[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AGQGVGAGE3RTSF6D0S5C8Y":3,"skill-same:01M7AGQGVGAGE3RTSF6D0S5C8Y":49},{"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":31,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M7AGQGVGAGE3RTSF6D0S5C8Y","skill-factory",null,"Create a new re_gent skill from a plain-language description, writing a valid SKILL.md. Use when the user wants a new skill, or to build one that style-factory proposed.","bonez-io\u002Fre_gent","bonez-io","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F256186208?v=4","01M7AGPCGD4RYYFYNC4M0TT73S","Bonez","01M7AGPCH1215VZW2QYGSST8ER",5,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fbonez-io\u002Fre_gent\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskill-factory\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: Create a new re_gent skill from a plain-language description, writing a valid SKILL.md. Use when the user wants a new skill, or to build one that style-factory proposed.\nallowed-tools: Bash(rgt log *), Bash(rgt sessions *), Glob, Read, Write\nargument-hint: \"\u003Cdescription of what the skill should do>\"\n---\n\nTurn a description into a working skill file.\n\nA skill is a prompt plus a tool grant. The intelligence is the agent's, the data is\nre_gent's, and the skill is the wiring between them — so writing one is mostly\ndeciding *what to ask for* and *what it is allowed to run*.\n\n## 1. Settle the shape\n\nBefore writing, be able to answer in one sentence each:\n\n- **Trigger** — when should an agent reach for this? This becomes `description`,\n  and it is the single most important line in the file: it is what the agent\n  matches against. Name the situation, not the mechanism.\n- **Input** — a path, a step hash, a symptom, nothing? This becomes\n  `argument-hint`.\n- **Data** — which `rgt` commands supply the facts.\n- **Output** — what the user should be holding at the end.\n\nIf the request is vague, ask one question. A skill built on a guess triggers at the\nwrong moment and is worse than no skill.\n\n## 2. Check it is not already there\n\nUse `Glob` to list `.claude\u002Fskills\u002F*\u002FSKILL.md` (or the active host's matching\nskills directory), then read any neighbour that looks close.\n\nExtending an existing skill beats adding a\nnear-duplicate — two skills with overlapping descriptions make the agent pick badly.\n\n## 3. Write it\n\n`.claude\u002Fskills\u002F\u003Ckebab-case-name>\u002FSKILL.md`:\n\n```markdown\n---\ndescription: \u003Cwhat it does + when to use it, one sentence>\nallowed-tools: Bash(rgt \u003Ccommand> *)\nargument-hint: \"\u003Carg>\"\n---\n\n\u003CInstructions to the agent.>\n```\n\nRules that matter:\n\n- **Grant the narrowest tools that work.** `Bash(rgt log *)` — never bare `Bash`.\n  A skill that only reads should never be able to write.\n- **Write instructions, not prose.** The reader is an agent about to act.\n- **Say what to do with the data**, not just how to fetch it. The gathering is the\n  easy half; the analysis is the skill.\n- **Prefer real commands you have verified exist.** Check with `rgt \u003Ccmd> --help`\n  before referencing a flag. A skill that cites a flag that does not exist fails at\n  the moment it is trusted.\n- **Name sibling skills** the agent should chain to, so skills compose.\n\n## 4. Verify before claiming it works\n\n```bash\nrgt \u003Ceach command in allowed-tools> --help\n```\n\nConfirm every command and flag exists. Then state plainly what you could not test —\na skill's real behaviour only shows when an agent runs it against real history.\n\n## Report\n\nPath written, the `description` line verbatim (so the user can judge when it will\ntrigger), the commands it may run, and one example invocation.\n","Turn a description into a working skill file.\n\nA skill is a prompt plus a tool grant. The intelligence is the agent's, the data is\nre_gent's, and the skill is the wiring between them — so writing one is mostly\ndeciding *what to ask for* and *what it is allowed to run*.\n\n## 1. Settle the shape\n\nBefore writing, be able to answer in one sentence each:\n\n- **Trigger** — when should an agent reach for this? This becomes `description`,\n  and it is the single most important line in the file: it is what the agent\n  matches against. Name the situation, not the mechanism.\n- **Input** — a path, a step hash, a symptom, nothing? This becomes\n  `argument-hint`.\n- **Data** — which `rgt` commands supply the facts.\n- **Output** — what the user should be holding at the end.\n\nIf the request is vague, ask one question. A skill built on a guess triggers at the\nwrong moment and is worse than no skill.\n\n## 2. Check it is not already there\n\nUse `Glob` to list `.claude\u002Fskills\u002F*\u002FSKILL.md` (or the active host's matching\nskills directory), then read any neighbour that looks close.\n\nExtending an existing skill beats adding a\nnear-duplicate — two skills with overlapping descriptions make the agent pick badly.\n\n## 3. Write it\n\n`.claude\u002Fskills\u002F\u003Ckebab-case-name>\u002FSKILL.md`:\n\n```markdown\n---\ndescription: \u003Cwhat it does + when to use it, one sentence>\nallowed-tools: Bash(rgt \u003Ccommand> *)\nargument-hint: \"\u003Carg>\"\n---\n\n\u003CInstructions to the agent.>\n```\n\nRules that matter:\n\n- **Grant the narrowest tools that work.** `Bash(rgt log *)` — never bare `Bash`.\n  A skill that only reads should never be able to write.\n- **Write instructions, not prose.** The reader is an agent about to act.\n- **Say what to do with the data**, not just how to fetch it. The gathering is the\n  easy half; the analysis is the skill.\n- **Prefer real commands you have verified exist.** Check with `rgt \u003Ccmd> --help`\n  before referencing a flag. A skill that cites a flag that does not exist fails at\n  the moment it is trusted.\n- **Name sibling skills** the agent should chain to, so skills compose.\n\n## 4. Verify before claiming it works\n\n```bash\nrgt \u003Ceach command in allowed-tools> --help\n```\n\nConfirm every command and flag exists. Then state plainly what you could not test —\na skill's real behaviour only shows when an agent runs it against real history.\n\n## Report\n\nPath written, the `description` line verbatim (so the user can judge when it will\ntrigger), the commands it may run, and one example invocation.\n",{"description":7,"allowed-tools":24,"argument-hint":25},"Bash(rgt log *), Bash(rgt sessions *), Glob, Read, Write","\u003Cdescription of what the skill should do>","main","df5e369a539750edc2be9367f31e9b255b549e4a",".claude\u002Fskills\u002Fskill-factory",0,"https:\u002F\u002Fgithub.com\u002Fbonez-io\u002Fre_gent","https:\u002F\u002Fre-gent.dev","https:\u002F\u002Fgithub.com\u002Fbonez-io","https:\u002F\u002Fbonez.io","2026-11-11 16:03:01",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add bonez-io\u002Fre_gent --skill skill-factory",{"tool":41,"command":42},"bunx","bunx skills add bonez-io\u002Fre_gent --skill skill-factory",{"tool":44,"command":45},"pnpm","pnpm dlx skills add bonez-io\u002Fre_gent --skill skill-factory","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbonez-io\u002Fre_gent\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskill-factory\u002FSKILL.md",true,[],[50,57,62,69,76,83],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7AGRPKYC03Q4T1KV839ME3R","style-factory","Read captured conversations to learn how this person actually works, then propose skills tailored to them. Use to discover which repeated workflows are worth turning into skills.","https:\u002F\u002Fgithub.com\u002Fbonez-io\u002Fre_gent\u002Fblob\u002Fmain\u002Finternal\u002Fskills\u002Fdata\u002Fstyle-factory\u002FSKILL.md",[],[],{"skillNo":58,"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":59,"categories":60,"keywords":61,"publishedAt":19},"01M7AGRKF7J7YSXRPD81CJKJ1T","https:\u002F\u002Fgithub.com\u002Fbonez-io\u002Fre_gent\u002Fblob\u002Fmain\u002Finternal\u002Fskills\u002Fdata\u002Fskill-factory\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7AGRHX4CPYHX1D5MYJ1NCE3","show","Show detailed context for a re_gent step, including tool calls, tool results, and conversation.","https:\u002F\u002Fgithub.com\u002Fbonez-io\u002Fre_gent\u002Fblob\u002Fmain\u002Finternal\u002Fskills\u002Fdata\u002Fshow\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"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},"01M7AGRF1XZP9DXKNF0NEXZ22H","rewind","Rewind workspace and conversation to a previous re_gent step. Non-destructive with automatic backup. Use when recovering from mistakes or exploring alternative paths.","https:\u002F\u002Fgithub.com\u002Fbonez-io\u002Fre_gent\u002Fblob\u002Fmain\u002Finternal\u002Fskills\u002Fdata\u002Frewind\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},"01M7AGRBSQFJR4GX2RVP7DZE9Z","regent-skills","Discover and install re_gent skills. Use when the user asks what re_gent skills exist, wants to add one, or asks a question about their own history that no installed skill covers.","https:\u002F\u002Fgithub.com\u002Fbonez-io\u002Fre_gent\u002Fblob\u002Fmain\u002Finternal\u002Fskills\u002Fdata\u002Fregent-skills\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},"01M7AGR9MXTZ91ZVQB1MPP3QYJ","log","View the re_gent activity log for the default or selected session. The default view shows the conversation timeline and tool calls; file summaries are available with file flags.","https:\u002F\u002Fgithub.com\u002Fbonez-io\u002Fre_gent\u002Fblob\u002Fmain\u002Finternal\u002Fskills\u002Fdata\u002Flog\u002FSKILL.md",[],[]]