[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79D45A0QJMNQ58MWE7CC3C3":3,"skill-same:01M79D45A0QJMNQ58MWE7CC3C3":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":29,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M79D45A0QJMNQ58MWE7CC3C3","pclaw-features",null,"Channel-neutral reference for PersonalClaw's capabilities — sessions, agents, models, dashboard, scheduling, goal loops, tasks, subagents, file\u002Fmedia handling, and config — so you can explain what PersonalClaw can do and route the user to the right surface.","PersonalClaw\u002FPersonalClaw","PersonalClaw","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F306824595?v=4","01M79D0KNQCPQXVH30C5PREVCW","01M79D0KPT5XDNEAW87TEYQW3V",9,"MIT","https:\u002F\u002Fgithub.com\u002FPersonalClaw\u002FPersonalClaw\u002Fblob\u002Fmain\u002Fsrc\u002Fpersonalclaw\u002Fskills\u002Fbundled\u002Fpclaw-features\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pclaw-features\ndescription: Channel-neutral reference for PersonalClaw's capabilities — sessions, agents, models, dashboard, scheduling, goal loops, tasks, subagents, file\u002Fmedia handling, and config — so you can explain what PersonalClaw can do and route the user to the right surface.\nalways: false\ntriggers: help, commands, what can you do, getting started, onboard, capabilities, features, dashboard, setup, how do i\n---\n# PersonalClaw Features\n\nPersonalClaw is a personal AI workspace: persistent **sessions**, configurable\n**agents** and **models**, autonomous **goal loops**, a **dashboard** web UI, and\na set of native tools (files, knowledge, memory, subagents, scheduling,\nartifacts, notifications). It runs as a long-lived gateway and can be reached\nfrom multiple surfaces — the dashboard, and connected **channels** (e.g. a Slack\nchannel, if one is configured). This skill describes capabilities\n**channel-neutrally**: prefer the dashboard or the native tools, and only mention\na specific channel's command syntax when the user is actually on that channel.\n\n## Core capabilities\n\n| Capability | What it is |\n|---|---|\n| **Sessions** | Persistent chat sessions with warm history. Resume an earlier session or start fresh; sessions survive restarts. |\n| **Agents** | Named agent profiles (system prompt, model binding, tools, hooks, workflows). Switch the active agent or override it for one session. |\n| **Models** | A bound model per session\u002Fagent. `auto` lets PersonalClaw choose; or pin a specific native\u002Fremote model. |\n| **Goal Loops** | The unified autonomous goal engine — classify a target, plan it, then loop one self-directed cycle per turn while a deterministic supervisor decides done-ness (see the `loop-worker` skill). |\n| **Subagents** | Spin up background workers for parallel\u002Fisolated work via `subagent_run` (see the `delegation` skill). |\n| **Tasks** | Tracked units of work with status and dependency links, via the `\u002Fapi\u002Ftasks` CRUD and the native task provider (see the `task-and-project` skill). |\n| **Scheduling** | Recurring\u002Fdeferred jobs via the `schedule_*` tools (add\u002Flist\u002Fget\u002Fupdate\u002Fpause\u002Fresume\u002Fremove\u002Ftrigger). |\n| **Knowledge** | A searchable knowledge pool: `knowledge_search` \u002F `knowledge_get` \u002F `knowledge_create` (see the `knowledge-grounding` skill). |\n| **Memory** | Durable lessons, preferences, and facts: `memory_remember` \u002F `memory_list` \u002F `memory_forget` (see the `memory-discipline` skill). |\n| **Artifacts** | Named, versioned generated content (widgets, HTML, docs) via `artifact_*` (see the `artifacts` skill). |\n| **Notifications** | Reach the user out-of-band via `notify` (and `notify_attachment` for files). |\n| **Hooks** | Event-driven handoffs registered with `hook_register`. |\n| **Workflows** | Reusable standard operating procedures: `workflow_list` \u002F `workflow_get` \u002F `workflow_run` \u002F `workflow_create`. |\n\n## Dashboard\n\nThe dashboard is the primary web UI — chat, sessions, agents, models, memory,\nknowledge, scheduling, goal loops, artifacts, files, and system monitoring all\nlive there. Point the user to the relevant dashboard page when they ask \"where\ndo I…\": e.g. memory and lessons under the memory page, scheduled jobs under the\nscheduling page, saved artifacts at `\u002Fartifacts\u002F\u003Cslug>`.\n\n**Access:**\n- **Local \u002F loopback** — open the dashboard URL directly; loopback access needs\n  no token. Over SSH, forward the port (`ssh -L \u003Cport>:localhost:\u003Cport> \u003Chost>`)\n  and open `http:\u002F\u002Flocalhost:\u003Cport>`.\n- **Remote** — if a public dashboard URL is configured, remote access uses a\n  short-lived presigned link (request one from whatever surface you're on).\n\n## Configuration\n\nConfiguration lives in `~\u002F.personalclaw\u002Fconfig.json` (override the home dir with\n`PERSONALCLAW_HOME`). Common fields:\n\n- `agent.approval_mode` — `\"interactive\"` (the default: every call that needs\n  approval asks, a chat on its card and an agent no chat started in the Inbox),\n  `\"trust_reads\"` (a chat also runs a read-only shell command unasked) or `\"auto\"`\n  (an agent no chat started approves every call it makes; chats still ask).\n- `agent.model` — default model (`\"auto\"` or a specific model id).\n- `dashboard.url` — hostname\u002Fport\u002Fbind for remote dashboard access. Omit for\n  localhost-only.\n\n```json\n{\n  \"agent\": { \"approval_mode\": \"interactive\", \"model\": \"auto\" },\n  \"dashboard\": { \"url\": \"http:\u002F\u002Fmy-host.example.com:8080\" }\n}\n```\n\n| Environment variable | Purpose | Default |\n|---|---|---|\n| `PERSONALCLAW_HOME` | Config\u002Fdata directory | `~\u002F.personalclaw` |\n| `PERSONALCLAW_PORT` | Dashboard port (dev mode) | `10000` |\n| `PERSONALCLAW_PROJECT_DIR` | Agent config\u002Fskills directory | Auto-detected |\n\n## File & media handling\n\nPersonalClaw processes attachments the user sends on any channel that supports\nthem:\n\n| Attachment type | Behavior |\n|---|---|\n| **Voice memos** (audio\u002F*) | Transcribed locally (speech-to-text), text injected into the conversation. |\n| **Images** (png, jpeg, gif, webp, bmp) | Sent to the model as vision input. |\n| **Text\u002Fcode files** (text\u002F*) | Content read and injected inline (truncated for very large files). |\n| **Other files** | Metadata noted; not auto-downloaded. |\n\nSpeech-to-text is on by default where a transcription backend is available.\n\n## Channel surfaces\n\nPersonalClaw can be driven from connected channels in addition to the dashboard.\nEach channel may expose its own command syntax — describe it only when the user\nis on that channel. **For example, if using a Slack channel:** users typically\nrequest a dashboard link, toggle auto-approval, switch agents, manage tracked\nchannels, or force-halt a running turn via that channel's commands; the channel\nalso defines per-channel activation modes (respond always \u002F on mention \u002F observe\n\u002F off). Treat any such channel-specific command surface as an implementation\ndetail of that channel, not a core PersonalClaw concept — the underlying\ncapabilities (sessions, agents, scheduling, stop\u002Fcancel) are the same regardless\nof surface.\n","# PersonalClaw Features\n\nPersonalClaw is a personal AI workspace: persistent **sessions**, configurable\n**agents** and **models**, autonomous **goal loops**, a **dashboard** web UI, and\na set of native tools (files, knowledge, memory, subagents, scheduling,\nartifacts, notifications). It runs as a long-lived gateway and can be reached\nfrom multiple surfaces — the dashboard, and connected **channels** (e.g. a Slack\nchannel, if one is configured). This skill describes capabilities\n**channel-neutrally**: prefer the dashboard or the native tools, and only mention\na specific channel's command syntax when the user is actually on that channel.\n\n## Core capabilities\n\n| Capability | What it is |\n|---|---|\n| **Sessions** | Persistent chat sessions with warm history. Resume an earlier session or start fresh; sessions survive restarts. |\n| **Agents** | Named agent profiles (system prompt, model binding, tools, hooks, workflows). Switch the active agent or override it for one session. |\n| **Models** | A bound model per session\u002Fagent. `auto` lets PersonalClaw choose; or pin a specific native\u002Fremote model. |\n| **Goal Loops** | The unified autonomous goal engine — classify a target, plan it, then loop one self-directed cycle per turn while a deterministic supervisor decides done-ness (see the `loop-worker` skill). |\n| **Subagents** | Spin up background workers for parallel\u002Fisolated work via `subagent_run` (see the `delegation` skill). |\n| **Tasks** | Tracked units of work with status and dependency links, via the `\u002Fapi\u002Ftasks` CRUD and the native task provider (see the `task-and-project` skill). |\n| **Scheduling** | Recurring\u002Fdeferred jobs via the `schedule_*` tools (add\u002Flist\u002Fget\u002Fupdate\u002Fpause\u002Fresume\u002Fremove\u002Ftrigger). |\n| **Knowledge** | A searchable knowledge pool: `knowledge_search` \u002F `knowledge_get` \u002F `knowledge_create` (see the `knowledge-grounding` skill). |\n| **Memory** | Durable lessons, preferences, and facts: `memory_remember` \u002F `memory_list` \u002F `memory_forget` (see the `memory-discipline` skill). |\n| **Artifacts** | Named, versioned generated content (widgets, HTML, docs) via `artifact_*` (see the `artifacts` skill). |\n| **Notifications** | Reach the user out-of-band via `notify` (and `notify_attachment` for files). |\n| **Hooks** | Event-driven handoffs registered with `hook_register`. |\n| **Workflows** | Reusable standard operating procedures: `workflow_list` \u002F `workflow_get` \u002F `workflow_run` \u002F `workflow_create`. |\n\n## Dashboard\n\nThe dashboard is the primary web UI — chat, sessions, agents, models, memory,\nknowledge, scheduling, goal loops, artifacts, files, and system monitoring all\nlive there. Point the user to the relevant dashboard page when they ask \"where\ndo I…\": e.g. memory and lessons under the memory page, scheduled jobs under the\nscheduling page, saved artifacts at `\u002Fartifacts\u002F\u003Cslug>`.\n\n**Access:**\n- **Local \u002F loopback** — open the dashboard URL directly; loopback access needs\n  no token. Over SSH, forward the port (`ssh -L \u003Cport>:localhost:\u003Cport> \u003Chost>`)\n  and open `http:\u002F\u002Flocalhost:\u003Cport>`.\n- **Remote** — if a public dashboard URL is configured, remote access uses a\n  short-lived presigned link (request one from whatever surface you're on).\n\n## Configuration\n\nConfiguration lives in `~\u002F.personalclaw\u002Fconfig.json` (override the home dir with\n`PERSONALCLAW_HOME`). Common fields:\n\n- `agent.approval_mode` — `\"interactive\"` (the default: every call that needs\n  approval asks, a chat on its card and an agent no chat started in the Inbox),\n  `\"trust_reads\"` (a chat also runs a read-only shell command unasked) or `\"auto\"`\n  (an agent no chat started approves every call it makes; chats still ask).\n- `agent.model` — default model (`\"auto\"` or a specific model id).\n- `dashboard.url` — hostname\u002Fport\u002Fbind for remote dashboard access. Omit for\n  localhost-only.\n\n```json\n{\n  \"agent\": { \"approval_mode\": \"interactive\", \"model\": \"auto\" },\n  \"dashboard\": { \"url\": \"http:\u002F\u002Fmy-host.example.com:8080\" }\n}\n```\n\n| Environment variable | Purpose | Default |\n|---|---|---|\n| `PERSONALCLAW_HOME` | Config\u002Fdata directory | `~\u002F.personalclaw` |\n| `PERSONALCLAW_PORT` | Dashboard port (dev mode) | `10000` |\n| `PERSONALCLAW_PROJECT_DIR` | Agent config\u002Fskills directory | Auto-detected |\n\n## File & media handling\n\nPersonalClaw processes attachments the user sends on any channel that supports\nthem:\n\n| Attachment type | Behavior |\n|---|---|\n| **Voice memos** (audio\u002F*) | Transcribed locally (speech-to-text), text injected into the conversation. |\n| **Images** (png, jpeg, gif, webp, bmp) | Sent to the model as vision input. |\n| **Text\u002Fcode files** (text\u002F*) | Content read and injected inline (truncated for very large files). |\n| **Other files** | Metadata noted; not auto-downloaded. |\n\nSpeech-to-text is on by default where a transcription backend is available.\n\n## Channel surfaces\n\nPersonalClaw can be driven from connected channels in addition to the dashboard.\nEach channel may expose its own command syntax — describe it only when the user\nis on that channel. **For example, if using a Slack channel:** users typically\nrequest a dashboard link, toggle auto-approval, switch agents, manage tracked\nchannels, or force-halt a running turn via that channel's commands; the channel\nalso defines per-channel activation modes (respond always \u002F on mention \u002F observe\n\u002F off). Treat any such channel-specific command surface as an implementation\ndetail of that channel, not a core PersonalClaw concept — the underlying\ncapabilities (sessions, agents, scheduling, stop\u002Fcancel) are the same regardless\nof surface.\n",{"name":5,"always":19,"triggers":23,"description":7},"help, commands, what can you do, getting started, onboard, capabilities, features, dashboard, setup, how do i","main","cfba933d376f99978247a7d18b592232c649e87a","src\u002Fpersonalclaw\u002Fskills\u002Fbundled\u002Fpclaw-features",6,"https:\u002F\u002Fgithub.com\u002FPersonalClaw\u002FPersonalClaw","https:\u002F\u002Fpersonalclaw.dev","https:\u002F\u002Fgithub.com\u002FPersonalClaw","Self-hosted personal AI agent — an agentic OS for one person: chat, goal loops, memory, knowledge, automation, apps. Local-first, zero telemetry, MIT.","2026-11-15 04:04:52",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add PersonalClaw\u002FPersonalClaw --skill pclaw-features",{"tool":39,"command":40},"bunx","bunx skills add PersonalClaw\u002FPersonalClaw --skill pclaw-features",{"tool":42,"command":43},"pnpm","pnpm dlx skills add PersonalClaw\u002FPersonalClaw --skill pclaw-features","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPersonalClaw\u002FPersonalClaw\u002Fblob\u002Fmain\u002Fsrc\u002Fpersonalclaw\u002Fskills\u002Fbundled\u002Fpclaw-features\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":18},"01M79D5S4EBPTFGMRDY7AM7ERD","ledger-read","Read a ledger CSV","https:\u002F\u002Fgithub.com\u002FPersonalClaw\u002FPersonalClaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fexternal_formats_golden\u002Fskill-md\u002Fskills\u002Fledger-read\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":18},"01M79D5QFEBGM2PTM21WVTA90K","budget-coach","Weekly spend review","https:\u002F\u002Fgithub.com\u002FPersonalClaw\u002FPersonalClaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fexternal_formats_golden\u002Fskill-md\u002Fskills\u002Fbudget-coach\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":18},"01M79D5MTEV62YBKTNY874Y9C4","yt-transcript","Fetch the transcript of a YouTube video and summarise it with timestamps. Use when the user shares a youtube.com or youtu.be link and asks what it says.","https:\u002F\u002Fgithub.com\u002FPersonalClaw\u002FPersonalClaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fagent_tool_skills\u002Fyt-transcript\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":18},"01M79D5JG2M47DS0X3GRZ94PXY","incident-writeup","Turn my incident notes, Slack excerpts and graphs into a blameless postmortem in Cartwheel's format. Use after an on-call incident once the mitigation is in.","https:\u002F\u002Fgithub.com\u002FPersonalClaw\u002FPersonalClaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fagent_tool_skills\u002Fincident-writeup\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M79D5DX9SWDFDAFW3AD5FATT","feedsmith-release","Cut a feedsmith release - bump the version, move the Unreleased changelog section, tag, and draft the GitHub release notes. Use when I say \"release feedsmith\" or \"cut 0.x\".","https:\u002F\u002Fgithub.com\u002FPersonalClaw\u002FPersonalClaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fagent_tool_skills\u002Ffeedsmith-release\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M79D59Z7A0FEZSB5AEQYHNSR","feedsmith-bench","Benchmark feedsmith fetch against a real OPML, cold and warm, and compare with main. Use before merging anything that touches fetch.py or store.py.","https:\u002F\u002Fgithub.com\u002FPersonalClaw\u002FPersonalClaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fagent_tool_homes\u002Fnoor\u002F.codex\u002Fskills\u002Ffeedsmith-bench\u002FSKILL.md",[],[]]