[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C4T8H28QSPBCMWY0PKEB9N":3,"skill-same:01M6C4T8H28QSPBCMWY0PKEB9N":77},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":6,"ownerHtmlUrl":60,"ownerBlogUrl":61,"ownerDescription":62,"updatedAt":63,"install":64,"resources":76},"01M6C4T8H28QSPBCMWY0PKEB9N","cursor-review",null,"Run a Cursor Composer review as an advisory second opinion while keeping the primary review verdict on the host brain. Use when user invokes cursor:review, asks Cursor to review, or wants composer to sanity-check a diff. Cursor never owns APPROVE\u002FREQUEST_CHANGES.","Chachamaru127\u002Fclaude-code-harness","Chachamaru127","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F96473544?v=4","01M6C4N084DDDEK9SJPGFG9H9M","Chachamaru","01M6C4N0CCNFST9P8C7EJNVH42",3209,"MIT","https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fskills\u002Fcursor-review\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"review","cursor","cursor review","when","second","approve","changes","true","composer","sanity","verdict","scope","host","as","advisory","never","diff","use","user","read","check","grep","Bash","run","second opinion","2026-11-10 10:12:30",false,"---\nname: cursor-review\ndescription: \"Run a Cursor Composer review as an advisory second opinion while keeping the primary review verdict on the host brain. Use when user invokes cursor:review, asks Cursor to review, or wants composer to sanity-check a diff. Cursor never owns APPROVE\u002FREQUEST_CHANGES.\"\ndescription-en: \"Run a Cursor Composer review as an advisory second opinion while keeping the primary review verdict on the host brain. Use when user invokes cursor:review, asks Cursor to review, or wants composer to sanity-check a diff. Cursor never owns APPROVE\u002FREQUEST_CHANGES.\"\ndescription-ja: \"Cursor Composer に advisory second opinion としてレビューさせるスキル。cursor:review、Cursor にレビューして、composer で差分を sanity check して、という時に使う。primary verdict は常に host brain が持ち、Cursor は APPROVE\u002FREQUEST_CHANGES を所有しない。\"\nallowed-tools: [\"Read\", \"Bash\", \"Grep\"]\nargument-hint: \"[--base \u003Cref>] [review-scope]\"\nuser-invocable: true\n---\n\n# cursor:review - Advisory Cursor Review\n\nCursor Composer (`composer-2.5-fast`) を read-only second opinion として使う review skill。primary verdict は host brain (Opus \u002F Claude role) が出す。\n\n## Quick Reference\n\n```bash\ncursor:review --base origin\u002Fmain\ncursor:review \"Phase 88.5 command namespace diff\"\n```\n\n## Rules\n\n- Cursor review is advisory. The final verdict must come from the host reviewer.\n- Do not pass `--write` to `cursor-companion.sh`.\n- Use resolver\u002Fmodel routing, not direct env checks:\n\n  ```bash\n  bash scripts\u002Fresolve-impl-backend.sh --backend cursor --role reviewer\n  bash scripts\u002Fmodel-routing.sh --host cursor --role worker --field model\n  ```\n\n- Prefer the existing `harness-review` contract when a full review is requested. This command exists for users who explicitly ask for the Cursor lane.\n\n## Flow\n\n1. Resolve the Harness helper root:\n\n   ```bash\n   HARNESS_PLUGIN_ROOT=\"${HARNESS_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-}}\"\n   if [ -z \"$HARNESS_PLUGIN_ROOT\" ] && [ -n \"${CLAUDE_SKILL_DIR:-}\" ]; then\n     probe=\"$(cd \"${CLAUDE_SKILL_DIR}\" && pwd)\"\n     while [ \"$probe\" != \"\u002F\" ] && [ ! -d \"$probe\u002Fscripts\" ]; do\n       probe=\"$(cd \"$probe\u002F..\" && pwd)\"\n     done\n     [ -d \"$probe\u002Fscripts\" ] && HARNESS_PLUGIN_ROOT=\"$probe\"\n   fi\n   if [ -z \"$HARNESS_PLUGIN_ROOT\" ]; then\n     echo \"ERROR: HARNESS_PLUGIN_ROOT is not set and could not be derived from CLAUDE_PLUGIN_ROOT or CLAUDE_SKILL_DIR\" >&2\n     exit 2\n   fi\n   ```\n\n2. Determine review scope:\n\n   ```bash\n   BASE_REF=\"${TASK_BASE_REF:-origin\u002Fmain}\"\n   REVIEW_SCOPE=\"${ARGUMENTS:-}\"\n   if [ -n \"${REVIEW_SCOPE}\" ]; then\n     set -- ${REVIEW_SCOPE}\n     while [ \"$#\" -gt 0 ]; do\n       case \"$1\" in\n         --base)\n           BASE_REF=\"${2:?--base requires a ref}\"\n           shift 2\n           ;;\n         --base=*)\n           BASE_REF=\"${1#--base=}\"\n           shift\n           ;;\n         *)\n           shift\n           ;;\n       esac\n     done\n   fi\n   DIFF_STAT=\"$(git diff --stat \"${BASE_REF}..HEAD\")\"\n   DIFF_TEXT=\"$(git diff \"${BASE_REF}..HEAD\")\"\n   ```\n\n3. Ask Cursor in read-only mode:\n\n   ```bash\n   PROMPT=\"$(cat \u003C\u003CEOF\nReview this diff as an advisory second opinion.\nBase ref: ${BASE_REF}\nRequested scope: ${ARGUMENTS:-full diff}\nRequirement, purpose and DoD: \u003Coriginal request and completion criteria>\nSpec and validation evidence: \u003Crelevant paths and observed results>\n\nFocus on bugs, regressions, missing tests, and unsafe assumptions. Do not propose broad refactors.\nUse the supplied requirement, DoD, spec and validation evidence to assess the requested scope; inspect missing context read-only.\nFor each finding, state its location, trigger, impact and checkable evidence. Separate hypotheses from observed defects; do not invent findings to fill a quota.\nReturn an assessment only. Do not implement changes or treat the implementation worker's self-report as verification.\n\nDiff stat:\n${DIFF_STAT}\n\nDiff:\n${DIFF_TEXT}\nEOF\n)\"\n   bash \"${HARNESS_PLUGIN_ROOT}\u002Fscripts\u002Fcursor-companion.sh\" task \"${PROMPT}\"\n   ```\n\n4. Host reads Cursor's output and performs the primary review:\n\n   - Findings first, ordered by severity.\n   - Mark Cursor-originated points as advisory when used.\n   - `APPROVE` \u002F `REQUEST_CHANGES` must be the host decision, not a copied Cursor verdict.\n\n## Output\n\nUse the standard review shape:\n\n- findings\n- open questions\n- validation run\n- final host verdict\n","# cursor:review - Advisory Cursor Review\n\nCursor Composer (`composer-2.5-fast`) を read-only second opinion として使う review skill。primary verdict は host brain (Opus \u002F Claude role) が出す。\n\n## Quick Reference\n\n```bash\ncursor:review --base origin\u002Fmain\ncursor:review \"Phase 88.5 command namespace diff\"\n```\n\n## Rules\n\n- Cursor review is advisory. The final verdict must come from the host reviewer.\n- Do not pass `--write` to `cursor-companion.sh`.\n- Use resolver\u002Fmodel routing, not direct env checks:\n\n  ```bash\n  bash scripts\u002Fresolve-impl-backend.sh --backend cursor --role reviewer\n  bash scripts\u002Fmodel-routing.sh --host cursor --role worker --field model\n  ```\n\n- Prefer the existing `harness-review` contract when a full review is requested. This command exists for users who explicitly ask for the Cursor lane.\n\n## Flow\n\n1. Resolve the Harness helper root:\n\n   ```bash\n   HARNESS_PLUGIN_ROOT=\"${HARNESS_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-}}\"\n   if [ -z \"$HARNESS_PLUGIN_ROOT\" ] && [ -n \"${CLAUDE_SKILL_DIR:-}\" ]; then\n     probe=\"$(cd \"${CLAUDE_SKILL_DIR}\" && pwd)\"\n     while [ \"$probe\" != \"\u002F\" ] && [ ! -d \"$probe\u002Fscripts\" ]; do\n       probe=\"$(cd \"$probe\u002F..\" && pwd)\"\n     done\n     [ -d \"$probe\u002Fscripts\" ] && HARNESS_PLUGIN_ROOT=\"$probe\"\n   fi\n   if [ -z \"$HARNESS_PLUGIN_ROOT\" ]; then\n     echo \"ERROR: HARNESS_PLUGIN_ROOT is not set and could not be derived from CLAUDE_PLUGIN_ROOT or CLAUDE_SKILL_DIR\" >&2\n     exit 2\n   fi\n   ```\n\n2. Determine review scope:\n\n   ```bash\n   BASE_REF=\"${TASK_BASE_REF:-origin\u002Fmain}\"\n   REVIEW_SCOPE=\"${ARGUMENTS:-}\"\n   if [ -n \"${REVIEW_SCOPE}\" ]; then\n     set -- ${REVIEW_SCOPE}\n     while [ \"$#\" -gt 0 ]; do\n       case \"$1\" in\n         --base)\n           BASE_REF=\"${2:?--base requires a ref}\"\n           shift 2\n           ;;\n         --base=*)\n           BASE_REF=\"${1#--base=}\"\n           shift\n           ;;\n         *)\n           shift\n           ;;\n       esac\n     done\n   fi\n   DIFF_STAT=\"$(git diff --stat \"${BASE_REF}..HEAD\")\"\n   DIFF_TEXT=\"$(git diff \"${BASE_REF}..HEAD\")\"\n   ```\n\n3. Ask Cursor in read-only mode:\n\n   ```bash\n   PROMPT=\"$(cat \u003C\u003CEOF\nReview this diff as an advisory second opinion.\nBase ref: ${BASE_REF}\nRequested scope: ${ARGUMENTS:-full diff}\nRequirement, purpose and DoD: \u003Coriginal request and completion criteria>\nSpec and validation evidence: \u003Crelevant paths and observed results>\n\nFocus on bugs, regressions, missing tests, and unsafe assumptions. Do not propose broad refactors.\nUse the supplied requirement, DoD, spec and validation evidence to assess the requested scope; inspect missing context read-only.\nFor each finding, state its location, trigger, impact and checkable evidence. Separate hypotheses from observed defects; do not invent findings to fill a quota.\nReturn an assessment only. Do not implement changes or treat the implementation worker's self-report as verification.\n\nDiff stat:\n${DIFF_STAT}\n\nDiff:\n${DIFF_TEXT}\nEOF\n)\"\n   bash \"${HARNESS_PLUGIN_ROOT}\u002Fscripts\u002Fcursor-companion.sh\" task \"${PROMPT}\"\n   ```\n\n4. Host reads Cursor's output and performs the primary review:\n\n   - Findings first, ordered by severity.\n   - Mark Cursor-originated points as advisory when used.\n   - `APPROVE` \u002F `REQUEST_CHANGES` must be the host decision, not a copied Cursor verdict.\n\n## Output\n\nUse the standard review shape:\n\n- findings\n- open questions\n- validation run\n- final host verdict\n",{"name":5,"description":7,"allowed-tools":49,"argument-hint":52,"description-en":7,"description-ja":53,"user-invocable":54},[50,41,51],"Read","Grep","[--base \u003Cref>] [review-scope]","Cursor Composer に advisory second opinion としてレビューさせるスキル。cursor:review、Cursor にレビューして、composer で差分を sanity check して、という時に使う。primary verdict は常に host brain が持ち、Cursor は APPROVE\u002FREQUEST_CHANGES を所有しない。",true,"main","c2304c325d4432f51d632e0586d886767b0f41ea","skills\u002Fcursor-review",306,"https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness","https:\u002F\u002Fgithub.com\u002FChachamaru127","https:\u002F\u002Fcanai.jp\u002F","Going all-in on the AI business from April 2025\r\nOSS release: 3k Stars\r\nAI adoption starting with \"I want\"\r\nAX Support | Tokenomics | AISDR |","2026-11-11 17:18:34",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":54},[66,69,72],{"tool":67,"command":68},"npx","npx skills add Chachamaru127\u002Fclaude-code-harness --skill cursor-review",{"tool":70,"command":71},"bunx","bunx skills add Chachamaru127\u002Fclaude-code-harness --skill cursor-review",{"tool":73,"command":74},"pnpm","pnpm dlx skills add Chachamaru127\u002Fclaude-code-harness --skill cursor-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fskills\u002Fcursor-review\u002FSKILL.md",[],[78,95,103,119,148,172],{"skillNo":79,"name":80,"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":81,"categories":82,"keywords":88,"publishedAt":44},"01M6C4VZCJB9EN3KZXGNARAF6P","escape-skill","https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fzz-review-escape\u002FSKILL.md",[83],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[89,90,91,92,26,93,94],"escape skill","escape","Tools","false","path","quoted",{"skillNo":96,"name":97,"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":98,"categories":99,"keywords":100,"publishedAt":44},"01M6C4VYAJW332S5R2MM3RNE0G","zz-review-empty","https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fzz-review-empty\u002FSKILL.md",[],[19,101,102,92,26],"zz review empty","empty",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":110,"publishedAt":44},"01M6C4VWW4GNAZ2680GY04S3EW","session-send","This skill should be used when the user asks to notify other session, requests a session handoff, says tell other agent, or needs a cross-session message.","https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fskills\u002Fsession-send\u002FSKILL.md",[109],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},[111,112,113,114,115,41,37,116,117,118,22],"session","session send","send","handoff","session handoff","message","notify","requests",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":126,"publishedAt":44},"01M6C4VSMYH6XQGR087HQ9Y7HT","memory","Manage SSOT, memory, and cross-tool memory search. Guardian of decisions.md and patterns.md. Use when user mentions memory, SSOT, decisions.md, patterns.md, merging, migration, SSOT promotion, sync memory, save learnings, memory search, harness-mem, past decisions, or record this. Do NOT load for: implementation work, reviews, ad-hoc notes, or in-session logging.","https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fskills\u002Fmemory\u002FSKILL.md",[125],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},[121,127,128,129,130,131,132,133,41,134,135,136,137,38,138,139,37,111,36,140,141,142,143,144,145,26,146,147,22],"MCP","sync","notes","harness","search","memory search","guardian","migrate","tool","work","decisions","write","edit","migration","manage","do","learnings","promotion","reviews","load","for",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":44},"01M6C4VQ3507BV9XRX4BDSES6J","maintenance","File cleanup and archiving. Tidies up bloated Plans.md, session-log.md, old logs, and state files. Trigger: \u002Fmaintenance, cleanup, archive, organize, split session-log. Do NOT load for: implementation, review, release, new feature development.","https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fskills\u002Fmaintenance\u002FSKILL.md",[],[150,19,155,156,42,157,158,159,160,41,161,40,38,138,139,162,111,163,164,165,142,166,167,168,169,170,26,146,147,171],"development","cleanup","release","state","file","logs","archive","new feature","up","log","files","feature","plans","trigger","整理","split","new",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":190,"publishedAt":44},"01M6C4VK473YJ872RNMBYK7P4R","japanese-writing-drafter","Detect when the operator corrects the agent's Japanese phrasing mid-conversation (rewrites a sentence, calls out a style problem, says 'this wording is bad, say it like X instead') and draft a pending writing-rule proposal into ~\u002F.claude\u002Fwriting-lint\u002Fproposals.jsonl for later human review. This skill is the ONLY writer of proposals.jsonl — it never edits rules.jsonl and never sets status to anything but pending. Promotion to rules.jsonl only happens via the human-run scripts\u002Fwriting-rule-approve.sh. Use when user mentions writing-rule proposal, 表現を直して, 文体を直して, その言い方はNG, writing lint 提案, 指摘をルール化して. Do NOT load for: approving or rejecting proposals (use scripts\u002Fwriting-rule-approve.sh), listing pending proposals (use scripts\u002Fwriting-rule-list.sh), or scanning text against the existing dictionary (the writinglint engine \u002F PostToolUse hook does that).","https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fskills\u002Fjapanese-writing-drafter\u002FSKILL.md",[178,181,184,185],{"categoryNo":179,"categoryName":180,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":182,"categoryName":183,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},{"categoryNo":186,"categoryName":187,"taxonomyType":188,"taxonomyTypeDesc":189},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[191,192,193,19,194,42,195,196,41,197,198,199,200,38,201,202,36,34,203,204,205,206,207,208,209,210,211,212,213,214,22,215],"writing","japanese writing drafter","japanese","status","lint","operator","提案","text","engine","Rules","list","proposals","only","scanning","say","human review","later","conversation","writer","human","scripts","problem","proposal","jsonl","listing"]