[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75H3KWB3Y8RSSXGDZ8F63DH":3,"skill-same:01M75H3KWB3Y8RSSXGDZ8F63DH":46},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M75H3KWB3Y8RSSXGDZ8F63DH","bootstrap-botfile",null,"Drive the botfile CLI to manage AI-agent skills, instructions, and commands. Use when asked to sync, plan, adopt, or check the status of agent components managed by botfile.","listfold\u002Fbotfile","listfold","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F219838606?v=4","01M75H3BBQZBYK6EYC7Z9BVJBG","01M75H3BCD4MEWK4FRFAAPJ1QY",18,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flistfold\u002Fbotfile\u002Fblob\u002Fmain\u002Fexamples\u002Fbotfile_example\u002Fbotfile\u002Fskills\u002Fbootstrap-botfile\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: bootstrap-botfile\ndescription: Drive the botfile CLI to manage AI-agent skills, instructions, and commands. Use when asked to sync, plan, adopt, or check the status of agent components managed by botfile.\n---\n\n# botfile\n\nbotfile manages AI-agent skills, instructions, and commands as symlinks from source repositories you control.\n\nThis skill carries botfile's operator guide. The CLI prints the same guide: run `botfile guide` (or `botfile guide --format markdown|json`); it is also published at [botfile.org\u002Fagents.html](https:\u002F\u002Fbotfile.org\u002Fagents.html). If `botfile` is not on PATH, install it first (with the user's agreement) per [botfile.org](https:\u002F\u002Fbotfile.org\u002F#install).\n\n## Model\n\n- **source**: A local directory, often a git checkout, holding curated components. botfile reads it in place; git does any fetching.\n- **plugin**: A named bundle inside a source. Even a single-bundle source has an explicit plugin directory: `\u003Csource>\u002F\u003Cplugin>\u002F`.\n- **component**: A typed artifact under a plugin. Kinds today: a skill (a directory with a SKILL.md), an instruction (a .md file), and a command (a .md file the agent exposes as a slash command).\n- **selection**: A config rule mapping a source (and optionally one plugin or component) to one or more agents that should receive it.\n\n## Config\n\nPath: `~\u002F.config\u002Fbotfile\u002Fconfig.toml`\n\n```toml\n[[sources]]\nname = \"personal\"\nlocation = \"~\u002Fbotfiles\u002Fpersonal\"\n\n[[selections]]\nsource = \"personal\"\nagents = [\"claude-code\"]\n```\n\n## Scope\n\n- botfile operates at user scope only: the per-user paths under your home directory. It never writes into a project checkout (a repo's .claude\u002F or an in-repo AGENTS.md); project-scoped components belong to the project.\n- Selections fan out: one component reaches every agent its selections name, one symlink per agent's native path, and agents reading the shared ~\u002F.agents\u002Fskills pool are served by a single link. Symlinks, not copies, so an edit to the source is live through every agent at once.\n- The kinds differ in how they reach the model: an instruction is ambient (the harness injects it into every session), so it matters that instructions can be scoped to all, some, or one agent; a skill is on-demand: its name and description always sit in context and its body loads when the model matches it to the task or the user invokes it; a command is a prompt file the user runs explicitly (\u002Fname). On-demand kinds are cheap when idle, not free. Not every agent supports commands; the agents table shows a dash where a kind has no native surface.\n- A selection picks any depth of source > plugin > component: omit plugin and component for the whole source, set plugin for one bundle, set both for a single component (component is `\u003Ckind>\u002F\u003Cname>`, like `skill\u002Freview`).\n- An omitted plugin or component is a wildcard; an unknown config key is rejected rather than ignored, so a typo cannot silently widen a selection.\n\n## Workflow\n\nRun in this order; only run `sync` after the user agrees.\n\n1. **botfile status**: See what is managed, out of sync, and adoptable. Read-only, safe to run anytime.\n2. **botfile plan**: Preview the exact symlinks a sync would create or remove. Read-only; changes nothing.\n3. **confirm with the user**: Show the plan and get the user's agreement before changing anything on disk.\n4. **botfile sync**: Apply the plan only after the user agrees: create and remove symlinks to match the config.\n5. **botfile adopt \u003Cpath> --into \u003Csource>\u002F\u003Cplugin>**: If sync reports a conflict (a real file where botfile wants a link), adopt that file into a source instead of overwriting it. botfile never clobbers.\n\n## Commands\n\n| Command | Does |\n|---|---|\n| `botfile plan` | show what a sync would change |\n| `botfile sync` | reconcile your agents to match your config |\n| `botfile status` | show what is managed, out of sync, and adoptable |\n| `botfile adopt \u003Cpath> --into \u003Csource>\u002F\u003Cplugin>` | bring an agent-created component under management |\n| `botfile guide` | print this guide (text, markdown, or json) |\n| `botfile version` | print the version |\n| `botfile upgrade [--check]` | replace this binary with the latest release, checksum-verified (--check: report only) |\n\n## Agents\n\n| Agent | Skills | Instructions | Commands |\n|---|---|---|---|\n| `claude-code` | `~\u002F.claude\u002Fskills\u002F\u003Cname>\u002F` | `~\u002F.claude\u002Frules\u002F\u003Cname>.md` | `~\u002F.claude\u002Fcommands\u002F\u003Cname>.md` |\n| `codex-cli` | `~\u002F.agents\u002Fskills\u002F\u003Cname>\u002F` | `~\u002F.codex\u002FAGENTS.md` | `~\u002F.codex\u002Fprompts\u002F\u003Cname>.md` |\n| `copilot-cli` | `~\u002F.agents\u002Fskills\u002F\u003Cname>\u002F` | `~\u002F.copilot\u002Fcopilot-instructions.md` | - |\n| `copilot-vscode` | `~\u002F.agents\u002Fskills\u002F\u003Cname>\u002F` | `~\u002F.copilot\u002Finstructions\u002F\u003Cname>.instructions.md` | - |\n| `crush` | `~\u002F.agents\u002Fskills\u002F\u003Cname>\u002F` | `~\u002F.config\u002Fcrush\u002FCRUSH.md` | - |\n| `opencode` | `~\u002F.agents\u002Fskills\u002F\u003Cname>\u002F` | `~\u002F.config\u002Fopencode\u002FAGENTS.md` | `~\u002F.config\u002Fopencode\u002Fcommands\u002F\u003Cname>.md` |\n| `pi.dev` | `~\u002F.agents\u002Fskills\u002F\u003Cname>\u002F` | `~\u002F.pi\u002Fagent\u002FAGENTS.md` | `~\u002F.pi\u002Fagent\u002Fprompts\u002F\u003Cname>.md` |\n\n## JSON for agents\n\n- Every command accepts --format json. Prefer it: parse the structured report rather than scraping text.\n- The JSON envelope carries schemaVersion, command, phase, outcome, exitCode, plus ops, notes, issues, and summary counts.\n- exitCode is authoritative: 0 ok, 1 blocked (a conflict or broken config refused the change), 2 a usage or effect error.\n- plan and status never modify anything; only sync and adopt change the filesystem, and upgrade replaces botfile's own binary (checksum-verified, never in the background).\n","# botfile\n\nbotfile manages AI-agent skills, instructions, and commands as symlinks from source repositories you control.\n\nThis skill carries botfile's operator guide. The CLI prints the same guide: run `botfile guide` (or `botfile guide --format markdown|json`); it is also published at [botfile.org\u002Fagents.html](https:\u002F\u002Fbotfile.org\u002Fagents.html). If `botfile` is not on PATH, install it first (with the user's agreement) per [botfile.org](https:\u002F\u002Fbotfile.org\u002F#install).\n\n## Model\n\n- **source**: A local directory, often a git checkout, holding curated components. botfile reads it in place; git does any fetching.\n- **plugin**: A named bundle inside a source. Even a single-bundle source has an explicit plugin directory: `\u003Csource>\u002F\u003Cplugin>\u002F`.\n- **component**: A typed artifact under a plugin. Kinds today: a skill (a directory with a SKILL.md), an instruction (a .md file), and a command (a .md file the agent exposes as a slash command).\n- **selection**: A config rule mapping a source (and optionally one plugin or component) to one or more agents that should receive it.\n\n## Config\n\nPath: `~\u002F.config\u002Fbotfile\u002Fconfig.toml`\n\n```toml\n[[sources]]\nname = \"personal\"\nlocation = \"~\u002Fbotfiles\u002Fpersonal\"\n\n[[selections]]\nsource = \"personal\"\nagents = [\"claude-code\"]\n```\n\n## Scope\n\n- botfile operates at user scope only: the per-user paths under your home directory. It never writes into a project checkout (a repo's .claude\u002F or an in-repo AGENTS.md); project-scoped components belong to the project.\n- Selections fan out: one component reaches every agent its selections name, one symlink per agent's native path, and agents reading the shared ~\u002F.agents\u002Fskills pool are served by a single link. Symlinks, not copies, so an edit to the source is live through every agent at once.\n- The kinds differ in how they reach the model: an instruction is ambient (the harness injects it into every session), so it matters that instructions can be scoped to all, some, or one agent; a skill is on-demand: its name and description always sit in context and its body loads when the model matches it to the task or the user invokes it; a command is a prompt file the user runs explicitly (\u002Fname). On-demand kinds are cheap when idle, not free. Not every agent supports commands; the agents table shows a dash where a kind has no native surface.\n- A selection picks any depth of source > plugin > component: omit plugin and component for the whole source, set plugin for one bundle, set both for a single component (component is `\u003Ckind>\u002F\u003Cname>`, like `skill\u002Freview`).\n- An omitted plugin or component is a wildcard; an unknown config key is rejected rather than ignored, so a typo cannot silently widen a selection.\n\n## Workflow\n\nRun in this order; only run `sync` after the user agrees.\n\n1. **botfile status**: See what is managed, out of sync, and adoptable. Read-only, safe to run anytime.\n2. **botfile plan**: Preview the exact symlinks a sync would create or remove. Read-only; changes nothing.\n3. **confirm with the user**: Show the plan and get the user's agreement before changing anything on disk.\n4. **botfile sync**: Apply the plan only after the user agrees: create and remove symlinks to match the config.\n5. **botfile adopt \u003Cpath> --into \u003Csource>\u002F\u003Cplugin>**: If sync reports a conflict (a real file where botfile wants a link), adopt that file into a source instead of overwriting it. botfile never clobbers.\n\n## Commands\n\n| Command | Does |\n|---|---|\n| `botfile plan` | show what a sync would change |\n| `botfile sync` | reconcile your agents to match your config |\n| `botfile status` | show what is managed, out of sync, and adoptable |\n| `botfile adopt \u003Cpath> --into \u003Csource>\u002F\u003Cplugin>` | bring an agent-created component under management |\n| `botfile guide` | print this guide (text, markdown, or json) |\n| `botfile version` | print the version |\n| `botfile upgrade [--check]` | replace this binary with the latest release, checksum-verified (--check: report only) |\n\n## Agents\n\n| Agent | Skills | Instructions | Commands |\n|---|---|---|---|\n| `claude-code` | `~\u002F.claude\u002Fskills\u002F\u003Cname>\u002F` | `~\u002F.claude\u002Frules\u002F\u003Cname>.md` | `~\u002F.claude\u002Fcommands\u002F\u003Cname>.md` |\n| `codex-cli` | `~\u002F.agents\u002Fskills\u002F\u003Cname>\u002F` | `~\u002F.codex\u002FAGENTS.md` | `~\u002F.codex\u002Fprompts\u002F\u003Cname>.md` |\n| `copilot-cli` | `~\u002F.agents\u002Fskills\u002F\u003Cname>\u002F` | `~\u002F.copilot\u002Fcopilot-instructions.md` | - |\n| `copilot-vscode` | `~\u002F.agents\u002Fskills\u002F\u003Cname>\u002F` | `~\u002F.copilot\u002Finstructions\u002F\u003Cname>.instructions.md` | - |\n| `crush` | `~\u002F.agents\u002Fskills\u002F\u003Cname>\u002F` | `~\u002F.config\u002Fcrush\u002FCRUSH.md` | - |\n| `opencode` | `~\u002F.agents\u002Fskills\u002F\u003Cname>\u002F` | `~\u002F.config\u002Fopencode\u002FAGENTS.md` | `~\u002F.config\u002Fopencode\u002Fcommands\u002F\u003Cname>.md` |\n| `pi.dev` | `~\u002F.agents\u002Fskills\u002F\u003Cname>\u002F` | `~\u002F.pi\u002Fagent\u002FAGENTS.md` | `~\u002F.pi\u002Fagent\u002Fprompts\u002F\u003Cname>.md` |\n\n## JSON for agents\n\n- Every command accepts --format json. Prefer it: parse the structured report rather than scraping text.\n- The JSON envelope carries schemaVersion, command, phase, outcome, exitCode, plus ops, notes, issues, and summary counts.\n- exitCode is authoritative: 0 ok, 1 blocked (a conflict or broken config refused the change), 2 a usage or effect error.\n- plan and status never modify anything; only sync and adopt change the filesystem, and upgrade replaces botfile's own binary (checksum-verified, never in the background).\n",{"name":5,"description":7},"main","a373a5e27ed3970c219c2f096787bcd17c04754d","examples\u002Fbotfile_example\u002Fbotfile\u002Fskills\u002Fbootstrap-botfile",1,"https:\u002F\u002Fgithub.com\u002Flistfold\u002Fbotfile","https:\u002F\u002Fbotfile.org","https:\u002F\u002Fgithub.com\u002Flistfold","https:\u002F\u002Flistfold.com","2026-11-02 06:25:26",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add listfold\u002Fbotfile --skill bootstrap-botfile",{"tool":38,"command":39},"bunx","bunx skills add listfold\u002Fbotfile --skill bootstrap-botfile",{"tool":41,"command":42},"pnpm","pnpm dlx skills add listfold\u002Fbotfile --skill bootstrap-botfile","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flistfold\u002Fbotfile\u002Fblob\u002Fmain\u002Fexamples\u002Fbotfile_example\u002Fbotfile\u002Fskills\u002Fbootstrap-botfile\u002FSKILL.md",true,[],[47],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":18},"01M75H3RHFYG6JSJPHTQBX7JDM","echo","Repeat the user's message back verbatim, and nothing else.","https:\u002F\u002Fgithub.com\u002Flistfold\u002Fbotfile\u002Fblob\u002Fmain\u002Fexamples\u002Fbotfile_example\u002Fstandards\u002Fskills\u002Fecho\u002FSKILL.md",[],[]]