[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M780PCBCRV16F3A34467BKG1":3,"skill-same:01M780PCBCRV16F3A34467BKG1":48},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M780PCBCRV16F3A34467BKG1","sweep",null,"Shard a repo-wide mechanical edit into per-package writer subagents, costing O(shards) not O(matches). Use for a rote change across many files, such as renaming an import or swapping an API call.","DTCurrie\u002Fhouserules","DTCurrie","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1930371?v=4","01M780ND83PAY17A9HX96HHWG4","Devin T. Currie","01M780ND8W21FE1NSPAG03M0HM",2,"MIT","https:\u002F\u002Fgithub.com\u002FDTCurrie\u002Fhouserules\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fpayload\u002Fskills\u002Fsweep\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sweep\ndescription: Shard a repo-wide mechanical edit into per-package writer subagents, costing O(shards) not O(matches). Use for a rote change across many files, such as renaming an import or swapping an API call.\nargument-hint: \u003Cthe mechanical change to make across the repo>\nallowed-tools: Bash, Grep, Glob, Read, Agent, AskUserQuestion\n---\n\nApply a mechanical, repo-wide change **off-context**: **$ARGUMENTS**\n\nThe whole point is cost. A naive sweep reads every match and every diff into this context, which is\nO(matches). Instead: locate once, shard by package, and fan out one **cheap writer per shard**. The\norchestrator sees only a one-line count per package, which is O(shards). You never load the match set.\n\n## 0. Is this actually a sweep?\n\nUse this only for a **rote, rule-based** edit with a crisp definition of done, such as a find\u002Freplace,\nan import rename, or a codemod-shaped change. If each site needs real judgment, it's not a sweep. Do\nit inline or plan it. If it touches a handful of files in one package, just do it, because the fan-out\noverhead isn't worth it.\n\n## 1. Locate once (count, don't read)\n\nFind the scope with a single counting pass. **Do not** read the matches into context.\n\n```\ngrep -rlZ '\u003Cpattern>' -- \u003Cpaths> | xargs -0 -n1 dirname | sort | uniq -c\n```\n\nAlso count the matched lines, which step 3 reports if it has to ask. This prints one number and loads\nno match:\n\n```\ngrep -rE '\u003Cpattern>' -- \u003Cpaths> | wc -l\n```\n\nYou want the **set of files and packages** that match and _how many_, not their contents. If the\npattern needs refining, refine it here, cheaply, before fanning out.\n\n## 2. Shard by package\n\nGroup the matching files by package, using `.claude\u002Fhouserules.config.json` `targets[].pathPrefix` or the\ntop-level dir. Each package is one shard. Sharding by package rather than by file keeps writers from\ncolliding and makes verification package-scoped.\n\n## 3. Fan out one writer per shard, in ONE message\n\nIf there are more than 8 shards, call `AskUserQuestion` before any `Agent` call, and dispatch nothing\nuntil the user answers. The question states three numbers: the shard count, the matched line count\nfrom step 1, and an estimate of the cost. The estimate is one agent per shard, about 55k tokens per\nwriter (shards × 55k in total), and about 3 minutes, because the writers run in parallel. Offer three\noptions:\n\n- **Run all shards.**\n- **Run a named slice.** The user names the packages to include, and you dispatch only those.\n- **Cancel.** Dispatch nothing and stop.\n\nWith 8 or fewer shards, skip the question and dispatch.\n\nDispatch all shards in a single message as parallel `Agent` calls. Each writer is **cheap and\npinned**: request `model: haiku` (or `effort: low`). A mechanical edit doesn't need a strong model,\nand a fleet of strong ones is the cost trap this skill exists to avoid.\n\nGive each writer:\n\n- the **exact transformation rule**, unambiguous and the same for every shard, and\n- its shard only, meaning the file list or the package path, and\n- this instruction: **report only a one-line result**, `\u003Cpackage>: edited N file(s)`, or `0, no\nmatches`, or `blocked: \u003Creason>`. It must **not** paste diffs, file contents, or per-file logs.\n\n> **Writer brief (per shard):** In `\u003Cpackage>`, apply exactly this change: `\u003Crule>`. Only touch files\n> matching `\u003Cpattern>`. Do not reformat, do not fix unrelated issues, do not explain. Reply with one\n> line: `\u003Cpackage>: edited N file(s)`.\n\n## 4. Collect counts + verify\n\nTally the one-liners into a single table of package → count. Then verify the touched packages. If\n`\u002Fverify-changed` is installed, run it, because it scopes to exactly what changed plus dependents.\nOtherwise run the repo's verify on the affected packages. Report the total as `edited N files across M\npackages` along with the verify verdict. If a writer reported `blocked`, surface just that shard for a\ncloser look.\n\n## Notes\n\n- The orchestrator transcript should contain **M count-lines and a verdict**, never the match set or a\n  single diff. If you find yourself reading matches here, stop and push it into a writer.\n- Same rule for every shard. If shards need _different_ rules, they're different sweeps. Run them\n  separately.\n","Apply a mechanical, repo-wide change **off-context**: **$ARGUMENTS**\n\nThe whole point is cost. A naive sweep reads every match and every diff into this context, which is\nO(matches). Instead: locate once, shard by package, and fan out one **cheap writer per shard**. The\norchestrator sees only a one-line count per package, which is O(shards). You never load the match set.\n\n## 0. Is this actually a sweep?\n\nUse this only for a **rote, rule-based** edit with a crisp definition of done, such as a find\u002Freplace,\nan import rename, or a codemod-shaped change. If each site needs real judgment, it's not a sweep. Do\nit inline or plan it. If it touches a handful of files in one package, just do it, because the fan-out\noverhead isn't worth it.\n\n## 1. Locate once (count, don't read)\n\nFind the scope with a single counting pass. **Do not** read the matches into context.\n\n```\ngrep -rlZ '\u003Cpattern>' -- \u003Cpaths> | xargs -0 -n1 dirname | sort | uniq -c\n```\n\nAlso count the matched lines, which step 3 reports if it has to ask. This prints one number and loads\nno match:\n\n```\ngrep -rE '\u003Cpattern>' -- \u003Cpaths> | wc -l\n```\n\nYou want the **set of files and packages** that match and _how many_, not their contents. If the\npattern needs refining, refine it here, cheaply, before fanning out.\n\n## 2. Shard by package\n\nGroup the matching files by package, using `.claude\u002Fhouserules.config.json` `targets[].pathPrefix` or the\ntop-level dir. Each package is one shard. Sharding by package rather than by file keeps writers from\ncolliding and makes verification package-scoped.\n\n## 3. Fan out one writer per shard, in ONE message\n\nIf there are more than 8 shards, call `AskUserQuestion` before any `Agent` call, and dispatch nothing\nuntil the user answers. The question states three numbers: the shard count, the matched line count\nfrom step 1, and an estimate of the cost. The estimate is one agent per shard, about 55k tokens per\nwriter (shards × 55k in total), and about 3 minutes, because the writers run in parallel. Offer three\noptions:\n\n- **Run all shards.**\n- **Run a named slice.** The user names the packages to include, and you dispatch only those.\n- **Cancel.** Dispatch nothing and stop.\n\nWith 8 or fewer shards, skip the question and dispatch.\n\nDispatch all shards in a single message as parallel `Agent` calls. Each writer is **cheap and\npinned**: request `model: haiku` (or `effort: low`). A mechanical edit doesn't need a strong model,\nand a fleet of strong ones is the cost trap this skill exists to avoid.\n\nGive each writer:\n\n- the **exact transformation rule**, unambiguous and the same for every shard, and\n- its shard only, meaning the file list or the package path, and\n- this instruction: **report only a one-line result**, `\u003Cpackage>: edited N file(s)`, or `0, no\nmatches`, or `blocked: \u003Creason>`. It must **not** paste diffs, file contents, or per-file logs.\n\n> **Writer brief (per shard):** In `\u003Cpackage>`, apply exactly this change: `\u003Crule>`. Only touch files\n> matching `\u003Cpattern>`. Do not reformat, do not fix unrelated issues, do not explain. Reply with one\n> line: `\u003Cpackage>: edited N file(s)`.\n\n## 4. Collect counts + verify\n\nTally the one-liners into a single table of package → count. Then verify the touched packages. If\n`\u002Fverify-changed` is installed, run it, because it scopes to exactly what changed plus dependents.\nOtherwise run the repo's verify on the affected packages. Report the total as `edited N files across M\npackages` along with the verify verdict. If a writer reported `blocked`, surface just that shard for a\ncloser look.\n\n## Notes\n\n- The orchestrator transcript should contain **M count-lines and a verdict**, never the match set or a\n  single diff. If you find yourself reading matches here, stop and push it into a writer.\n- Same rule for every shard. If shards need _different_ rules, they're different sweeps. Run them\n  separately.\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25},"Bash, Grep, Glob, Read, Agent, AskUserQuestion","\u003Cthe mechanical change to make across the repo>","main","039f153ef841e9e6f26430b3e17ea428d8a3ce06","packages\u002Fcli\u002Fpayload\u002Fskills\u002Fsweep",0,"https:\u002F\u002Fgithub.com\u002FDTCurrie\u002Fhouserules","https:\u002F\u002Fgithub.com\u002FDTCurrie","Engineering Lead at @viamrobotics, specializing in 2D and 3D visualizations.","2026-11-13 21:14:33",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add DTCurrie\u002Fhouserules --skill sweep",{"tool":40,"command":41},"bunx","bunx skills add DTCurrie\u002Fhouserules --skill sweep",{"tool":43,"command":44},"pnpm","pnpm dlx skills add DTCurrie\u002Fhouserules --skill sweep","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FDTCurrie\u002Fhouserules\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fpayload\u002Fskills\u002Fsweep\u002FSKILL.md",true,[],[49,56,63,70,76,83],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M780QVJX363SHD100WRD4TD0","pr-description","Write the pull request description for a change as a pasteable markdown body. Use before opening or updating a PR, or when asked for a PR body, PR summary, or gh pr create text.","https:\u002F\u002Fgithub.com\u002FDTCurrie\u002Fhouserules\u002Fblob\u002Fmain\u002Fpackages\u002Fplugin-prose\u002Fpayload\u002Fskills\u002Fpr-description\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M780QR0V9D4AJHTPN1NJHQRG","ledger-sync","Push the backlog and decision ledgers to GitHub Projects (issues and project board items). Use when the user asks to sync, push, or upload to GitHub Projects or the project board.","https:\u002F\u002Fgithub.com\u002FDTCurrie\u002Fhouserules\u002Fblob\u002Fmain\u002Fpackages\u002Fplugin-github\u002Fpayload\u002Fskills\u002Fledger-sync\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M780QKAY9PW98XRYGQFNDEMP","backlog-adopt","Adopt a reported GitHub issue into the backlog ledger and the linked project board. Use to triage or track a GitHub issue or bug report as a backlog entry.","https:\u002F\u002Fgithub.com\u002FDTCurrie\u002Fhouserules\u002Fblob\u002Fmain\u002Fpackages\u002Fplugin-github\u002Fpayload\u002Fskills\u002Fbacklog-adopt\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M780QJ4B917TCZM76X55NKQE","design-review","https:\u002F\u002Fgithub.com\u002FDTCurrie\u002Fhouserules\u002Fblob\u002Fmain\u002Fpackages\u002Fplugin-design\u002Fpayload\u002Fskills\u002Fdesign-review\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":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M780QEV3HGXEWMWG5VJEFF0J","chrome-devtools-mode","Switch the Chrome DevTools MCP server between its full 29-tool surface and the slim 3-tool one (--slim). Use when asked to change, shrink, or restore the chrome-devtools MCP tool surface.","https:\u002F\u002Fgithub.com\u002FDTCurrie\u002Fhouserules\u002Fblob\u002Fmain\u002Fpackages\u002Fplugin-design\u002Fpayload\u002Fskills\u002Fchrome-devtools-mode\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M780Q9MX9ADN41RZKQ47B8CT","decide","Record a decision to the decision ledger, with the rejected alternative and revisit trigger. Use when a discussion settles a design question or a new decision supersedes a prior one.","https:\u002F\u002Fgithub.com\u002FDTCurrie\u002Fhouserules\u002Fblob\u002Fmain\u002Fpackages\u002Fplugin-decisions\u002Fpayload\u002Fskills\u002Fdecide\u002FSKILL.md",[],[]]