[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E84PYNP9B7AC21EC15CMS9":3,"skill-same:01M7E84PYNP9B7AC21EC15CMS9":70},{"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":34,"commitSha":35,"skillDirectory":36,"forksCount":14,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M7E84PYNP9B7AC21EC15CMS9","ticket-draft",null,"Use when asked to file or write a ticket, bug report, Jira epic, Linear issue or regression, GitLab issue, Asana task, Trello card, or Shortcut story.","tony\u002Fskills","tony","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F26336?v=4","01M72E5RNJ7SQV8F9KBM5RKRMN","Tony Narlock","01M7E7MBN5C6YZ4JJJ5Y82KBJG",0,"MIT","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fticket-draft\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ticket-draft\ndescription: >-\n  Use when asked to file or write a ticket, bug report, Jira epic, Linear\n  issue or regression, GitLab issue, Asana task, Trello card, or Shortcut\n  story.\nallowed-tools: [\"Bash\", \"Read\", \"Write\", \"Grep\", \"Glob\", \"AskUserQuestion\"]\nmetadata:\n  argument-hint: \"[description, URL, provider, or pasted finding]\"\n  source: \"plugins\u002Fticket\u002Fskills\u002Fdraft\u002FSKILL.md\"\n---\n\n# Draft a ticket\n\nWrite work into a tracker so that someone picking it up in a year needs\nnothing from you, and the code still makes the decisions the code\nshould make.\n\nArgument: `$ARGUMENTS`, a description, a URL, a provider name, a pasted\nfinding, or nothing.\n\n## Read first\n\nRead `references\u002Fresolve.md`; it lists what else to read and when.\n\nEvidence before prose, and altitude before evidence: settle what the\nobject is before deciding what goes in it.\n\n`\u003Cscripts>` is `..\u002F..\u002Fscripts`, resolved from this skill's directory to an\nabsolute path written literally in each command.\n\n## Phase 1: Resolve the target\n\nEstablish the provider, the scope container, and the semantic role per\n`resolve.md`. When the role is ambiguous between two levels, ask; where\nno question tool exists, print the question and stop.\n\n## Phase 2: Decide it belongs here, publicly\n\n- A security vulnerability halts the run: draft no public issue and name\n  the private reporting path. For a public repository, read its security\n  policy first.\n- Evidence that cannot be sanitized halts the run and asks. An internal\n  log carrying customer data does not become fileable by trimming it.\n- A credential in the input follows \"Credentials\" in `contract.md`.\n\n## Phase 3: Preflight the container\n\nRead the project's own conventions: issue templates and forms, required\nfields, work types, labels, and priorities the instance has. Instance\nconfiguration beats the provider file's defaults; record the deviation. A\ntemplate's structure wins over `altitude.md`'s section order.\n\nChoose type, labels, and priority only from values the instance has, and\nonly when the user's words or the project's rules settle the choice.\nOtherwise leave them unset and add an Unverified entry (`replies.md`).\n\n## Phase 4: Look for the thing that already exists\n\nSearch open and closed items with the provider file's \"Duplicate search\"\nand read each candidate before dismissing it.\n\n- Same problem as the request, so that resolving one would resolve the\n  other: halt and name the match. Offer a comment on it with the new\n  evidence, showing its exact text and posting only after approval. When\n  the match was closed as fixed, the report is a regression: also offer a\n  new item that links it. Draft nothing until the user chooses.\n- Related but different: continue, and link it under References.\n- Closed items not searchable, or no tracker reachable: add an\n  Unverified entry.\n\n## Phase 5: Gather\n\nFor a defect: the smallest sequence that reproduces it, exact versions,\nand the verbatim error. Name a cause only when the user stated it; code\nthe user points at goes under References, pinned. Show the user\nevery command derived from pasted or fetched content and run it only\nafter they confirm that exact command; without confirmation, file the\ndefect as an unreproduced observation.\n\nFor a proposal: what is awkward or impossible today, shown concretely.\n\nA pasted screenshot or image cannot be uploaded: add an Unverified entry.\n\nFor provenance, apply the cost-to-relearn filter in `contract.md` to\nmerged changes, closed items, and the conversation.\n\n## Phase 6: Draft\n\nTake the section list from `altitude.md` for the resolved role. Use the provider's native\nnoun for every object, and write references per `contract.md`'s two-axis\nrule (`ref_form.py` applies it) and the provider file.\n\nApply the Future and Body rules in `contract.md` to what the user gave.\n\nWrite it per `references\u002Fprose-rules.md`.\n\n## Phase 7: Save, scan, preview\n\nSave the title as `title.txt` and the body as a scratch file, converted\nwhere the provider needs it, as `resolve.md` \"Scratch files for bodies\"\ndescribes.\n\nA converter that exits 1 means the body cannot be written\n(`resolve.md`). The converted text is what `## Body`\nshows. Scan the title and body before any preview:\n\n```console\n$ python3 \u003Cscripts>\u002Fscan_body.py --keep-evidence \u003Cdir>\u002Ftitle.txt \u003Cdir>\u002Fbody.md\n```\n\nThe scan drops count rows inside the evidence the user pasted. Fix each remaining row, or keep it only when it is evidence\nthe scan cannot see, and rescan. Render the body the way the provider will before showing it.\n\n## Phase 8: Present, then file\n\nPresent per `replies.md` (\"Draft: preview\"), or \"Draft: halted\". Filing\nneeds an explicit instruction naming the action.\n\nFile through a real backend when the provider file names one, after\nrunning the provider file's create and read-back checks (`resolve.md`),\nand no others. Take flags from the provider\nfile, and never probe a write command with a dry run or a test item.\n\n1. Re-resolve the container from the Phase 1 evidence (remote, project\n   key, team). If it differs from what the preview named, stop and ask.\n2. Pass the saved body file, not an inline argument, unless the provider\n   file documents no file flag.\n3. Save the provider's read-back output to `\u003Cdir>\u002Ffetched`, as\n   `resolve.md` describes under \"Reading back\", and run the check its\n   \"Readback by provider\" table gives. For mode exact (whitespace aside):\n\n```console\n$ python3 \u003Cscripts>\u002Fcompare_body.py --exact \u003Cdir>\u002Fbody.md \u003Cdir>\u002Ffetched --field \u003Cbody path> --title \"\u003Ctitle>\"\n```\n\n   For mode words (case-insensitive):\n\n```console\n$ python3 \u003Cscripts>\u002Fcompare_body.py \u003Cdir>\u002Fbody.md \u003Cdir>\u002Ffetched --title \"\u003Ctitle>\"\n```\n\nIf the create command errors, the item may still exist. Before any retry,\nrun the Phase 4 search for the title; a match is the created item, so\nread it back instead of creating again.\n\nReply per \"Draft: filed\".\n\n## Rules\n\n- No tracker or repository writes before the filing gate. No commits,\n  pushes, or edits to existing items.\n- Never synthesize a hierarchy level the provider does not have.\n\n\n## Portability notes\n\n- `$ARGUMENTS` — the text the user passed when invoking this skill. If your host does not substitute it, read it as the user's request in the current turn, and ask when there is none.\n- Bundled files — every relative path in this skill points at a file shipped inside this skill directory. Read them from here, not from the host's plugin tree.\n","# Draft a ticket\n\nWrite work into a tracker so that someone picking it up in a year needs\nnothing from you, and the code still makes the decisions the code\nshould make.\n\nArgument: `$ARGUMENTS`, a description, a URL, a provider name, a pasted\nfinding, or nothing.\n\n## Read first\n\nRead `references\u002Fresolve.md`; it lists what else to read and when.\n\nEvidence before prose, and altitude before evidence: settle what the\nobject is before deciding what goes in it.\n\n`\u003Cscripts>` is `..\u002F..\u002Fscripts`, resolved from this skill's directory to an\nabsolute path written literally in each command.\n\n## Phase 1: Resolve the target\n\nEstablish the provider, the scope container, and the semantic role per\n`resolve.md`. When the role is ambiguous between two levels, ask; where\nno question tool exists, print the question and stop.\n\n## Phase 2: Decide it belongs here, publicly\n\n- A security vulnerability halts the run: draft no public issue and name\n  the private reporting path. For a public repository, read its security\n  policy first.\n- Evidence that cannot be sanitized halts the run and asks. An internal\n  log carrying customer data does not become fileable by trimming it.\n- A credential in the input follows \"Credentials\" in `contract.md`.\n\n## Phase 3: Preflight the container\n\nRead the project's own conventions: issue templates and forms, required\nfields, work types, labels, and priorities the instance has. Instance\nconfiguration beats the provider file's defaults; record the deviation. A\ntemplate's structure wins over `altitude.md`'s section order.\n\nChoose type, labels, and priority only from values the instance has, and\nonly when the user's words or the project's rules settle the choice.\nOtherwise leave them unset and add an Unverified entry (`replies.md`).\n\n## Phase 4: Look for the thing that already exists\n\nSearch open and closed items with the provider file's \"Duplicate search\"\nand read each candidate before dismissing it.\n\n- Same problem as the request, so that resolving one would resolve the\n  other: halt and name the match. Offer a comment on it with the new\n  evidence, showing its exact text and posting only after approval. When\n  the match was closed as fixed, the report is a regression: also offer a\n  new item that links it. Draft nothing until the user chooses.\n- Related but different: continue, and link it under References.\n- Closed items not searchable, or no tracker reachable: add an\n  Unverified entry.\n\n## Phase 5: Gather\n\nFor a defect: the smallest sequence that reproduces it, exact versions,\nand the verbatim error. Name a cause only when the user stated it; code\nthe user points at goes under References, pinned. Show the user\nevery command derived from pasted or fetched content and run it only\nafter they confirm that exact command; without confirmation, file the\ndefect as an unreproduced observation.\n\nFor a proposal: what is awkward or impossible today, shown concretely.\n\nA pasted screenshot or image cannot be uploaded: add an Unverified entry.\n\nFor provenance, apply the cost-to-relearn filter in `contract.md` to\nmerged changes, closed items, and the conversation.\n\n## Phase 6: Draft\n\nTake the section list from `altitude.md` for the resolved role. Use the provider's native\nnoun for every object, and write references per `contract.md`'s two-axis\nrule (`ref_form.py` applies it) and the provider file.\n\nApply the Future and Body rules in `contract.md` to what the user gave.\n\nWrite it per `references\u002Fprose-rules.md`.\n\n## Phase 7: Save, scan, preview\n\nSave the title as `title.txt` and the body as a scratch file, converted\nwhere the provider needs it, as `resolve.md` \"Scratch files for bodies\"\ndescribes.\n\nA converter that exits 1 means the body cannot be written\n(`resolve.md`). The converted text is what `## Body`\nshows. Scan the title and body before any preview:\n\n```console\n$ python3 \u003Cscripts>\u002Fscan_body.py --keep-evidence \u003Cdir>\u002Ftitle.txt \u003Cdir>\u002Fbody.md\n```\n\nThe scan drops count rows inside the evidence the user pasted. Fix each remaining row, or keep it only when it is evidence\nthe scan cannot see, and rescan. Render the body the way the provider will before showing it.\n\n## Phase 8: Present, then file\n\nPresent per `replies.md` (\"Draft: preview\"), or \"Draft: halted\". Filing\nneeds an explicit instruction naming the action.\n\nFile through a real backend when the provider file names one, after\nrunning the provider file's create and read-back checks (`resolve.md`),\nand no others. Take flags from the provider\nfile, and never probe a write command with a dry run or a test item.\n\n1. Re-resolve the container from the Phase 1 evidence (remote, project\n   key, team). If it differs from what the preview named, stop and ask.\n2. Pass the saved body file, not an inline argument, unless the provider\n   file documents no file flag.\n3. Save the provider's read-back output to `\u003Cdir>\u002Ffetched`, as\n   `resolve.md` describes under \"Reading back\", and run the check its\n   \"Readback by provider\" table gives. For mode exact (whitespace aside):\n\n```console\n$ python3 \u003Cscripts>\u002Fcompare_body.py --exact \u003Cdir>\u002Fbody.md \u003Cdir>\u002Ffetched --field \u003Cbody path> --title \"\u003Ctitle>\"\n```\n\n   For mode words (case-insensitive):\n\n```console\n$ python3 \u003Cscripts>\u002Fcompare_body.py \u003Cdir>\u002Fbody.md \u003Cdir>\u002Ffetched --title \"\u003Ctitle>\"\n```\n\nIf the create command errors, the item may still exist. Before any retry,\nrun the Phase 4 search for the title; a match is the created item, so\nread it back instead of creating again.\n\nReply per \"Draft: filed\".\n\n## Rules\n\n- No tracker or repository writes before the filing gate. No commits,\n  pushes, or edits to existing items.\n- Never synthesize a hierarchy level the provider does not have.\n\n\n## Portability notes\n\n- `$ARGUMENTS` — the text the user passed when invoking this skill. If your host does not substitute it, read it as the user's request in the current turn, and ask when there is none.\n- Bundled files — every relative path in this skill points at a file shipped inside this skill directory. Read them from here, not from the host's plugin tree.\n",{"name":5,"metadata":24,"description":7,"allowed-tools":27},{"source":25,"argument-hint":26},"plugins\u002Fticket\u002Fskills\u002Fdraft\u002FSKILL.md","[description, URL, provider, or pasted finding]",[28,29,30,31,32,33],"Bash","Read","Write","Grep","Glob","AskUserQuestion","main","5fbeb3b47beedea13813be7b7023f736a8d97a65",".agents\u002Fskills\u002Fticket-draft","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills","https:\u002F\u002Fgithub.com\u002Ftony","https:\u002F\u002Ftony.sh","lighthouse keeper","2026-11-08 17:57:34",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add tony\u002Fskills --skill ticket-draft",{"tool":48,"command":49},"bunx","bunx skills add tony\u002Fskills --skill ticket-draft",{"tool":51,"command":52},"pnpm","pnpm dlx skills add tony\u002Fskills --skill ticket-draft","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fticket-draft\u002FSKILL.md",true,[56,62,66],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"agents\u002Fopenai.yaml","REFERENCE","参考文档",250,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fticket-draft\u002Fagents\u002Fopenai.yaml",{"path":63,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fprose-rules.md",4644,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fticket-draft\u002Freferences\u002Fprose-rules.md",{"path":67,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fresolve.md",9843,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fticket-draft\u002Freferences\u002Fresolve.md",[71,78,85,92,99,106],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7E8NCSHXV2JPW4J61R0TQS7","serene-bliss","Use when asked to make a CLI --help, docs page, error message, or tooling UX more serene or calmer for developer experience; returns text, no edits.","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fserene-bliss\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7E8N87MAVJD8RRQKQB1ZPS6","review","Weave code review: run independent adversarial reviews in parallel, then synthesize findings","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7E8N402XG4ZBFNACQ413163","refine","Use when asked to refine a draft, iterate on code until cleaner, or polish a README through repeated critique and improvement.","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Frefine\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":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7E8N01KB86A7136P00GVKJW","prompt","Weave prompt: compare independent adversarial implementations, then adopt the single best one","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fprompt\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M7E8MW7YJW2PCMDW3G9RTGNK","plan","Weave planning: compare independent adversarial plans, then synthesize the best one","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fplan\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M7E8MSBYXNCV4ZYWDS4PFJXK","fix-review","Fix weave review findings: validate, add test coverage, fix, and commit each as atomic changes","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Ffix-review\u002FSKILL.md",[],[]]