[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7B68F0GCQSF1V4SEGCW7100":3,"skill-same:01M7B68F0GCQSF1V4SEGCW7100":51},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7B68F0GCQSF1V4SEGCW7100","to-tickets",null,"Turn an established plan into independently verifiable vertical implementation slices with acceptance criteria, verification, and true dependencies. Use when breaking planned work into tickets; small changes can stay as one task.","scruffydan\u002FAI-Agents","scruffydan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F2068435?v=4","01M6C56C2R0BYE41M4FV0TFTYK","Dan Moutal","01M6C56C6D1V2XHNXQ3NA3Z80V",0,"MIT","https:\u002F\u002Fgithub.com\u002Fscruffydan\u002FAI-Agents\u002Fblob\u002Fmain\u002Fsource\u002Fskills\u002Fto-tickets\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fscruffydan\u002FAI-Agents\u002Fblob\u002Fmain\u002Fsource\u002Fskills\u002Fto-tickets\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: to-tickets\ndescription: Turn an established plan into independently verifiable vertical implementation slices with acceptance criteria, verification, and true dependencies. Use when breaking planned work into tickets; small changes can stay as one task.\n---\n\n# Turn a Plan into Tickets\n\nConvert an established plan into the smallest useful set of implementation slices.\nEach slice should deliver a narrow, complete behavior that can be demonstrated\nand verified through the relevant layers. Avoid separate database, backend, and\nUI tickets when none would establish a useful outcome on its own. Infrastructure\nor internal changes can deliver an observable operational or developer outcome.\nIf one focused task suffices, keep it as one; do not manufacture a backlog.\n\n## Reuse the plan\n\nRead the relevant plan, repository guidance, affected code, and verification\ncommands within current permissions. Reuse accepted scope, decisions, and\nconstraints rather than reopening them. Use the existing task record and\n`project-context` workflow when available; avoid parallel records or separate\ndebt ledgers. `thorough-plan` develops an approach; this skill decomposes an\nestablished approach. If the plan lacks a consequential decision, identify the\nspecific gap and continue slicing unaffected work. Ask only when the answer\nmaterially changes the slices; label assumptions and proposals as such.\n\n## Choose slices and dependencies\n\nStart with the smallest complete path that proves the approach, then extend\nbehavior in useful increments. Include integration, error handling, and relevant\ntests in each slice rather than postponing them to a final integration ticket.\nKeep the project working between slices. Scope slices for reviewable outcomes,\nnot a fixed duration, file count, or number of tickets.\n\nRecord a dependency only when another slice must supply a concrete capability,\ninterface, data state, or decision before this slice can complete. Name that\nprerequisite and explain why. Distinguish a preferred order from a true blocker;\nmark independent slices explicitly. Break dependency cycles by narrowing scope\nor agreeing on a stable interface. Do not claim independence when verification\nstill requires unfinished work. For unresolved external blockers, name the missing\ninput, affected slices, and what would unblock them without inventing an owner\nor deadline.\n\nWhere persisted data or compatibility warrants staged change, consider\nexpand–migrate–contract:\n\n- **Expand:** add compatible interfaces or storage while existing consumers work.\n- **Migrate:** move consumers or backfill data in verifiable increments; include\n  coexistence, failure recovery, and data preservation checks as relevant.\n- **Contract:** remove old paths only after evidence shows migration is complete\n  and the agreed compatibility window has ended.\n\nMake those prerequisites explicit. Use a simpler direct change when it meets the\nproject's compatibility and data requirements; this pattern is not a required\narchitecture.\n\n## Present actionable tickets\n\nDefault to the conversation. For each slice, provide a concise title and:\n\n- **Outcome:** the observable behavior or capability and its link to the plan's\n  requirement or goal.\n- **Scope:** included work, relevant components, and boundaries needed to prevent\n  overlap or unplanned expansion.\n- **Acceptance criteria:** observable success and relevant failure, compatibility,\n  or data preservation behavior; avoid vague criteria such as “works correctly.”\n- **Verification:** specific existing checks, proportionate new tests, or manual\n  observations that would establish the criteria. Label planned checks as planned;\n  a drafted ticket is not completion evidence.\n- **Dependencies\u002Fblockers:** prerequisite slice IDs and reasons, unresolved inputs,\n  or “None.” Distinguish completion dependencies from work that can start now.\n\nUse stable IDs when useful for cross-references. Keep enough context in each ticket\nfor implementation without reconstructing the whole conversation; link the source\nplan and accepted decisions instead of duplicating them. Finish by checking that\nin-scope requirements are covered, every ticket has an independently verifiable\noutcome, dependencies are justified, and no unrelated work has slipped in.\n\nWriting files or updating a tracker requires authorization for that destination;\nreuse authorization already given. Ticket decomposition alone does not authorize\nsetup, external ticket creation, publication, implementation, or delegated execution.\nWhen saving is authorized, update the existing task record rather than creating a\nsecond ledger. Report what was actually saved or created and any remaining gaps.\n\n## Source\n\nAdapted from selected ideas in Matt Pocock's\n[to-tickets skill](https:\u002F\u002Fgithub.com\u002Fmattpocock\u002Fskills\u002Fblob\u002F9e2abf8611a345efbf779aacb171cff015bcdeb6\u002Fskills\u002Fengineering\u002Fto-tickets\u002FSKILL.md):\nvertical slices, explicit blockers, and expand–migrate–contract.\nThe upstream MIT notice is retained in [LICENSE](LICENSE).\n","# Turn a Plan into Tickets\n\nConvert an established plan into the smallest useful set of implementation slices.\nEach slice should deliver a narrow, complete behavior that can be demonstrated\nand verified through the relevant layers. Avoid separate database, backend, and\nUI tickets when none would establish a useful outcome on its own. Infrastructure\nor internal changes can deliver an observable operational or developer outcome.\nIf one focused task suffices, keep it as one; do not manufacture a backlog.\n\n## Reuse the plan\n\nRead the relevant plan, repository guidance, affected code, and verification\ncommands within current permissions. Reuse accepted scope, decisions, and\nconstraints rather than reopening them. Use the existing task record and\n`project-context` workflow when available; avoid parallel records or separate\ndebt ledgers. `thorough-plan` develops an approach; this skill decomposes an\nestablished approach. If the plan lacks a consequential decision, identify the\nspecific gap and continue slicing unaffected work. Ask only when the answer\nmaterially changes the slices; label assumptions and proposals as such.\n\n## Choose slices and dependencies\n\nStart with the smallest complete path that proves the approach, then extend\nbehavior in useful increments. Include integration, error handling, and relevant\ntests in each slice rather than postponing them to a final integration ticket.\nKeep the project working between slices. Scope slices for reviewable outcomes,\nnot a fixed duration, file count, or number of tickets.\n\nRecord a dependency only when another slice must supply a concrete capability,\ninterface, data state, or decision before this slice can complete. Name that\nprerequisite and explain why. Distinguish a preferred order from a true blocker;\nmark independent slices explicitly. Break dependency cycles by narrowing scope\nor agreeing on a stable interface. Do not claim independence when verification\nstill requires unfinished work. For unresolved external blockers, name the missing\ninput, affected slices, and what would unblock them without inventing an owner\nor deadline.\n\nWhere persisted data or compatibility warrants staged change, consider\nexpand–migrate–contract:\n\n- **Expand:** add compatible interfaces or storage while existing consumers work.\n- **Migrate:** move consumers or backfill data in verifiable increments; include\n  coexistence, failure recovery, and data preservation checks as relevant.\n- **Contract:** remove old paths only after evidence shows migration is complete\n  and the agreed compatibility window has ended.\n\nMake those prerequisites explicit. Use a simpler direct change when it meets the\nproject's compatibility and data requirements; this pattern is not a required\narchitecture.\n\n## Present actionable tickets\n\nDefault to the conversation. For each slice, provide a concise title and:\n\n- **Outcome:** the observable behavior or capability and its link to the plan's\n  requirement or goal.\n- **Scope:** included work, relevant components, and boundaries needed to prevent\n  overlap or unplanned expansion.\n- **Acceptance criteria:** observable success and relevant failure, compatibility,\n  or data preservation behavior; avoid vague criteria such as “works correctly.”\n- **Verification:** specific existing checks, proportionate new tests, or manual\n  observations that would establish the criteria. Label planned checks as planned;\n  a drafted ticket is not completion evidence.\n- **Dependencies\u002Fblockers:** prerequisite slice IDs and reasons, unresolved inputs,\n  or “None.” Distinguish completion dependencies from work that can start now.\n\nUse stable IDs when useful for cross-references. Keep enough context in each ticket\nfor implementation without reconstructing the whole conversation; link the source\nplan and accepted decisions instead of duplicating them. Finish by checking that\nin-scope requirements are covered, every ticket has an independently verifiable\noutcome, dependencies are justified, and no unrelated work has slipped in.\n\nWriting files or updating a tracker requires authorization for that destination;\nreuse authorization already given. Ticket decomposition alone does not authorize\nsetup, external ticket creation, publication, implementation, or delegated execution.\nWhen saving is authorized, update the existing task record rather than creating a\nsecond ledger. Report what was actually saved or created and any remaining gaps.\n\n## Source\n\nAdapted from selected ideas in Matt Pocock's\n[to-tickets skill](https:\u002F\u002Fgithub.com\u002Fmattpocock\u002Fskills\u002Fblob\u002F9e2abf8611a345efbf779aacb171cff015bcdeb6\u002Fskills\u002Fengineering\u002Fto-tickets\u002FSKILL.md):\nvertical slices, explicit blockers, and expand–migrate–contract.\nThe upstream MIT notice is retained in [LICENSE](LICENSE).\n",{"name":5,"description":7},"main","d384d240bc9515ef5d58bbf638aef5e767854c51","source\u002Fskills\u002Fto-tickets","https:\u002F\u002Fgithub.com\u002Fscruffydan\u002FAI-Agents","https:\u002F\u002Fgithub.com\u002Fscruffydan","ofdan.ca","Friendly neighbourhood sysadmin","2026-11-14 04:31:13",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add scruffydan\u002FAI-Agents --skill to-tickets",{"tool":39,"command":40},"bunx","bunx skills add scruffydan\u002FAI-Agents --skill to-tickets",{"tool":42,"command":43},"pnpm","pnpm dlx skills add scruffydan\u002FAI-Agents --skill to-tickets","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fscruffydan\u002FAI-Agents\u002Fblob\u002Fmain\u002Fsource\u002Fskills\u002Fto-tickets\u002FSKILL.md",true,[47],{"path":48,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":16},"LICENSE","许可证",1068,[52,60,68,76,84,92],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":56,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":20},"01M7B68RJTMNJJRM89EGMGQ1WJ","writing-for-agents","Author or revise agent instruction artifacts such as AGENTS.md, skill instructions, and agent prompts. Use for their triggers, structure, constraints, and completion criteria, not ordinary coding answers or general prose editing.","https:\u002F\u002Fgithub.com\u002Fscruffydan\u002FAI-Agents\u002Fblob\u002Fmain\u002Fsource\u002Fskills\u002Fwriting-for-agents\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fscruffydan\u002FAI-Agents\u002Fblob\u002Fmain\u002Fsource\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":64,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":20},"01M7B68NGQRJXA232T7X9SQ9HM","why","Investigate why a design or architectural choice was made, using code history and decision records. Use for rationale questions like why X was built this way or chosen over Y, not how code works today (use teach), debugging failures, or Five Whys process analysis.","https:\u002F\u002Fgithub.com\u002Fscruffydan\u002FAI-Agents\u002Fblob\u002Fmain\u002Fsource\u002Fskills\u002Fwhy\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fscruffydan\u002FAI-Agents\u002Fblob\u002Fmain\u002Fsource\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":72,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":20},"01M7B68J77GKP1C1T1XF1DZ97V","unslop","Edit prose to remove AI writing patterns such as stock vocabulary, filler, hedging, and mannered phrasing. Use when asked to unslop or de-AI text, or to polish a substantial prose draft; not for code, short routine replies, or deciding the content and structure of documentation or agent instructions.","https:\u002F\u002Fgithub.com\u002Fscruffydan\u002FAI-Agents\u002Fblob\u002Fmain\u002Fsource\u002Fskills\u002Funslop\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fscruffydan\u002FAI-Agents\u002Fblob\u002Fmain\u002Fsource\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":80,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":20},"01M7B68C77N5M2N5BHK8137V43","technical-writing","Write or revise technical documentation, tutorials, how-to guides, reference material, and explanations so readers can understand and complete their task.","https:\u002F\u002Fgithub.com\u002Fscruffydan\u002FAI-Agents\u002Fblob\u002Fmain\u002Fsource\u002Fskills\u002Ftechnical-writing\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fscruffydan\u002FAI-Agents\u002Fblob\u002Fmain\u002Fsource\u002Fskills\u002Ftechnical-writing\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":20},"01M7B689G60Y3H3S8FSR1MM5PJ","teach","Explain what a concept means or how code works today, from the current code and docs. Use for how-it-works questions, including why code behaves as it does, not why a design was chosen or introduced (use why) or diagnosing failures.","https:\u002F\u002Fgithub.com\u002Fscruffydan\u002FAI-Agents\u002Fblob\u002Fmain\u002Fsource\u002Fskills\u002Fteach\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fscruffydan\u002FAI-Agents\u002Fblob\u002Fmain\u002Fsource\u002Fskills\u002Fteach\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":20},"01M7B6874405JZ16FFRCCH2VWC","takeover","Finish someone else's pull request, branch, or agent thread while preserving the original contributors' credit. Use when the user asks to take over existing work or requests a takeover.","https:\u002F\u002Fgithub.com\u002Fscruffydan\u002FAI-Agents\u002Fblob\u002Fmain\u002Fsource\u002Fskills\u002Ftakeover\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fscruffydan\u002FAI-Agents\u002Fblob\u002Fmain\u002Fsource\u002Fskills\u002Ftakeover\u002FSKILL.md",[],[]]