[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MDPXHDQQ4D9QH2EZFANC51":3,"skill-same:01M6MDPXHDQQ4D9QH2EZFANC51":68},{"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":23,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":49,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M6MDPXHDQQ4D9QH2EZFANC51","supportpages",null,"Create or retry illustrated help articles with WTFM (by SupportPages.io) using its MCP connection and article writer. Use for WTFM or SupportPages.io article requests, including generating an unpublished draft for review.","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\u002FSupportPages-io\u002Fwtfm\u002Fscripts\u002Fskills\u002Fsupportpages\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"MCP","review","create","help","use","writer","draft","article","io","with","retry","connection","article writer","requests","for","2026-11-10 10:12:30",false,"---\nname: supportpages\ndescription: Create or retry illustrated help articles with WTFM (by SupportPages.io) using its MCP connection and article writer. Use for WTFM or SupportPages.io article requests, including generating an unpublished draft for review.\n---\n\n\u003C!-- Managed by SupportPages: article coordination v1 -->\n\n# WTFM articles\n\nUse the SupportPages.io MCP connection for the current project.\n\nFor inventory questions such as \"what support articles do we have?\", call\n`supportpages_list_articles` directly, without status or initialization first.\nWhen signed out or in local mode it reads the project's current local article\nfiles. Report those titles and paths without asking the user to sign in. An empty\nlocal list means no local articles were found, not that the hosted help centre is\nempty. Do not infer the inventory from Git status. Use `source: \"hosted\"` only\nwhen the user explicitly asks what is on SupportPages.io.\n\nFor article creation, check\n`supportpages_status`, finish initialization if required, and call\n`supportpages_prepare_article` before writing. Follow the returned readiness or\ncapacity instructions. Show the prepared editor link; a preview is not a finished\ndraft.\n\nWhen the prepared run has `prefer_background: true`, **delegate the writing task\nto a background subagent**. This skill explicitly requests delegation for that\narticle. Use the SupportPages.io writer and the returned Codex launch instructions,\nincluding the complete task brief, model settings and self-contained entrypoint.\nPass the complete task brief directly in the subagent tool's task\u002Fmessage argument\non launches and retries. Do not copy it into a temporary JSON file, create a\nhandoff script, or print it with a shell command. The existing entrypoint already\nloads the saved run; no parent-side file edit is needed to launch the writer.\nIf no custom-agent selector exists, use a named SupportPages.io subagent with the\nsupplied writer instructions. The writer runs the entrypoint before generating\nanything, uses the command wrapper, and runs the finish command after validation.\n\n**Prioritize completion and approvals over quiet operation.** After launch,\nrecord the actual execution mode and host task identity with\n`supportpages_update_run`. Show the editor link and say \"launched\" unless actual\nwriter startup is confirmed. Keep the main turn active and supervise the writer\nusing the host's agent wait\u002Fmessage facilities. Use bounded waits and concise\nprogress updates; do not end the turn merely because launch succeeded.\n\nThe writer may send milestone updates and must surface blockers immediately.\nWhen an operation needs permission and host policy permits it, the writer should\nrequest approval directly through the host's native approval mechanism, with the\nexact command and reason. A sandbox restriction is not an explicit user denial.\nDo not suppress approval prompts or route them only to an idle parent. Continue\nafter approval is granted. An explicit denial or a policy forbidding approval\nrequests stops that action; never bypass it or enable YOLO.\n\nIf a background writer cannot surface approvals, confirm it has stopped and\ncontinue the same article in the foreground using MCP recovery instructions and\nthe normal approval mechanism. Foreground execution retains the same permissions.\nIf the host cannot supervise a delegated task, use foreground execution. Keep\nthe MCP session alive; do not launch a separate agent CLI.\n\nInspect the writer's final result and saved run. A host \"Completed\" notification\ndoes not establish success. For a stopped writer that failed or is\n`permission_blocked` before generation finished, record `event: \"failed\"` and\n`stopped: true` with `supportpages_update_run`, then show the specific cause,\nrecovery and editor link. Do not mark a writer failed while awaiting approval.\nIf generation succeeded but delivery is pending or failed, recover with\n`supportpages_complete_article` without regenerating or marking the writer failed.\n\nThe main agent owns MCP calls. After successful writing, call\n`supportpages_complete_article` to confirm delivery, report the final editor link\nand follow its completion instructions. Leave the article unpublished until the\nuser affirmatively asks to publish that draft.\n\n**Local folders.** When `supportpages_status` or `supportpages_init` reports\n`local`, the folder has no help centre and needs no sign-in: articles are saved\nas Markdown with their screenshots. There is no capacity check, preview or editor\nlink. Show the saved markdown path returned by `supportpages_complete_article` as\nthe deliverable and never ask whether to publish automatically. Mention once\nthat running `wtfm publish` in the terminal hosts the saved articles.\n\nIf the user explicitly asks to host or publish saved local articles, call\n`supportpages_publish`. Follow its browser approval and help-centre selection\nsteps, then pass the selected article slugs. It uploads drafts and connects the\nfolder for future articles. Do not accept credentials in chat or approve sign-in\nfor the user. Making those drafts publicly visible is a separate action using\n`supportpages_publish_article` when authorized.\n\n**Hosted analysis and videos.** Use `supportpages_find_article_gaps`,\n`supportpages_suggest_sections`, `supportpages_recommend_articles` or\n`supportpages_create_video_walkthrough` for the requested action. These tools\ncheck the prerequisites and open required browser setup pages. When signed out,\nfirst explain that an account\u002Fdevice sign-in is needed; sign in or create an\naccount through the opened approval page. Do not begin with a repository invitation\nor send the user to the app homepage. Show the comparison code, and show the link\nas a fallback if `browser_opened` is false. Never approve browser consent.\n\nAfter the user completes a step, call `supportpages_setup_hosted` with the\nreturned `next_arguments`. Ask which help centre to use when `project_required`\nis returned (or use `supportpages_create_project` if the user wants a new one),\nthen pass its `project_id`. The next required device-consent or repository setup\npage opens automatically. Preserve the original request and `resume_arguments`\nthrough these steps; do not start local analysis, recording or unrelated jobs.\nOnce setup is available, retry `resume_tool` with `resume_arguments`. Walkthroughs\nrequire a completed hosted article: use `supportpages_list_articles` with\n`source: \"hosted\"` to select it. Do not restore deleted files or upload a local\narticle without the user's explicit instruction. Finished videos remain private\nuntil explicitly shared.\n\nHonor an explicit request to return immediately, explaining that approvals and\ncompletion may need another user turn on hosts that do not wake the parent.\nRetain the run ID and host task identity; reconcile the run on resumption.\n\nHonor an explicit foreground request. If delegation cannot run, distinguish a\nmissing host tool, an explicit session restriction, or the actual launch error;\ndo not infer that background execution is disabled merely because the user did\nnot separately request a subagent. Explain the specific limitation and use the\nsame prepared brief in the foreground. Stop any launched writer before switching\nmodes. Do not override host restrictions or launch a separate agent CLI.\n\nFor retries, follow the MCP recovery instructions and use\n`supportpages_retry_article` after stopping the old writer. If generation already\nfinished and delivery failed, recover delivery instead of regenerating.\n","\u003C!-- Managed by SupportPages: article coordination v1 -->\n\n# WTFM articles\n\nUse the SupportPages.io MCP connection for the current project.\n\nFor inventory questions such as \"what support articles do we have?\", call\n`supportpages_list_articles` directly, without status or initialization first.\nWhen signed out or in local mode it reads the project's current local article\nfiles. Report those titles and paths without asking the user to sign in. An empty\nlocal list means no local articles were found, not that the hosted help centre is\nempty. Do not infer the inventory from Git status. Use `source: \"hosted\"` only\nwhen the user explicitly asks what is on SupportPages.io.\n\nFor article creation, check\n`supportpages_status`, finish initialization if required, and call\n`supportpages_prepare_article` before writing. Follow the returned readiness or\ncapacity instructions. Show the prepared editor link; a preview is not a finished\ndraft.\n\nWhen the prepared run has `prefer_background: true`, **delegate the writing task\nto a background subagent**. This skill explicitly requests delegation for that\narticle. Use the SupportPages.io writer and the returned Codex launch instructions,\nincluding the complete task brief, model settings and self-contained entrypoint.\nPass the complete task brief directly in the subagent tool's task\u002Fmessage argument\non launches and retries. Do not copy it into a temporary JSON file, create a\nhandoff script, or print it with a shell command. The existing entrypoint already\nloads the saved run; no parent-side file edit is needed to launch the writer.\nIf no custom-agent selector exists, use a named SupportPages.io subagent with the\nsupplied writer instructions. The writer runs the entrypoint before generating\nanything, uses the command wrapper, and runs the finish command after validation.\n\n**Prioritize completion and approvals over quiet operation.** After launch,\nrecord the actual execution mode and host task identity with\n`supportpages_update_run`. Show the editor link and say \"launched\" unless actual\nwriter startup is confirmed. Keep the main turn active and supervise the writer\nusing the host's agent wait\u002Fmessage facilities. Use bounded waits and concise\nprogress updates; do not end the turn merely because launch succeeded.\n\nThe writer may send milestone updates and must surface blockers immediately.\nWhen an operation needs permission and host policy permits it, the writer should\nrequest approval directly through the host's native approval mechanism, with the\nexact command and reason. A sandbox restriction is not an explicit user denial.\nDo not suppress approval prompts or route them only to an idle parent. Continue\nafter approval is granted. An explicit denial or a policy forbidding approval\nrequests stops that action; never bypass it or enable YOLO.\n\nIf a background writer cannot surface approvals, confirm it has stopped and\ncontinue the same article in the foreground using MCP recovery instructions and\nthe normal approval mechanism. Foreground execution retains the same permissions.\nIf the host cannot supervise a delegated task, use foreground execution. Keep\nthe MCP session alive; do not launch a separate agent CLI.\n\nInspect the writer's final result and saved run. A host \"Completed\" notification\ndoes not establish success. For a stopped writer that failed or is\n`permission_blocked` before generation finished, record `event: \"failed\"` and\n`stopped: true` with `supportpages_update_run`, then show the specific cause,\nrecovery and editor link. Do not mark a writer failed while awaiting approval.\nIf generation succeeded but delivery is pending or failed, recover with\n`supportpages_complete_article` without regenerating or marking the writer failed.\n\nThe main agent owns MCP calls. After successful writing, call\n`supportpages_complete_article` to confirm delivery, report the final editor link\nand follow its completion instructions. Leave the article unpublished until the\nuser affirmatively asks to publish that draft.\n\n**Local folders.** When `supportpages_status` or `supportpages_init` reports\n`local`, the folder has no help centre and needs no sign-in: articles are saved\nas Markdown with their screenshots. There is no capacity check, preview or editor\nlink. Show the saved markdown path returned by `supportpages_complete_article` as\nthe deliverable and never ask whether to publish automatically. Mention once\nthat running `wtfm publish` in the terminal hosts the saved articles.\n\nIf the user explicitly asks to host or publish saved local articles, call\n`supportpages_publish`. Follow its browser approval and help-centre selection\nsteps, then pass the selected article slugs. It uploads drafts and connects the\nfolder for future articles. Do not accept credentials in chat or approve sign-in\nfor the user. Making those drafts publicly visible is a separate action using\n`supportpages_publish_article` when authorized.\n\n**Hosted analysis and videos.** Use `supportpages_find_article_gaps`,\n`supportpages_suggest_sections`, `supportpages_recommend_articles` or\n`supportpages_create_video_walkthrough` for the requested action. These tools\ncheck the prerequisites and open required browser setup pages. When signed out,\nfirst explain that an account\u002Fdevice sign-in is needed; sign in or create an\naccount through the opened approval page. Do not begin with a repository invitation\nor send the user to the app homepage. Show the comparison code, and show the link\nas a fallback if `browser_opened` is false. Never approve browser consent.\n\nAfter the user completes a step, call `supportpages_setup_hosted` with the\nreturned `next_arguments`. Ask which help centre to use when `project_required`\nis returned (or use `supportpages_create_project` if the user wants a new one),\nthen pass its `project_id`. The next required device-consent or repository setup\npage opens automatically. Preserve the original request and `resume_arguments`\nthrough these steps; do not start local analysis, recording or unrelated jobs.\nOnce setup is available, retry `resume_tool` with `resume_arguments`. Walkthroughs\nrequire a completed hosted article: use `supportpages_list_articles` with\n`source: \"hosted\"` to select it. Do not restore deleted files or upload a local\narticle without the user's explicit instruction. Finished videos remain private\nuntil explicitly shared.\n\nHonor an explicit request to return immediately, explaining that approvals and\ncompletion may need another user turn on hosts that do not wake the parent.\nRetain the run ID and host task identity; reconcile the run on resumption.\n\nHonor an explicit foreground request. If delegation cannot run, distinguish a\nmissing host tool, an explicit session restriction, or the actual launch error;\ndo not infer that background execution is disabled merely because the user did\nnot separately request a subagent. Explain the specific limitation and use the\nsame prepared brief in the foreground. Stop any launched writer before switching\nmodes. Do not override host restrictions or launch a separate agent CLI.\n\nFor retries, follow the MCP recovery instructions and use\n`supportpages_retry_article` after stopping the old writer. If generation already\nfinished and delivery failed, recover delivery instead of regenerating.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002FSupportPages-io\u002Fwtfm\u002Fscripts\u002Fskills\u002Fsupportpages",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":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill supportpages",{"tool":60,"command":61},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill supportpages",{"tool":63,"command":64},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill supportpages","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FSupportPages-io\u002Fwtfm\u002Fscripts\u002Fskills\u002Fsupportpages\u002FSKILL.md",true,[],[69,79,87,95,103,111],{"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":73,"licenseFileUrl":74,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":78},"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":73,"licenseFileUrl":83,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":78},"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":73,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":78},"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":73,"licenseFileUrl":99,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":78},"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":73,"licenseFileUrl":107,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":78},"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":73,"licenseFileUrl":115,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":78},"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",[],[]]