[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M758TSR35Y4CFZB570R185VM":3,"skill-same:01M758TSR35Y4CFZB570R185VM":63},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":13,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":42},"01M758TSR35Y4CFZB570R185VM","playtest-prd-prep",null,"Reconcile one validated Continuity Loom author-playtest report against live repo and tracker state, preserve proven strengths, and write one same-stem change portfolio for playtest-to-issues custody before any later \u002Fto-prd pass. Invoke explicitly with a reports\u002Fplaytest-*.md path; this skill diagnoses and prepares but does not implement or publish.","joeloverbeck\u002Fcontinuity-loom","joeloverbeck","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F120873?v=4","01M758KCBJ0GWAPGN74C9NJF8T","01M758KCCNQ8F0YS327T45F7C0",0,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fcontinuity-loom\u002Fblob\u002Fmain\u002Freports\u002Fskill-evidence\u002Fplaytest-prd-prep-200fcc29\u002Fdecontamination\u002Fdec_19a21bd7-5ca2-4cb8-a7cb-d2aa701824f4\u002Fcandidate\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: playtest-prd-prep\ndescription: Reconcile one validated Continuity Loom author-playtest report against live repo and tracker state, preserve proven strengths, and write one same-stem change portfolio for playtest-to-issues custody before any later \u002Fto-prd pass. Invoke explicitly with a reports\u002Fplaytest-*.md path; this skill diagnoses and prepares but does not implement or publish.\ndisable-model-invocation: true\n---\n\n# Playtest PRD Prep\n\nTurn one `.claude\u002Fskills\u002Fplaytest` report into\n`reports\u002F\u003Cplaytest-report-stem>-prd-prep.md`. This run may write only that prep artifact. Never\nedit the source report, product code, tests, docs, skills, specs, tickets, or tracker; never invoke\n`\u002Fto-prd` or satisfy its seam checkpoint. The validated artifact goes through\n`$playtest-to-issues` before any later `\u002Fto-prd` pass.\n\n## Intake\n\nRequire one canonical `reports\u002Fplaytest-\u003Cstory-slug>-\u003Ctimestamp>.md` path or an unambiguous glob.\nExclude assets and derivative `*-prd-prep.md` files. If needed, search `reports\u002F`\ncase-insensitively and proceed only when exactly one report resolves.\n\nRun:\n\n```bash\nnode .claude\u002Fskills\u002Fplaytest\u002Fscripts\u002Fvalidate-report.mjs --report \u003Creport>\nnode .claude\u002Fskills\u002Fplaytest-prd-prep\u002Fscripts\u002Fvalidate-prd-prep.mjs --inspect-source \u003Creport>\n```\n\nStop without writing when schema, privacy, or ledger failures make exhaustive disposition unsafe.\nContinue when the inspector explicitly classifies a bounded historical prompt-evaluation mismatch\nas nonblocking; disclose it and add the required `$skill-audit` maintenance follow-up without\nrepairing the source. Missing optional evidence, stale commits, unavailable tracker reads, and\nfailed reproduction are limitations, not source invalidation; affected items become verification\nwork.\n\nBefore analysis, record the canonical path, validation and inventory, run mode, prior-report\npointer and prior prep state, current same-stem prep state, branch, HEAD, and baseline worktree.\n\n## Reconcile\n\n### 1. Establish live evidence\n\n1. Retain exact `git status --short --untracked-files=all`,\n   `git branch --show-current`, and `git rev-parse HEAD` output. Pre-existing dirt remains\n   unowned unless this run explicitly adopts it.\n2. Read `AGENTS.md`, `docs\u002FACTIVE-DOCS.md`, `docs\u002FFOUNDATIONS.md`, affected active authorities,\n   `docs\u002Fagents\u002Fissue-tracker.md`, `docs\u002Fagents\u002Ftriage-labels.md`, and `tickets\u002FREADME.md`.\n   Use `archive\u002F**` only when explicitly routed as historical evidence.\n3. Read the complete report and use its Cumulative Finding Ledger as the frontier. Follow only its\n   explicit `prior_report` chain, and only when an `open`, `repeated`, or `not-retested` row\n   lacks decision-relevant detail. Never scan unrelated reports.\n4. Compare the launch HEAD with the current affected paths. Distinguish relevant committed drift,\n   relevant worktree drift, and unrelated dirt. Classify report durability with tracked, clean,\n   publication-ref-visible, and content-identical evidence; summarize but never cite machine-local\n   evidence.\n5. For a continuation, derive the prior report's same-stem prep. Treat it as historical\n   recommendations, not authority. If present, reconcile its first action, every PRD candidate,\n   and every non-PRD item as `consumed`, `still live`, `rejected`, or `superseded`; otherwise\n   record `missing at intake`.\n6. Apply the same reconciliation to any current same-stem prep before reusing it.\n7. Search exact report terms and IDs across current open and relevant closed tracker work. Start\n   with projected metadata; fetch bodies\u002Fcomments only for likely owners. If unavailable, record\n   that limitation and do not claim AFK-ready label certainty.\n\n### 2. Disposition the report\n\nGive every cumulative row exactly one disposition from the artifact contract; every prioritized ID\nmust already occur there. Treat observations as evidence, not mandates. Promote a stable rule only\nwhen supported by current source\u002Ftests, repeated evidence, deterministic reproduction, or governing\nauthority. Preserve one-run ambiguity and model variability as verification, coverage, or research\nunless a safe deterministic mitigation is justified.\n\nUse evidence in this order: report and privacy-safe evidence; current authorities, implementation,\nand focused tests; exact tracker overlap\u002Fcloseout; focused read-only probes; then a browser\nreproduction only if contradiction still blocks classification. For that last case, read\n[`browser-driver.md`](..\u002Fplaytest\u002Freferences\u002Fbrowser-driver.md), keep blank-key guarded localhost\nstate under `\u002Ftmp`, and do not start a full journey, accept prose, click provider controls, or make\nOpenRouter requests.\n\nEvery strength is a preservation constraint, mapped globally or to the work it constrains with\nregression evidence. It never creates scope. Finish with one supported disposition, destination,\nand PRD impact for every row.\n\n### 3. Build the smallest governed portfolio\n\nTrace each report-derived rule across mechanically affected code, tests, active docs, and skills;\nexclude work that does not trace to a row, strength, or required consistency consequence. Route:\n\n- broad or risky product behavior to a PRD candidate;\n- narrow scoped product work to a ticket candidate;\n- playtest\u002Freport process work to skill maintenance;\n- inaccurate active authority to a doc correction;\n- conflict with closed work to verification\u002Freopen;\n- insufficient evidence to coverage or research; and\n- covered, resolved, preference-only, duplicate, or disproportional work to covered\u002Frejected.\n\nBundle PRD rows only when product rule, decision, implementation seam, and acceptance proof align.\nDefault to one first PRD plus deferred follow-ons; use a multi-PRD program only for real dependency\nor shared ratification. No new PRD is valid.\n\nRank work by invariant risk, author trust\u002Fcore-loop impact, severity, dependency, evidence,\ntestability, and strength-regression risk. `First operational action` is the first substantive\naction custody must resolve—not `$playtest-to-issues`, `playtest-to-issues`, or `\u002Fto-prd`; use\n`none - \u003Creason>` when nothing precedes the remaining portfolio.\n\nDescribe behavior, authority, current seam, surfaces, acceptance, and testing at PRD-ready depth.\nAvoid patch order, volatile symbols, components, or abstractions unless architecture makes them\nunavoidable. If one material scope, sequence, or stewardship choice remains, ask one focused\nquestion with a recommendation; do not run a routine requirements interview.\n\n### 4. Write the artifact\n\nRead [the artifact contract](references\u002Fprep-format.md) in full immediately before writing. Write\nor rewrite the one default same-stem artifact at the contract's current version; never fork\nnumbered\u002Ftimestamped copies. The producer owns migration of older or unversioned prep artifacts and\nmust account for all prior recommendations.\n\nConsult `\u002Fto-prd` only for house style. Do not draft a PRD, create an issue, apply labels, or ask\nits seam question; record that the checkpoint remains owed. Keep the artifact privacy-safe: no full\nprompts, payloads, raw assistance, candidate\u002Faccepted prose, keys, localhost URLs, or machine-local\npaths. Summarize temporary evidence as `summarized, not cited`.\n\nThe artifact must let `\u002Fto-prd` select and draft the intended package without rereading the source\nfor provenance, scope, strengths, authorities, sequencing, or deferrals.\n\n### 5. Validate and close\n\nKeep the contract's three self-checks at their draft values and run:\n\n```bash\nnode .claude\u002Fskills\u002Fplaytest-prd-prep\u002Fscripts\u002Fvalidate-prd-prep.mjs --draft \u003Creport> \u003Cprep-artifact>\n```\n\nFix every error and compare emitted counts with the report. The helper proves shape\u002Fcoverage, not\nsemantics. Manually review dispositions, grouping, authorities, preservation, evidence, privacy,\nand stale language.\n\nImmediately before the freshness check, capture full status and branch again, replace the final\nworktree ledger with that exact snapshot, and classify every path. Then set the three final\nself-check values and run:\n\n```bash\nnode .claude\u002Fskills\u002Fplaytest-prd-prep\u002Fscripts\u002Fvalidate-prd-prep.mjs \u003Creport> \u003Cprep-artifact>\n```\n\nAfter a pass, capture status and branch again. If either differs from the validated snapshot,\nupdate the ledger, repeat affected semantic\u002Fprivacy\u002Ffreshness review, and revalidate until equal.\nDo not run root gates for this report-only change; report focused checks and skipped broader gates.\n\nCompletion requires an accepted source inspection, exhaustive row and strength coverage, passing\nfinal validation, completed semantic\u002Fprivacy\u002Ffreshness review, an exact worktree boundary, and the\n`$playtest-to-issues` handoff.\n\nRender this exact keyed block from the validated artifact as the final content:\n\n```text\nSource report: \u003Ccanonical source report>\nPrep artifact: \u003Csame-stem prep artifact>\nFirst operational action: \u003Csubstantive action or none - reason>\nPublication verdict: \u003Cpackage and intended first PRD, or no-new-PRD result>\nDeferred work: \u003Cevery deferred PRD candidate, or none>\nNon-PRD work: \u003Cevery item and destination, or none>\nIssue-custody handoff: $playtest-to-issues \"\u003Cprep-artifact>\"; required before \u002Fto-prd\nTracker and durability: \u003Ctracker limitations; source durability; artifact durability>\nIntentional change: \u003Cauthored prep artifact>\nRemaining dirt:\n- \u003Cpath>: \u003Cpre-existing, concurrent\u002Funowned, or intentional classification>\nNon-actions: no implementation, source-report edit, tracker mutation, PRD publication, or \u002Fto-prd seam checkpoint occurred\n```\n","# Playtest PRD Prep\n\nTurn one `.claude\u002Fskills\u002Fplaytest` report into\n`reports\u002F\u003Cplaytest-report-stem>-prd-prep.md`. This run may write only that prep artifact. Never\nedit the source report, product code, tests, docs, skills, specs, tickets, or tracker; never invoke\n`\u002Fto-prd` or satisfy its seam checkpoint. The validated artifact goes through\n`$playtest-to-issues` before any later `\u002Fto-prd` pass.\n\n## Intake\n\nRequire one canonical `reports\u002Fplaytest-\u003Cstory-slug>-\u003Ctimestamp>.md` path or an unambiguous glob.\nExclude assets and derivative `*-prd-prep.md` files. If needed, search `reports\u002F`\ncase-insensitively and proceed only when exactly one report resolves.\n\nRun:\n\n```bash\nnode .claude\u002Fskills\u002Fplaytest\u002Fscripts\u002Fvalidate-report.mjs --report \u003Creport>\nnode .claude\u002Fskills\u002Fplaytest-prd-prep\u002Fscripts\u002Fvalidate-prd-prep.mjs --inspect-source \u003Creport>\n```\n\nStop without writing when schema, privacy, or ledger failures make exhaustive disposition unsafe.\nContinue when the inspector explicitly classifies a bounded historical prompt-evaluation mismatch\nas nonblocking; disclose it and add the required `$skill-audit` maintenance follow-up without\nrepairing the source. Missing optional evidence, stale commits, unavailable tracker reads, and\nfailed reproduction are limitations, not source invalidation; affected items become verification\nwork.\n\nBefore analysis, record the canonical path, validation and inventory, run mode, prior-report\npointer and prior prep state, current same-stem prep state, branch, HEAD, and baseline worktree.\n\n## Reconcile\n\n### 1. Establish live evidence\n\n1. Retain exact `git status --short --untracked-files=all`,\n   `git branch --show-current`, and `git rev-parse HEAD` output. Pre-existing dirt remains\n   unowned unless this run explicitly adopts it.\n2. Read `AGENTS.md`, `docs\u002FACTIVE-DOCS.md`, `docs\u002FFOUNDATIONS.md`, affected active authorities,\n   `docs\u002Fagents\u002Fissue-tracker.md`, `docs\u002Fagents\u002Ftriage-labels.md`, and `tickets\u002FREADME.md`.\n   Use `archive\u002F**` only when explicitly routed as historical evidence.\n3. Read the complete report and use its Cumulative Finding Ledger as the frontier. Follow only its\n   explicit `prior_report` chain, and only when an `open`, `repeated`, or `not-retested` row\n   lacks decision-relevant detail. Never scan unrelated reports.\n4. Compare the launch HEAD with the current affected paths. Distinguish relevant committed drift,\n   relevant worktree drift, and unrelated dirt. Classify report durability with tracked, clean,\n   publication-ref-visible, and content-identical evidence; summarize but never cite machine-local\n   evidence.\n5. For a continuation, derive the prior report's same-stem prep. Treat it as historical\n   recommendations, not authority. If present, reconcile its first action, every PRD candidate,\n   and every non-PRD item as `consumed`, `still live`, `rejected`, or `superseded`; otherwise\n   record `missing at intake`.\n6. Apply the same reconciliation to any current same-stem prep before reusing it.\n7. Search exact report terms and IDs across current open and relevant closed tracker work. Start\n   with projected metadata; fetch bodies\u002Fcomments only for likely owners. If unavailable, record\n   that limitation and do not claim AFK-ready label certainty.\n\n### 2. Disposition the report\n\nGive every cumulative row exactly one disposition from the artifact contract; every prioritized ID\nmust already occur there. Treat observations as evidence, not mandates. Promote a stable rule only\nwhen supported by current source\u002Ftests, repeated evidence, deterministic reproduction, or governing\nauthority. Preserve one-run ambiguity and model variability as verification, coverage, or research\nunless a safe deterministic mitigation is justified.\n\nUse evidence in this order: report and privacy-safe evidence; current authorities, implementation,\nand focused tests; exact tracker overlap\u002Fcloseout; focused read-only probes; then a browser\nreproduction only if contradiction still blocks classification. For that last case, read\n[`browser-driver.md`](..\u002Fplaytest\u002Freferences\u002Fbrowser-driver.md), keep blank-key guarded localhost\nstate under `\u002Ftmp`, and do not start a full journey, accept prose, click provider controls, or make\nOpenRouter requests.\n\nEvery strength is a preservation constraint, mapped globally or to the work it constrains with\nregression evidence. It never creates scope. Finish with one supported disposition, destination,\nand PRD impact for every row.\n\n### 3. Build the smallest governed portfolio\n\nTrace each report-derived rule across mechanically affected code, tests, active docs, and skills;\nexclude work that does not trace to a row, strength, or required consistency consequence. Route:\n\n- broad or risky product behavior to a PRD candidate;\n- narrow scoped product work to a ticket candidate;\n- playtest\u002Freport process work to skill maintenance;\n- inaccurate active authority to a doc correction;\n- conflict with closed work to verification\u002Freopen;\n- insufficient evidence to coverage or research; and\n- covered, resolved, preference-only, duplicate, or disproportional work to covered\u002Frejected.\n\nBundle PRD rows only when product rule, decision, implementation seam, and acceptance proof align.\nDefault to one first PRD plus deferred follow-ons; use a multi-PRD program only for real dependency\nor shared ratification. No new PRD is valid.\n\nRank work by invariant risk, author trust\u002Fcore-loop impact, severity, dependency, evidence,\ntestability, and strength-regression risk. `First operational action` is the first substantive\naction custody must resolve—not `$playtest-to-issues`, `playtest-to-issues`, or `\u002Fto-prd`; use\n`none - \u003Creason>` when nothing precedes the remaining portfolio.\n\nDescribe behavior, authority, current seam, surfaces, acceptance, and testing at PRD-ready depth.\nAvoid patch order, volatile symbols, components, or abstractions unless architecture makes them\nunavoidable. If one material scope, sequence, or stewardship choice remains, ask one focused\nquestion with a recommendation; do not run a routine requirements interview.\n\n### 4. Write the artifact\n\nRead [the artifact contract](references\u002Fprep-format.md) in full immediately before writing. Write\nor rewrite the one default same-stem artifact at the contract's current version; never fork\nnumbered\u002Ftimestamped copies. The producer owns migration of older or unversioned prep artifacts and\nmust account for all prior recommendations.\n\nConsult `\u002Fto-prd` only for house style. Do not draft a PRD, create an issue, apply labels, or ask\nits seam question; record that the checkpoint remains owed. Keep the artifact privacy-safe: no full\nprompts, payloads, raw assistance, candidate\u002Faccepted prose, keys, localhost URLs, or machine-local\npaths. Summarize temporary evidence as `summarized, not cited`.\n\nThe artifact must let `\u002Fto-prd` select and draft the intended package without rereading the source\nfor provenance, scope, strengths, authorities, sequencing, or deferrals.\n\n### 5. Validate and close\n\nKeep the contract's three self-checks at their draft values and run:\n\n```bash\nnode .claude\u002Fskills\u002Fplaytest-prd-prep\u002Fscripts\u002Fvalidate-prd-prep.mjs --draft \u003Creport> \u003Cprep-artifact>\n```\n\nFix every error and compare emitted counts with the report. The helper proves shape\u002Fcoverage, not\nsemantics. Manually review dispositions, grouping, authorities, preservation, evidence, privacy,\nand stale language.\n\nImmediately before the freshness check, capture full status and branch again, replace the final\nworktree ledger with that exact snapshot, and classify every path. Then set the three final\nself-check values and run:\n\n```bash\nnode .claude\u002Fskills\u002Fplaytest-prd-prep\u002Fscripts\u002Fvalidate-prd-prep.mjs \u003Creport> \u003Cprep-artifact>\n```\n\nAfter a pass, capture status and branch again. If either differs from the validated snapshot,\nupdate the ledger, repeat affected semantic\u002Fprivacy\u002Ffreshness review, and revalidate until equal.\nDo not run root gates for this report-only change; report focused checks and skipped broader gates.\n\nCompletion requires an accepted source inspection, exhaustive row and strength coverage, passing\nfinal validation, completed semantic\u002Fprivacy\u002Ffreshness review, an exact worktree boundary, and the\n`$playtest-to-issues` handoff.\n\nRender this exact keyed block from the validated artifact as the final content:\n\n```text\nSource report: \u003Ccanonical source report>\nPrep artifact: \u003Csame-stem prep artifact>\nFirst operational action: \u003Csubstantive action or none - reason>\nPublication verdict: \u003Cpackage and intended first PRD, or no-new-PRD result>\nDeferred work: \u003Cevery deferred PRD candidate, or none>\nNon-PRD work: \u003Cevery item and destination, or none>\nIssue-custody handoff: $playtest-to-issues \"\u003Cprep-artifact>\"; required before \u002Fto-prd\nTracker and durability: \u003Ctracker limitations; source durability; artifact durability>\nIntentional change: \u003Cauthored prep artifact>\nRemaining dirt:\n- \u003Cpath>: \u003Cpre-existing, concurrent\u002Funowned, or intentional classification>\nNon-actions: no implementation, source-report edit, tracker mutation, PRD publication, or \u002Fto-prd seam checkpoint occurred\n```\n",{"name":5,"description":7,"disable-model-invocation":23},true,"main","bb13c72ec4134361fec0b0584913aee821330c02","reports\u002Fskill-evidence\u002Fplaytest-prd-prep-200fcc29\u002Fdecontamination\u002Fdec_19a21bd7-5ca2-4cb8-a7cb-d2aa701824f4\u002Fcandidate","https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fcontinuity-loom","https:\u002F\u002Fgithub.com\u002Fjoeloverbeck","2026-11-10 23:00:02",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":23},[32,35,38],{"tool":33,"command":34},"npx","npx skills add joeloverbeck\u002Fcontinuity-loom --skill playtest-prd-prep",{"tool":36,"command":37},"bunx","bunx skills add joeloverbeck\u002Fcontinuity-loom --skill playtest-prd-prep",{"tool":39,"command":40},"pnpm","pnpm dlx skills add joeloverbeck\u002Fcontinuity-loom --skill playtest-prd-prep","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fcontinuity-loom\u002Fblob\u002Fmain\u002Freports\u002Fskill-evidence\u002Fplaytest-prd-prep-200fcc29\u002Fdecontamination\u002Fdec_19a21bd7-5ca2-4cb8-a7cb-d2aa701824f4\u002Fcandidate\u002FSKILL.md",[43,49,53,59],{"path":44,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":47,"sourceHtmlUrl":48},"agents\u002Fopenai.yaml","REFERENCE","参考文档",285,"https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fcontinuity-loom\u002Fblob\u002Fmain\u002Freports\u002Fskill-evidence\u002Fplaytest-prd-prep-200fcc29\u002Fdecontamination\u002Fdec_19a21bd7-5ca2-4cb8-a7cb-d2aa701824f4\u002Fcandidate\u002Fagents\u002Fopenai.yaml",{"path":50,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fprep-format.md",12203,"https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fcontinuity-loom\u002Fblob\u002Fmain\u002Freports\u002Fskill-evidence\u002Fplaytest-prd-prep-200fcc29\u002Fdecontamination\u002Fdec_19a21bd7-5ca2-4cb8-a7cb-d2aa701824f4\u002Fcandidate\u002Freferences\u002Fprep-format.md",{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"scripts\u002Fvalidate-prd-prep.mjs","SCRIPT","脚本",49959,"https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fcontinuity-loom\u002Fblob\u002Fmain\u002Freports\u002Fskill-evidence\u002Fplaytest-prd-prep-200fcc29\u002Fdecontamination\u002Fdec_19a21bd7-5ca2-4cb8-a7cb-d2aa701824f4\u002Fcandidate\u002Fscripts\u002Fvalidate-prd-prep.mjs",{"path":60,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Fvalidate-prd-prep.test.mjs",33128,"https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fcontinuity-loom\u002Fblob\u002Fmain\u002Freports\u002Fskill-evidence\u002Fplaytest-prd-prep-200fcc29\u002Fdecontamination\u002Fdec_19a21bd7-5ca2-4cb8-a7cb-d2aa701824f4\u002Fcandidate\u002Fscripts\u002Fvalidate-prd-prep.test.mjs",[64,71,76,81,88,93],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M758XG3F9AESCQBKYQX0GPSD","triage","Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.","https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fcontinuity-loom\u002Fblob\u002Fmain\u002Freports\u002Fskill-evidence\u002Ftriage\u002Freviews\u002Frev_a4ce832d-b023-4fa0-8d5d-382e558791d8\u002Fcandidate\u002FSKILL.md",[],[],{"skillNo":72,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":18},"01M758XDY39PNPRY8FSXVE8SZN","https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fcontinuity-loom\u002Fblob\u002Fmain\u002Freports\u002Fskill-evidence\u002Ftriage\u002Fdecontamination\u002Fdec_2d4305f8-ee96-4376-a267-061413c4fdd6\u002Fcandidate\u002FSKILL.md",[],[],{"skillNo":77,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M758XB4XZ6N5XP8XZXWVMVQ0","https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fcontinuity-loom\u002Fblob\u002Fmain\u002Freports\u002Fskill-evidence\u002Ftriage\u002Fdecontamination\u002Fdec_2d4305f8-ee96-4376-a267-061413c4fdd6\u002Fbaseline\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M758X7WRCGV9BM5RNEGH4MSX","to-prd","Turn the current conversation into a PRD and publish it to the project issue tracker — no requirements interview, just synthesis of what you've already discussed; the seam confirmation is the sole checkpoint.","https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fcontinuity-loom\u002Fblob\u002Fmain\u002Freports\u002Fskill-evidence\u002Fto-prd\u002Fdecontamination\u002Fdec_581ad8e4-4f9d-4aad-a6ee-59eeec05c8a4\u002Fpre-land-backup\u002FSKILL.md",[],[],{"skillNo":89,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M758X55QJQTVHH1MWHJF2BBZ","https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fcontinuity-loom\u002Fblob\u002Fmain\u002Freports\u002Fskill-evidence\u002Fto-prd\u002Fdecontamination\u002Fdec_581ad8e4-4f9d-4aad-a6ee-59eeec05c8a4\u002Fcandidate\u002FSKILL.md",[],[],{"skillNo":94,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":18},"01M758X1Z0F2YRRHNTR3ZCY02C","https:\u002F\u002Fgithub.com\u002Fjoeloverbeck\u002Fcontinuity-loom\u002Fblob\u002Fmain\u002Freports\u002Fskill-evidence\u002Fto-prd\u002Fdecontamination\u002Fdec_581ad8e4-4f9d-4aad-a6ee-59eeec05c8a4\u002Fbaseline\u002FSKILL.md",[],[]]