":41},"01M699H9J2NWQXE4BDT6R0FH7S","testfx-acceptance-validation","Validate TestFx shipping paths and capable CI execution using packed consumers, package\u002Fcache provenance, exact exits and artifacts, and selected-versus-executed test evidence. Use for acceptance regressions, package\u002FMSBuild\u002Flauncher\u002Fprotocol changes, or skipped-only CI results; not for unrelated unit-only or documentation changes.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ftestfx\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ftestfx-acceptance-validation\u002FSKILL.md",[167],{"categoryNo":103,"categoryName":104,"taxonomyType":21,"taxonomyTypeDesc":22},[169,170,150,106,171,109,172,173,174,117,175,27,176,177,178,179,180,181,182,183,184,185,135,31],"testfx acceptance validation","acceptance","msbuild","launcher","ci","execution","package","cache","artifacts","provenance","documentation","unrelated","shipping","results","protocol","unit","ci results",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":192,"publishedAt":41},"01M699H70BB999BT4F627T1PHE","session-delivery-hygiene","Gate local-session scope, persistent delivery, live PR state, integration provenance, and owned cleanup. Use before implementing guidance changes, changing or pushing PR work, diagnosing package\u002Foutput mismatches, or handing off implementation.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ftestfx\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fsession-delivery-hygiene\u002FSKILL.md",[],[193,194,195,196,197,115,83,198,199,94,200,175,27,178,201,202,79,203,204,205],"session delivery hygiene","delivery","session","hygiene","scope","cleanup","work","pr","output","state","integration","guidance","gate"]