[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KX2NDD83W61499E6VN1TN3":3,"skill-same:01M6KX2NDD83W61499E6VN1TN3":73},{"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":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M6KX2NDD83W61499E6VN1TN3","issue-restructure",null,"Split one GitHub issue into focused replacements, or merge several into one keeper, migrating substance and cross-linking before closing.","dougborg\u002Fharness-kit","dougborg","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1261222?v=4","01M6KWS4PB51EYD4ZDJJSGNGB2","Doug Borg","01M6KWS4T8ZZW6SX5QZS9B5BN2",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fproject-management\u002Fissue-restructure\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32],"issue","issue restructure","github","merge","gh issue","api","Bash","gh","repo","read","github issue","closing","split","linking","2026-11-10 10:12:30",false,"---\nname: issue-restructure\ndescription: Split one GitHub issue into focused replacements, or merge several into one keeper, migrating substance and cross-linking before closing.\nargument-hint: \"split \u003C#> | merge \u003C#> \u003C#> [#...]\"\nallowed-tools: Bash(gh issue *), Bash(gh api *), Bash(gh repo *), Read\n---\n\n# Issue Restructure\n\nChange how issues partition the work: one into many (`split`) or many into one\n(`merge`), without losing the comment-thread substance the old partition\nproduced. Both modes migrate before they close, the user previews every title,\nbody, and label set before anything is filed or closed, and every keeper and\nsource end up linking to each other.\n\n## 1. Read every involved issue\n\n```bash\ngh issue view \u003C#> --json title,body,state,labels,comments\n```\n\nFor `split`, read `\u003C#>`; for `merge`, read all of them. The comments often\nhold the latest framing the body misses. From each, collect what isn't\nalready on the keeper or replacements:\n\n- alternative approaches proposed in replies;\n- corrections after filing (\"this was wrong, the real issue is …\");\n- `file:line` samples added later;\n- cross-links to other issues and PRs;\n- labels triagers added after filing that hint at scope.\n\nEach is a migration candidate. `--json comments` returns at most the first\n100; for a longer thread, fetch them all:\n\n```bash\ngh api --paginate \"repos\u002F\u003Cowner>\u002F\u003Crepo>\u002Fissues\u002F\u003C#>\u002Fcomments\"\n```\n\nFor a merge of more than five issues, or issues across repositories, read\n[bulk-and-cross-repo.md](bulk-and-cross-repo.md) first.\n\nDone when you have a list of migration candidates for every issue involved.\n\n## 2. Split\n\n1. Confirm `\u003C#>` covers genuinely independent work streams, because splitting\n   fragments discussion. Keep one issue when the pieces add up to a single\n   PR, when the user only wants sub-tasks (use body checkboxes), or when\n   every piece hangs on the same upstream decision (list the options in one\n   issue). If it only needs reframing, call the Skill tool with\n   \"issue-update\" instead and stop here.\n2. Draft the replacements, each with a clear title, scope, labels, and a link\n   back to `\u003C#>`. Place each migration candidate in the replacement it\n   belongs to.\n3. Show the user the plan and wait for confirmation:\n\n   ```text\n   Splitting #\u003Csrc> into:\n\n     #A: \u003Ctitle>\n         Scope: \u003Cone sentence>\n         Labels: \u003Clist>\n\n     #B: \u003Ctitle>\n         Scope: \u003Cone sentence>\n         Labels: \u003Clist>\n\n     #C: ...\n\n   #\u003Csrc> will be closed with: \"Split into #A \u002F #B \u002F #C — ...\"\n   Original body will be edited to point to replacements.\n   ```\n\n4. File the replacements in order, calling the Skill tool with\n   \"issue-create\" once per replacement, so each gets the same duplicate\n   search, labels, and preview. Tell each call that `\u003C#>` is the known source\n   being split: an adjacent issue to link, not a duplicate to stop on.\n5. Edit `\u003C#>`'s body to open with \"Split into #A, #B, #C\", then close it:\n\n   ```bash\n   gh issue edit \u003C#> --body-file - \u003C\u003C'EOF'\n   > Split into #A, #B, #C.\n\n   \u003Coriginal body>\n   EOF\n   gh issue close \u003C#> --comment \"Split into #A \u002F #B \u002F #C — see body for scope each covers.\"\n   ```\n\nDone when every replacement is filed and links back, and `\u003C#>` is closed\npointing at all of them.\n\n## 3. Merge\n\nThe inverse of split: each non-keeper is superseded by the keeper.\n\n1. Pick the keeper, in this order: the broadest accurate scope (its framing\n   already covers the others), then the most discussion (the longest thread\n   stays in place without migration), then the most recent activity\n   (readers expect a current issue to be active), then the lowest number\n   (older is more canonical). If no issue clearly qualifies, the set\n   probably shouldn't merge: call the Skill tool with \"issue-create\" for a\n   new umbrella, then once per old issue with \"issue-close\" in `supersede`\n   mode, and stop here.\n2. Draft **one** consolidated migration comment on the keeper, grouping the\n   migrated content by source issue and linking each source, and the label\n   change if the keeper's scope grew.\n3. Show the user the migration comment and the label diff, and wait for\n   confirmation. Then post them:\n\n   ```bash\n   gh issue comment \u003Ckeeper#> --body-file - \u003C\u003C'EOF'\n   \u003Cmigration comment>\n   EOF\n   gh issue edit \u003Ckeeper#> --add-label \"...\"   # only if scope grew\n   ```\n\n4. Close the non-keepers by calling the Skill tool with \"issue-close\" once\n   per non-keeper, as `supersede \u003Cnon-keeper#> \u003Ckeeper#>`. Tell each call the\n   substance is already migrated, so it only drafts and previews the close\n   comment (\"Merged into #\u003Ckeeper>\", with a pointer to that source's section\n   of the migration comment).\n\nDone when every migration candidate is on the keeper, the migration comment\nlinks every source, every non-keeper is closed pointing at the keeper, and\nthe keeper's labels match its scope.\n\n## Related\n\n- `issue-create` — files each replacement during `split`.\n- `issue-close` — `merge` closes each non-keeper through its `supersede`\n  mode.\n- `issue-update` — use it instead of `split` when the issue only needs\n  reframing.\n","# Issue Restructure\n\nChange how issues partition the work: one into many (`split`) or many into one\n(`merge`), without losing the comment-thread substance the old partition\nproduced. Both modes migrate before they close, the user previews every title,\nbody, and label set before anything is filed or closed, and every keeper and\nsource end up linking to each other.\n\n## 1. Read every involved issue\n\n```bash\ngh issue view \u003C#> --json title,body,state,labels,comments\n```\n\nFor `split`, read `\u003C#>`; for `merge`, read all of them. The comments often\nhold the latest framing the body misses. From each, collect what isn't\nalready on the keeper or replacements:\n\n- alternative approaches proposed in replies;\n- corrections after filing (\"this was wrong, the real issue is …\");\n- `file:line` samples added later;\n- cross-links to other issues and PRs;\n- labels triagers added after filing that hint at scope.\n\nEach is a migration candidate. `--json comments` returns at most the first\n100; for a longer thread, fetch them all:\n\n```bash\ngh api --paginate \"repos\u002F\u003Cowner>\u002F\u003Crepo>\u002Fissues\u002F\u003C#>\u002Fcomments\"\n```\n\nFor a merge of more than five issues, or issues across repositories, read\n[bulk-and-cross-repo.md](bulk-and-cross-repo.md) first.\n\nDone when you have a list of migration candidates for every issue involved.\n\n## 2. Split\n\n1. Confirm `\u003C#>` covers genuinely independent work streams, because splitting\n   fragments discussion. Keep one issue when the pieces add up to a single\n   PR, when the user only wants sub-tasks (use body checkboxes), or when\n   every piece hangs on the same upstream decision (list the options in one\n   issue). If it only needs reframing, call the Skill tool with\n   \"issue-update\" instead and stop here.\n2. Draft the replacements, each with a clear title, scope, labels, and a link\n   back to `\u003C#>`. Place each migration candidate in the replacement it\n   belongs to.\n3. Show the user the plan and wait for confirmation:\n\n   ```text\n   Splitting #\u003Csrc> into:\n\n     #A: \u003Ctitle>\n         Scope: \u003Cone sentence>\n         Labels: \u003Clist>\n\n     #B: \u003Ctitle>\n         Scope: \u003Cone sentence>\n         Labels: \u003Clist>\n\n     #C: ...\n\n   #\u003Csrc> will be closed with: \"Split into #A \u002F #B \u002F #C — ...\"\n   Original body will be edited to point to replacements.\n   ```\n\n4. File the replacements in order, calling the Skill tool with\n   \"issue-create\" once per replacement, so each gets the same duplicate\n   search, labels, and preview. Tell each call that `\u003C#>` is the known source\n   being split: an adjacent issue to link, not a duplicate to stop on.\n5. Edit `\u003C#>`'s body to open with \"Split into #A, #B, #C\", then close it:\n\n   ```bash\n   gh issue edit \u003C#> --body-file - \u003C\u003C'EOF'\n   > Split into #A, #B, #C.\n\n   \u003Coriginal body>\n   EOF\n   gh issue close \u003C#> --comment \"Split into #A \u002F #B \u002F #C — see body for scope each covers.\"\n   ```\n\nDone when every replacement is filed and links back, and `\u003C#>` is closed\npointing at all of them.\n\n## 3. Merge\n\nThe inverse of split: each non-keeper is superseded by the keeper.\n\n1. Pick the keeper, in this order: the broadest accurate scope (its framing\n   already covers the others), then the most discussion (the longest thread\n   stays in place without migration), then the most recent activity\n   (readers expect a current issue to be active), then the lowest number\n   (older is more canonical). If no issue clearly qualifies, the set\n   probably shouldn't merge: call the Skill tool with \"issue-create\" for a\n   new umbrella, then once per old issue with \"issue-close\" in `supersede`\n   mode, and stop here.\n2. Draft **one** consolidated migration comment on the keeper, grouping the\n   migrated content by source issue and linking each source, and the label\n   change if the keeper's scope grew.\n3. Show the user the migration comment and the label diff, and wait for\n   confirmation. Then post them:\n\n   ```bash\n   gh issue comment \u003Ckeeper#> --body-file - \u003C\u003C'EOF'\n   \u003Cmigration comment>\n   EOF\n   gh issue edit \u003Ckeeper#> --add-label \"...\"   # only if scope grew\n   ```\n\n4. Close the non-keepers by calling the Skill tool with \"issue-close\" once\n   per non-keeper, as `supersede \u003Cnon-keeper#> \u003Ckeeper#>`. Tell each call the\n   substance is already migrated, so it only drafts and previews the close\n   comment (\"Merged into #\u003Ckeeper>\", with a pointer to that source's section\n   of the migration comment).\n\nDone when every migration candidate is on the keeper, the migration comment\nlinks every source, every non-keeper is closed pointing at the keeper, and\nthe keeper's labels match its scope.\n\n## Related\n\n- `issue-create` — files each replacement during `split`.\n- `issue-close` — `merge` closes each non-keeper through its `supersede`\n  mode.\n- `issue-update` — use it instead of `split` when the issue only needs\n  reframing.\n",{"name":5,"description":7,"allowed-tools":38,"argument-hint":39},"Bash(gh issue *), Bash(gh api *), Bash(gh repo *), Read","split \u003C#> | merge \u003C#> \u003C#> [#...]","main","023b01bfb4a86fbf1e38a749f1044cce3e5da67d","skills\u002Fproject-management\u002Fissue-restructure",1,"https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit","https:\u002F\u002Fgithub.com\u002Fdougborg","http:\u002F\u002Fdougborg.org","Platforms and Infrastructure Software Engineer","2026-11-13 07:43:37",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add dougborg\u002Fharness-kit --skill issue-restructure",{"tool":55,"command":56},"bunx","bunx skills add dougborg\u002Fharness-kit --skill issue-restructure",{"tool":58,"command":59},"pnpm","pnpm dlx skills add dougborg\u002Fharness-kit --skill issue-restructure","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fproject-management\u002Fissue-restructure\u002FSKILL.md",true,[63,69],{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"agents\u002Fopenai.yaml","REFERENCE","参考文档",171,"https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fproject-management\u002Fissue-restructure\u002Fagents\u002Fopenai.yaml",{"path":70,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":71,"sourceHtmlUrl":72},"bulk-and-cross-repo.md",809,"https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fproject-management\u002Fissue-restructure\u002Fbulk-and-cross-repo.md",[74,93,113,146,170,187],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":85,"publishedAt":33},"01M6KX4J65S5FZKMSN5DQNPSZM","teach","Teach yourself a topic over several sessions, with lessons, references, and a record of what you've learned.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fteach\u002FSKILL.md",[80],{"categoryNo":81,"categoryName":82,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000039","教师与教育","PROFESSION","适用职业",[76,86,87,88,89,90,91,92],"lessons","you","with","learned","record","references","sessions",{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":104,"publishedAt":33},"01M6KX4FSSG7MHF00JDT5QT0BQ","svg-logo-designer","Generate SVG logos with multiple concepts, layouts, and color variations.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fsvg-logo-designer\u002FSKILL.md",[99],{"categoryNo":100,"categoryName":101,"taxonomyType":102,"taxonomyTypeDesc":103},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[105,106,107,108,109,110,88,111,28,112],"logo","designer","svg logo designer","SVG","color","concepts","write","generate",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":125,"publishedAt":33},"01M6KX4BD3J9MZPPSH4MENH7FP","documentation-writer","Writes and revises human-facing documentation — READMEs, contributor and setup guides, reference pages, architecture notes, CLAUDE.md, and changelog entries. Covers picking the right document type for the question being asked, structuring for skimming, writing examples that actually run, and keeping docs from going stale. Use when creating or rewriting docs, when a README has drifted from the code, or when deciding where a piece of information belongs. For SKILL.md and agent files, use \u002Fskill-writer instead.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fdocumentation-writer\u002FSKILL.md",[119,122],{"categoryNo":120,"categoryName":121,"taxonomyType":102,"taxonomyTypeDesc":103},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":123,"categoryName":124,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000036","内容创作者",[126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145],"writer","documentation writer","documentation","entries","changelog","architecture","document","files","use","question","README","notes","code","examples","pages","for","information","guides","type","writing",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":33},"01M6KX47ZJ4ZWHDN3MY8SYAWZZ","adhd-mode","Shapes every response for a reader with ADHD: the next action first, numbered steps, progress restated each turn, tangents held back, concrete time estimates, wins made visible. Stays on for the rest of the session until the reader says \"stop adhd mode\". On Claude Code, the harness-kit:adhd output style does the same without invoking this skill.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fadhd-mode\u002FSKILL.md",[],[153,154,155,156,141,157,158,88,159,160,161,162,163,164,165,166,167,168,169,138],"adhd","mode","adhd mode","next","action","kit","output","style","progress","time","back","stop","session","reader","first","REST","harness",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":33},"01M6KX463Z6E18EPDW873GDHKB","wait-what","That last message didn't land: re-explain it with the missing context.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fthinking\u002Fwait-what\u002FSKILL.md",[],[177,178,179,88,180,181,182,183,184,185,186],"wait","wait what","re","it","missing","message","context","explain","land","last",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":193,"publishedAt":33},"01M6KX43NE1NB0Y2HECY515730","to-questionnaire","Turn a decision you can't make alone into a questionnaire for the one person who can answer it, filled in async or together in a meeting.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fthinking\u002Fto-questionnaire\u002FSKILL.md",[],[194,195,141,196,197,198,199,87,200,180,201,202],"to questionnaire","questionnaire","person","can","answer","meeting","make","async","decision"]