[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MN20FFKAHRM6R811XR0WVP":3,"skill-same:01M6MN20FFKAHRM6R811XR0WVP":81},{"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":26,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M6MN20FFKAHRM6R811XR0WVP","agentdomains",null,"Get and manage a free public domain (yourname.makes.fyi or yourname.agentdomains.co) for an AI agent or app using the AgentDomains CLI. Use this whenever an agent builds a website or API and needs somewhere to put it, or needs a public hostname to expose a server, create a webhook URL, or get a stable address. Covers signup, claiming a name, pointing it at an IP or CNAME, getting HTTPS, forwarding (HTTP redirect) to an existing site, reverse-proxying the name to a backend over HTTPS, delegating to your own nameservers, removing a single DNS record, and closing the account again.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftashfeenahmed\u002FAgentDomains-skill\u002Fplugins\u002Fagentdomains\u002Fskills\u002Fagentdomains\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[5,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"app","at","closing","URL","co","fyi","http redirect","hostname","free","cli","webhook","ip","get","api","dns","server","website","create","ai agent","2026-11-10 10:12:30",false,"---\nname: agentdomains\ndescription: >-\n  Get and manage a free public domain (yourname.makes.fyi or\n  yourname.agentdomains.co) for an AI agent or app using the AgentDomains CLI. Use\n  this whenever an agent builds a website or API and needs somewhere to put it, or\n  needs a public hostname to expose a server, create a webhook URL, or get a stable\n  address. Covers signup, claiming a name, pointing it at an IP or CNAME, getting\n  HTTPS, forwarding (HTTP redirect) to an existing site, reverse-proxying the name\n  to a backend over HTTPS, delegating to your own nameservers, removing a single DNS\n  record, and closing the account again.\n---\n\n# AgentDomains — free domains for the sites agents build\n\nAgentDomains hands out real, public domains from a single CLI command. Names live\nunder two domains: `makes.fyi` (the default) and `agentdomains.co`, so you can\nclaim `yourname.makes.fyi` or `yourname.agentdomains.co`. No web forms. Signing up\nneeds nothing at all; the account's first name needs an email address, used only\nfor the confirmation link. Full docs: https:\u002F\u002Fdocs.agentdomains.co\n\n## When to use this skill\n\nReach for AgentDomains when you need a **public hostname** and don't have one:\n- putting a server that already has a public IP (a VPS, a cloud VM) behind a name,\n- a stable URL for a webhook or callback,\n- hosting a small site or API for an agent,\n- giving a long-running agent a memorable address.\n\nIf the user already has a domain they control, prefer that. AgentDomains is for the\n\"I just need a hostname, fast and free\" case.\n\n## Setup (once)\n\nEnsure the CLI is installed, then create an account. The bundled helper does both:\n\n```bash\nbash \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsetup.sh\"\n```\n\nOr manually:\n\n```bash\ngo install github.com\u002Ftashfeenahmed\u002FAgentDomains\u002Fcmd\u002Fagentdomains@latest\nagentdomains signup            # saves an API key to ~\u002F.agentdomains\u002Fconfig.json\n```\n\n`signup` creates an anonymous **provisional** account and asks for nothing — no\nemail, no form. One account can hold up to ten names at once. The **first** time\nyou register a name you must pass `--email`, or the API answers\n`400 registering a name needs an email`: we\nsend a confirmation link and start a 30-day clock. A human confirms the link to\nmake the account (and all its names) permanent — otherwise the account and every\nname on it are deleted automatically after 30 days.\n\n```bash\nagentdomains email you@example.com   # (re)send the confirmation link any time\n```\n\n## Core workflow\n\nAlways pass `--json` so you can parse results reliably.\n\n```bash\n# register a name and point it at an IP in one step (first claim needs --email)\nagentdomains claim mybot --email you@example.com --type A --content 203.0.113.10 --json\n# -> response includes a \"note\": tell the user to confirm within 30 days or it's deleted\n\n# after the first claim the email is remembered on the account, so it's optional:\nagentdomains claim mybot2 --type CNAME --content my-app.vercel.app --json\n\n# claim under agentdomains.co instead of the default makes.fyi\nagentdomains claim mybot --domain agentdomains.co --type A --content 203.0.113.10 --json\n\n# inspect \u002F manage (add --domain to scope when a label exists under both)\nagentdomains list --json\nagentdomains get mybot --json\nagentdomains record mybot --type A --content 203.0.113.10 --host www --json\nagentdomains unrecord mybot \u003Crecord-id> --json   # drop ONE record, keep the name\nagentdomains delete mybot --json\n```\n\nNames are claimed under `makes.fyi` by default; pass `--domain agentdomains.co` to\nuse the other one. Parse the `fqdn` field from `claim`\u002F`get` to learn the live\nhostname, e.g. `mybot.makes.fyi`.\n\n### A claimed name without a record serves nothing\n\nA bare `claim` (no `--type\u002F--content`, no forward, no proxy) registers the name\nbut points it at nothing: DNS returns NXDOMAIN and `https:\u002F\u002F\u003Cname>` refuses to\nconnect. When you already know where the name should point, set it up in the\nsame step: `claim --type\u002F--content` for an IP or CNAME, or `forward`\u002F`proxy`\n(which claim the name for you) for a URL or a public backend host. If you claim first and decide later, the response carries\n`serving: false` and a `next_step` naming the command that fixes it; run that\ncommand before you tell the user the site is live. `list` and `get` show the\nsame flag, so `agentdomains list --json` finds any names you hold that are\nstill dead. Never report a hostname as working until `serving` is true (or a\n`curl` against it succeeds).\n\n## Getting HTTPS\n\nAgentDomains handles DNS, so you bring your own certificate:\n- **HTTP-01** (simplest): point the domain at your server, then\n  `certbot certonly --standalone -d mybot.makes.fyi`.\n- **DNS-01** (no inbound server): add the challenge token as TXT:\n  `agentdomains txt mybot \"\u003Ctoken>\" --host _acme-challenge --json`.\n\n## Forwarding (URL redirect)\n\nSend a name to any URL with a real HTTP redirect, served at Cloudflare's edge\nwith valid HTTPS. `forward` claims the label first if you don't own it, so it's\none step:\n\n```bash\nagentdomains forward mysite https:\u002F\u002Fdestination.example.com --json\n# mysite.makes.fyi -> 302 redirect to https:\u002F\u002Fdestination.example.com\n\n# 301 permanent instead of the default 302 temporary:\nagentdomains forward mysite https:\u002F\u002Fdest.com --permanent --json\n\n# always land on the target root (don't carry the request path\u002Fquery):\nagentdomains forward mysite https:\u002F\u002Fdest.com --no-preserve-path --json\n\n# remove a forward (keeps the label):\nagentdomains unforward mysite --json\n```\n\nPath and query are preserved by default.\n\n**A forward takes the hostname over.** Any `A`\u002F`AAAA`\u002F`CNAME` sitting on the label\nitself is deleted as part of the call and listed back in `replaced_records`, so\nyou never have to clear the way first — claiming with a record and then\nforwarding is a perfectly good sequence. Records on a sub-label\n(`www.mysite.makes.fyi`) are different hostnames and survive, and TXT records are\nleft alone. Going the other way is still refused: while a forward is in place,\nadding an address record to the same label answers a 409 telling you to\n`unforward` first.\n\n## Reverse proxy (serve a backend at the name)\n\nServe a backend you run elsewhere at the name, over HTTPS, with our edge\ncertificate — nothing to set up on the backend, and the name stays in the\naddress bar (unlike a forward, which redirects away). `proxy` claims the label\nfirst if you don't own it:\n\n```bash\nagentdomains proxy shop myapp.fly.dev --json\n# shop.makes.fyi serves https:\u002F\u002Fmyapp.fly.dev over our cert, at shop.makes.fyi\n\n# remove the proxy (keeps the label):\nagentdomains unproxy shop --json\n```\n\nWe terminate HTTPS at the edge and fetch the backend by its own hostname, so it\naccepts the request without a certificate for the AgentDomains name. Like a\nforward, a proxy **replaces** the label's own `A`\u002F`AAAA`\u002F`CNAME` records and\nreports them as `replaced_records`; a proxy and a forward remain mutually\nexclusive, so `unforward` before proxying a forwarded label.\n\nCaveat: the proxy serves the backend but can't rewrite hostnames the app\nhardcodes. Apps that bake their own domain into OAuth\u002FSSO redirects (e.g. a\nKeycloak login) may bounce users to the backend's native hostname mid-login\nuntil the AgentDomains name is added in the app's own settings. Static sites and\napps using relative URLs work with no setup.\n\n## Nameserver delegation\n\nTo control the whole subtree yourself:\n\n```bash\nagentdomains ns mybot ns1.yourdns.com ns2.yourdns.com --json\n```\n\n## Non-interactive \u002F sandboxed use\n\nThe CLI reads credentials from the environment, so no interactive setup is needed:\n\n```bash\nexport AGENTDOMAINS_API_KEY=adom_...      # reuse an existing key\nexport AGENTDOMAINS_API_URL=https:\u002F\u002Fapi.agentdomains.co\n```\n\nYou can also call the HTTP API directly; see https:\u002F\u002Fdocs.agentdomains.co#api.\n\n## Prefer MCP?\n\nEverything above is also available as typed MCP tools, if your client speaks MCP and you\nwould rather not shell out. Seventeen tools covering the same operations: availability,\nsignup, claiming, records, ACME challenges, forwarding, proxying, delegation, and closing\nthe account.\n\n- **Hosted:** `https:\u002F\u002Fmcp.agentdomains.co` (Streamable HTTP). Nothing to install.\n  `claude mcp add --transport http agentdomains https:\u002F\u002Fmcp.agentdomains.co --header \"Authorization: Bearer adom_...\"`\n- **Local:** `npx -y agentdomains-mcp` (npm package `agentdomains-mcp`, stdio), reading\n  `AGENTDOMAINS_API_KEY` or falling back to the CLI's `~\u002F.agentdomains\u002Fconfig.json`.\n\nThe **same `adom_...` API key** works for the CLI, the MCP server, and the HTTP API — there is\nnothing separate to provision. Pick whichever interface fits; they are not alternatives to\nchoose between permanently. Reference: https:\u002F\u002Fdocs.agentdomains.co\u002F#mcp\n\n## Notes\n\n- Names: lowercase letters, digits, hyphens; some labels (e.g. `api`, `www`) are reserved.\n- Labels are lowercased when claimed: asking for `MyApp` gives you `myapp.makes.fyi`, and\n  that lowercase label is what every later command (`get`, `record`, `delete`) expects.\n- **Undoing one record:** `agentdomains unrecord \u003Clabel> \u003Crecord-id> --json` removes a\n  single record and keeps the name. Record ids come from `get` (and from the `claim` \u002F\n  `record` responses).\n- **A claim and its first record stand or fall together.** If the record is malformed\n  (400) or the DNS provider refuses it (503), the label is *not* claimed — retry the\n  whole `claim` once you have fixed the record. Re-claiming a name you already hold is\n  not a failure: the CLI prints \"you already own ...\" and exits 0, and the API answers\n  `409 {\"owned\":true}`.\n- **Closing an account:** `agentdomains account delete --json` deletes the account and\n  invalidates its API key. It refuses while names are still held and lists them; add\n  `--force` to delete those names along with it. There is no undo — the names go back\n  into the pool for anyone to claim.\n- **Errors say whether to retry.** An upstream failure answers `503` with `retry:true`\n  (an outage — come back in a moment) or `retry:false` (a misconfiguration on our side;\n  retrying is pointless, report it instead).\n- **Cost:** free for up to ten names per account, no card. Everything above works on\n  the free plan. An optional **Pro** plan ($5\u002Fmonth or $48\u002Fyear) raises the limit to 100\n  names, never releases a name for being unreachable, and gets priority support.\n- **At the limit** a claim answers `403` saying so. Tell the user they can free a slot\n  (`agentdomains delete \u003Cname>`) or upgrade to Pro. Don't pick for them and never start an\n  upgrade on your own. If they ask for Pro, `agentdomains upgrade --json` (or the\n  `upgrade_to_pro` MCP tool) returns a Stripe checkout `url`: give them the link and the\n  price. Only a person can pay, so don't try to complete the payment. `agentdomains\n  billing` returns the portal link for managing or cancelling. `whoami` shows the `plan`.\n- Be a good citizen: claim what you need, `delete` what you don't.\n- Service & docs: https:\u002F\u002Fagentdomains.co · https:\u002F\u002Fdocs.agentdomains.co\n","# AgentDomains — free domains for the sites agents build\n\nAgentDomains hands out real, public domains from a single CLI command. Names live\nunder two domains: `makes.fyi` (the default) and `agentdomains.co`, so you can\nclaim `yourname.makes.fyi` or `yourname.agentdomains.co`. No web forms. Signing up\nneeds nothing at all; the account's first name needs an email address, used only\nfor the confirmation link. Full docs: https:\u002F\u002Fdocs.agentdomains.co\n\n## When to use this skill\n\nReach for AgentDomains when you need a **public hostname** and don't have one:\n- putting a server that already has a public IP (a VPS, a cloud VM) behind a name,\n- a stable URL for a webhook or callback,\n- hosting a small site or API for an agent,\n- giving a long-running agent a memorable address.\n\nIf the user already has a domain they control, prefer that. AgentDomains is for the\n\"I just need a hostname, fast and free\" case.\n\n## Setup (once)\n\nEnsure the CLI is installed, then create an account. The bundled helper does both:\n\n```bash\nbash \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsetup.sh\"\n```\n\nOr manually:\n\n```bash\ngo install github.com\u002Ftashfeenahmed\u002FAgentDomains\u002Fcmd\u002Fagentdomains@latest\nagentdomains signup            # saves an API key to ~\u002F.agentdomains\u002Fconfig.json\n```\n\n`signup` creates an anonymous **provisional** account and asks for nothing — no\nemail, no form. One account can hold up to ten names at once. The **first** time\nyou register a name you must pass `--email`, or the API answers\n`400 registering a name needs an email`: we\nsend a confirmation link and start a 30-day clock. A human confirms the link to\nmake the account (and all its names) permanent — otherwise the account and every\nname on it are deleted automatically after 30 days.\n\n```bash\nagentdomains email you@example.com   # (re)send the confirmation link any time\n```\n\n## Core workflow\n\nAlways pass `--json` so you can parse results reliably.\n\n```bash\n# register a name and point it at an IP in one step (first claim needs --email)\nagentdomains claim mybot --email you@example.com --type A --content 203.0.113.10 --json\n# -> response includes a \"note\": tell the user to confirm within 30 days or it's deleted\n\n# after the first claim the email is remembered on the account, so it's optional:\nagentdomains claim mybot2 --type CNAME --content my-app.vercel.app --json\n\n# claim under agentdomains.co instead of the default makes.fyi\nagentdomains claim mybot --domain agentdomains.co --type A --content 203.0.113.10 --json\n\n# inspect \u002F manage (add --domain to scope when a label exists under both)\nagentdomains list --json\nagentdomains get mybot --json\nagentdomains record mybot --type A --content 203.0.113.10 --host www --json\nagentdomains unrecord mybot \u003Crecord-id> --json   # drop ONE record, keep the name\nagentdomains delete mybot --json\n```\n\nNames are claimed under `makes.fyi` by default; pass `--domain agentdomains.co` to\nuse the other one. Parse the `fqdn` field from `claim`\u002F`get` to learn the live\nhostname, e.g. `mybot.makes.fyi`.\n\n### A claimed name without a record serves nothing\n\nA bare `claim` (no `--type\u002F--content`, no forward, no proxy) registers the name\nbut points it at nothing: DNS returns NXDOMAIN and `https:\u002F\u002F\u003Cname>` refuses to\nconnect. When you already know where the name should point, set it up in the\nsame step: `claim --type\u002F--content` for an IP or CNAME, or `forward`\u002F`proxy`\n(which claim the name for you) for a URL or a public backend host. If you claim first and decide later, the response carries\n`serving: false` and a `next_step` naming the command that fixes it; run that\ncommand before you tell the user the site is live. `list` and `get` show the\nsame flag, so `agentdomains list --json` finds any names you hold that are\nstill dead. Never report a hostname as working until `serving` is true (or a\n`curl` against it succeeds).\n\n## Getting HTTPS\n\nAgentDomains handles DNS, so you bring your own certificate:\n- **HTTP-01** (simplest): point the domain at your server, then\n  `certbot certonly --standalone -d mybot.makes.fyi`.\n- **DNS-01** (no inbound server): add the challenge token as TXT:\n  `agentdomains txt mybot \"\u003Ctoken>\" --host _acme-challenge --json`.\n\n## Forwarding (URL redirect)\n\nSend a name to any URL with a real HTTP redirect, served at Cloudflare's edge\nwith valid HTTPS. `forward` claims the label first if you don't own it, so it's\none step:\n\n```bash\nagentdomains forward mysite https:\u002F\u002Fdestination.example.com --json\n# mysite.makes.fyi -> 302 redirect to https:\u002F\u002Fdestination.example.com\n\n# 301 permanent instead of the default 302 temporary:\nagentdomains forward mysite https:\u002F\u002Fdest.com --permanent --json\n\n# always land on the target root (don't carry the request path\u002Fquery):\nagentdomains forward mysite https:\u002F\u002Fdest.com --no-preserve-path --json\n\n# remove a forward (keeps the label):\nagentdomains unforward mysite --json\n```\n\nPath and query are preserved by default.\n\n**A forward takes the hostname over.** Any `A`\u002F`AAAA`\u002F`CNAME` sitting on the label\nitself is deleted as part of the call and listed back in `replaced_records`, so\nyou never have to clear the way first — claiming with a record and then\nforwarding is a perfectly good sequence. Records on a sub-label\n(`www.mysite.makes.fyi`) are different hostnames and survive, and TXT records are\nleft alone. Going the other way is still refused: while a forward is in place,\nadding an address record to the same label answers a 409 telling you to\n`unforward` first.\n\n## Reverse proxy (serve a backend at the name)\n\nServe a backend you run elsewhere at the name, over HTTPS, with our edge\ncertificate — nothing to set up on the backend, and the name stays in the\naddress bar (unlike a forward, which redirects away). `proxy` claims the label\nfirst if you don't own it:\n\n```bash\nagentdomains proxy shop myapp.fly.dev --json\n# shop.makes.fyi serves https:\u002F\u002Fmyapp.fly.dev over our cert, at shop.makes.fyi\n\n# remove the proxy (keeps the label):\nagentdomains unproxy shop --json\n```\n\nWe terminate HTTPS at the edge and fetch the backend by its own hostname, so it\naccepts the request without a certificate for the AgentDomains name. Like a\nforward, a proxy **replaces** the label's own `A`\u002F`AAAA`\u002F`CNAME` records and\nreports them as `replaced_records`; a proxy and a forward remain mutually\nexclusive, so `unforward` before proxying a forwarded label.\n\nCaveat: the proxy serves the backend but can't rewrite hostnames the app\nhardcodes. Apps that bake their own domain into OAuth\u002FSSO redirects (e.g. a\nKeycloak login) may bounce users to the backend's native hostname mid-login\nuntil the AgentDomains name is added in the app's own settings. Static sites and\napps using relative URLs work with no setup.\n\n## Nameserver delegation\n\nTo control the whole subtree yourself:\n\n```bash\nagentdomains ns mybot ns1.yourdns.com ns2.yourdns.com --json\n```\n\n## Non-interactive \u002F sandboxed use\n\nThe CLI reads credentials from the environment, so no interactive setup is needed:\n\n```bash\nexport AGENTDOMAINS_API_KEY=adom_...      # reuse an existing key\nexport AGENTDOMAINS_API_URL=https:\u002F\u002Fapi.agentdomains.co\n```\n\nYou can also call the HTTP API directly; see https:\u002F\u002Fdocs.agentdomains.co#api.\n\n## Prefer MCP?\n\nEverything above is also available as typed MCP tools, if your client speaks MCP and you\nwould rather not shell out. Seventeen tools covering the same operations: availability,\nsignup, claiming, records, ACME challenges, forwarding, proxying, delegation, and closing\nthe account.\n\n- **Hosted:** `https:\u002F\u002Fmcp.agentdomains.co` (Streamable HTTP). Nothing to install.\n  `claude mcp add --transport http agentdomains https:\u002F\u002Fmcp.agentdomains.co --header \"Authorization: Bearer adom_...\"`\n- **Local:** `npx -y agentdomains-mcp` (npm package `agentdomains-mcp`, stdio), reading\n  `AGENTDOMAINS_API_KEY` or falling back to the CLI's `~\u002F.agentdomains\u002Fconfig.json`.\n\nThe **same `adom_...` API key** works for the CLI, the MCP server, and the HTTP API — there is\nnothing separate to provision. Pick whichever interface fits; they are not alternatives to\nchoose between permanently. Reference: https:\u002F\u002Fdocs.agentdomains.co\u002F#mcp\n\n## Notes\n\n- Names: lowercase letters, digits, hyphens; some labels (e.g. `api`, `www`) are reserved.\n- Labels are lowercased when claimed: asking for `MyApp` gives you `myapp.makes.fyi`, and\n  that lowercase label is what every later command (`get`, `record`, `delete`) expects.\n- **Undoing one record:** `agentdomains unrecord \u003Clabel> \u003Crecord-id> --json` removes a\n  single record and keeps the name. Record ids come from `get` (and from the `claim` \u002F\n  `record` responses).\n- **A claim and its first record stand or fall together.** If the record is malformed\n  (400) or the DNS provider refuses it (503), the label is *not* claimed — retry the\n  whole `claim` once you have fixed the record. Re-claiming a name you already hold is\n  not a failure: the CLI prints \"you already own ...\" and exits 0, and the API answers\n  `409 {\"owned\":true}`.\n- **Closing an account:** `agentdomains account delete --json` deletes the account and\n  invalidates its API key. It refuses while names are still held and lists them; add\n  `--force` to delete those names along with it. There is no undo — the names go back\n  into the pool for anyone to claim.\n- **Errors say whether to retry.** An upstream failure answers `503` with `retry:true`\n  (an outage — come back in a moment) or `retry:false` (a misconfiguration on our side;\n  retrying is pointless, report it instead).\n- **Cost:** free for up to ten names per account, no card. Everything above works on\n  the free plan. An optional **Pro** plan ($5\u002Fmonth or $48\u002Fyear) raises the limit to 100\n  names, never releases a name for being unreachable, and gets priority support.\n- **At the limit** a claim answers `403` saying so. Tell the user they can free a slot\n  (`agentdomains delete \u003Cname>`) or upgrade to Pro. Don't pick for them and never start an\n  upgrade on your own. If they ask for Pro, `agentdomains upgrade --json` (or the\n  `upgrade_to_pro` MCP tool) returns a Stripe checkout `url`: give them the link and the\n  price. Only a person can pay, so don't try to complete the payment. `agentdomains\n  billing` returns the portal link for managing or cancelling. `whoami` shows the `plan`.\n- Be a good citizen: claim what you need, `delete` what you don't.\n- Service & docs: https:\u002F\u002Fagentdomains.co · https:\u002F\u002Fdocs.agentdomains.co\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Ftashfeenahmed\u002FAgentDomains-skill\u002Fplugins\u002Fagentdomains\u002Fskills\u002Fagentdomains",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill agentdomains",{"tool":67,"command":68},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill agentdomains",{"tool":70,"command":71},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill agentdomains","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftashfeenahmed\u002FAgentDomains-skill\u002Fplugins\u002Fagentdomains\u002Fskills\u002Fagentdomains\u002FSKILL.md",true,[75],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"scripts\u002Fsetup.sh","SCRIPT","脚本",1051,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftashfeenahmed\u002FAgentDomains-skill\u002Fplugins\u002Fagentdomains\u002Fskills\u002Fagentdomains\u002Fscripts\u002Fsetup.sh",[82,92,100,108,116,124],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":91},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":91},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":104,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":91},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":112,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":91},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":91},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":128,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":91},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]