[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MMDFVEPBW7W92EZT91WXQV":3,"skill-same:01M6MMDFVEPBW7W92EZT91WXQV":105},{"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":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":49,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":52,"updatedAt":53,"install":54,"resources":66},"01M6MMDFVEPBW7W92EZT91WXQV","runtype",null,"Scope a Runtype project or set up platform access; route implementation to the relevant Runtype skill.","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\u002Fruntypelabs\u002Fskills\u002Fskills\u002Fruntype\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],"setup","SET","access","question","up","goal","implementation","route","project","platform","scope","relevant","true","2026-11-10 10:12:30",false,"---\nname: runtype\ndescription: 'Scope a Runtype project or set up platform access; route implementation to the relevant Runtype skill.'\nuser-invocable: true\nargument-hint: '[Runtype goal or setup question]'\n---\n\n# Runtype\n\nRuntype is a platform for shipping AI products: agents, flows, tools, surfaces, records,\nschedules, evals, and product templates. Use this skill as the entry point when the user\nasks about Runtype broadly or needs help connecting an agent to the platform.\n\nThis skill is a router. For implementation work, switch to the narrower skill that\nmatches the job.\n\n## Start with live context\n\n**If the Runtype MCP tools are available**, use them as the source of truth before you\ngive schema, catalog, or creation guidance:\n\n- `get_build_instructions(task=\"explain-capabilities\")` for scoping.\n- `get_build_instructions(task=\"build-product\")` before you build a product.\n- `get_build_instructions(task=\"generate-flow\")` before you build a flow.\n- `get_platform_documentation(topic=...)` for schemas, surface traits, tool catalogs,\n  SDK docs, Persona embed docs, dashboard links, and type definitions.\n- `search_documentation(query=...)` for how-to and conceptual questions. It returns an\n  answer with citations to doc pages.\n\n**If the MCP tools are not available**, check for existing authentication:\n\n- Run `runtype auth status` for a stored login or a pending signup.\n- If `RUNTYPE_API_KEY` is set, verify it with `runtype auth whoami --no-tty`. The\n  `status` command ignores environment credentials.\n- Reuse valid authentication. If a signup is pending, resume it with the `next` command\n  that `status` prints.\n- If `status` reports `unauthenticated` with a `requestedOrgId`, the directory is linked\n  to an organization with no stored login. Do not register a new account: have the user\n  log in to that organization privately (`runtype auth login --api-key \u003Ckey>`), or confirm\n  with them before `runtype unlink` if the link is stale.\n\nKeep working through the CLI while MCP is unavailable: `runtype mcp tools` lists the\nhosted tools and `runtype mcp call \u003Ctool>` runs one. Use MCP after its tools appear in\nyour session. A written configuration does not prove that the connection is active.\n\n**Only if the user asks for setup**, install or sign up:\n\n- **New account.** Run `runtype auth register --email \u003Cemail>`, then ask the user for the\n  6-digit code from their email and run `runtype auth verify \u003Ccode>`. Neither command\n  needs a TTY or a browser. Until the email is verified, the account is temporary, with\n  limited models and quota. If you registered without `--email`, send the code with\n  `runtype auth claim \u003Cemail>`.\n- **Existing account.** Have the user set `RUNTYPE_API_KEY` in the environment, or run\n  `runtype auth login --api-key \u003Ckey>` themselves. Credentials must not be pasted into the\n  conversation. Do not start the interactive browser login from a coding assistant.\n- **A narrower key.** Run\n  `runtype api-keys request --name \u003Cname> --scopes \u003Clist> --reason \u003Ctext>` with the\n  narrowest scopes the task needs. The user approves the request in the dashboard, and the\n  CLI writes the key to a local key file. From MCP, call `request_api_key`, keep the\n  `codeVerifier` it returns, and redeem the approved request with `claim_api_key`. Its\n  default delivery stores the key as a Runtype secret and returns only a `{{secret:KEY}}`\n  reference, so the key is never shown in the conversation.\n- **MCP.** Run `runtype install-mcp` for the current coding assistant, follow the action\n  or restart it reports, then confirm the account with `runtype auth whoami --no-tty`.\n\nFor installation or auth recovery, read the public setup script at\n`https:\u002F\u002Fruntype.ai\u002F.well-known\u002Fagent.md`. The raw auth protocol is at\n`https:\u002F\u002Fruntype.com\u002Fauth.md`.\n\n## Route to a focused skill\n\nUse this routing table instead of loading every Runtype detail into context:\n\n| User intent                                                                                                                                                                                        | Use                       |\n| -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------- |\n| Build, deploy, or validate a product with agents, flows, tools, surfaces, records, secrets, schedules, evals, or Agent Skills                                                                      | `runtype-build-product`   |\n| Inspect or modify a live account, debug failures, read logs\u002Ftraces, compare evals, manage resources                                                                                                | `runtype-admin`           |\n| Embed or theme a Persona chat widget, build fullscreen assistant layouts, use client tokens, or configure WebMCP\u002Fbrowser-side local tools                                                          | `runtype-persona`         |\n| Package a product as a distributable FPO template, handle pending secrets, validate import readiness                                                                                               | `runtype-templates`       |\n| Use the TypeScript\u002FPython SDK, CLI, Marathon, playbooks, sandboxes, or code-first stored\u002Fupsert\u002Fvirtual workflows                                                                                  | `runtype-sdk-marathon`    |\n| Connect an agent that runs outside Runtype (Flue, Cloudflare Agents SDK, Vercel AI SDK, LangChain, custom): send its traces to Runtype, let Runtype call it, capture and improve it from real runs | `runtype-external-agents` |\n| Design or review the tools an agent calls (names, schemas, results, errors, idempotency, secrets, bundling), on Runtype or any MCP or function-calling runtime                                     | `tool-design`             |\n\n## Platform concepts\n\n- Product: the container the user ships.\n- Agent: an LLM with a system prompt and tools. Start here for most interactive products.\n- Flow: a deterministic pipeline. Use for fixed sequences, indexing, batch work, and hot\n  paths that should be fast and cheap.\n- Tool: a typed callable, from built-ins, Orthogonal APIs, MCP servers, external HTTP,\n  custom code, local SDK tools, flows, or subagents.\n- Agent Skill: a versioned SKILL.md context bundle bound to a Runtype agent, which loads\n  it at run time through a `skill:\u003Cslug>` tool. It is a product feature, separate from\n  this coding-assistant skill. Read `get_platform_documentation(topic=\"agent-skills\")`.\n- Surface: where users or machines reach the product, such as `chat`, `api`, `mcp`,\n  `mcp_code`, `webhook`, `email`, `slack`, `schedule`, `sms`, `imessage`, `discord`,\n  `whatsapp`, `telegram`, `messaging`, `a2a`, and `hosted-page`. For the current list,\n  read `get_platform_documentation(topic=\"surface-types\")`.\n- Record: Runtype state and agent memory. Keep the source of truth for data that already\n  lives in another system there.\n- Eval: a saved set of test cases and graders that scores a flow or agent (an eval suite),\n  or a one-time batch that compares variants such as models or prompts. Surface evals in\n  the dashboard also cover routing and channel formatting end to end.\n- FPO template: the portable distribution format for a product.\n\nWhen a product has multiple capabilities on one conversational surface, Runtype can\nprovision an orchestrator that routes each incoming message to the right capability.\nSurfaces and capabilities are many-to-many.\n\n## Reference files\n\nThese local references are fallback context only. Prefer live MCP docs when available.\n\n- `references\u002Fprimitives.md` for the deeper platform model.\n- `references\u002Fmcp-tools.md` for MCP tool groups and selection.\n- `references\u002Fsurfaces.md` for surface traits and prompt implications.\n- `references\u002Fflow-steps.md` for flow step categories and common mistakes.\n- `references\u002Fpersona-widget.md` for Persona embed details.\n- `references\u002Ffpo-templates.md` for template packaging.\n- `references\u002Fworking-modes.md` for dashboard, MCP, REST, SDK, and on-prem tradeoffs.\n- `references\u002Frecipes.md` for worked product shapes.\n\n## Rules\n\n- Do not invent payload shapes. Fetch live docs or validate first.\n- Keep this router short. When you need more detail, fetch\n  `get_platform_documentation(topic=\"platform-catalog\")` or a focused topic, then read\n  the MCP resources that the docs point to.\n- Do not inline secret values. Use `{{secret:KEY}}` and pending-secret intake.\n- Do not copy a whole customer database into records. Store what Runtype needs to\n  correlate and remember.\n- Set an explicit, enabled model on every agent and prompt step. Do not rely on account\n  defaults.\n- Do not report success before you validate (`validate_flow` or `validate_product`) and\n  run a safe test (`execute_agent` or `run_flow`). Say which paths you did not test.\n- Do not use Runtype for generic one-off LLM chat unless the user wants to ship a\n  repeatable product or operational workflow.\n","# Runtype\n\nRuntype is a platform for shipping AI products: agents, flows, tools, surfaces, records,\nschedules, evals, and product templates. Use this skill as the entry point when the user\nasks about Runtype broadly or needs help connecting an agent to the platform.\n\nThis skill is a router. For implementation work, switch to the narrower skill that\nmatches the job.\n\n## Start with live context\n\n**If the Runtype MCP tools are available**, use them as the source of truth before you\ngive schema, catalog, or creation guidance:\n\n- `get_build_instructions(task=\"explain-capabilities\")` for scoping.\n- `get_build_instructions(task=\"build-product\")` before you build a product.\n- `get_build_instructions(task=\"generate-flow\")` before you build a flow.\n- `get_platform_documentation(topic=...)` for schemas, surface traits, tool catalogs,\n  SDK docs, Persona embed docs, dashboard links, and type definitions.\n- `search_documentation(query=...)` for how-to and conceptual questions. It returns an\n  answer with citations to doc pages.\n\n**If the MCP tools are not available**, check for existing authentication:\n\n- Run `runtype auth status` for a stored login or a pending signup.\n- If `RUNTYPE_API_KEY` is set, verify it with `runtype auth whoami --no-tty`. The\n  `status` command ignores environment credentials.\n- Reuse valid authentication. If a signup is pending, resume it with the `next` command\n  that `status` prints.\n- If `status` reports `unauthenticated` with a `requestedOrgId`, the directory is linked\n  to an organization with no stored login. Do not register a new account: have the user\n  log in to that organization privately (`runtype auth login --api-key \u003Ckey>`), or confirm\n  with them before `runtype unlink` if the link is stale.\n\nKeep working through the CLI while MCP is unavailable: `runtype mcp tools` lists the\nhosted tools and `runtype mcp call \u003Ctool>` runs one. Use MCP after its tools appear in\nyour session. A written configuration does not prove that the connection is active.\n\n**Only if the user asks for setup**, install or sign up:\n\n- **New account.** Run `runtype auth register --email \u003Cemail>`, then ask the user for the\n  6-digit code from their email and run `runtype auth verify \u003Ccode>`. Neither command\n  needs a TTY or a browser. Until the email is verified, the account is temporary, with\n  limited models and quota. If you registered without `--email`, send the code with\n  `runtype auth claim \u003Cemail>`.\n- **Existing account.** Have the user set `RUNTYPE_API_KEY` in the environment, or run\n  `runtype auth login --api-key \u003Ckey>` themselves. Credentials must not be pasted into the\n  conversation. Do not start the interactive browser login from a coding assistant.\n- **A narrower key.** Run\n  `runtype api-keys request --name \u003Cname> --scopes \u003Clist> --reason \u003Ctext>` with the\n  narrowest scopes the task needs. The user approves the request in the dashboard, and the\n  CLI writes the key to a local key file. From MCP, call `request_api_key`, keep the\n  `codeVerifier` it returns, and redeem the approved request with `claim_api_key`. Its\n  default delivery stores the key as a Runtype secret and returns only a `{{secret:KEY}}`\n  reference, so the key is never shown in the conversation.\n- **MCP.** Run `runtype install-mcp` for the current coding assistant, follow the action\n  or restart it reports, then confirm the account with `runtype auth whoami --no-tty`.\n\nFor installation or auth recovery, read the public setup script at\n`https:\u002F\u002Fruntype.ai\u002F.well-known\u002Fagent.md`. The raw auth protocol is at\n`https:\u002F\u002Fruntype.com\u002Fauth.md`.\n\n## Route to a focused skill\n\nUse this routing table instead of loading every Runtype detail into context:\n\n| User intent                                                                                                                                                                                        | Use                       |\n| -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------- |\n| Build, deploy, or validate a product with agents, flows, tools, surfaces, records, secrets, schedules, evals, or Agent Skills                                                                      | `runtype-build-product`   |\n| Inspect or modify a live account, debug failures, read logs\u002Ftraces, compare evals, manage resources                                                                                                | `runtype-admin`           |\n| Embed or theme a Persona chat widget, build fullscreen assistant layouts, use client tokens, or configure WebMCP\u002Fbrowser-side local tools                                                          | `runtype-persona`         |\n| Package a product as a distributable FPO template, handle pending secrets, validate import readiness                                                                                               | `runtype-templates`       |\n| Use the TypeScript\u002FPython SDK, CLI, Marathon, playbooks, sandboxes, or code-first stored\u002Fupsert\u002Fvirtual workflows                                                                                  | `runtype-sdk-marathon`    |\n| Connect an agent that runs outside Runtype (Flue, Cloudflare Agents SDK, Vercel AI SDK, LangChain, custom): send its traces to Runtype, let Runtype call it, capture and improve it from real runs | `runtype-external-agents` |\n| Design or review the tools an agent calls (names, schemas, results, errors, idempotency, secrets, bundling), on Runtype or any MCP or function-calling runtime                                     | `tool-design`             |\n\n## Platform concepts\n\n- Product: the container the user ships.\n- Agent: an LLM with a system prompt and tools. Start here for most interactive products.\n- Flow: a deterministic pipeline. Use for fixed sequences, indexing, batch work, and hot\n  paths that should be fast and cheap.\n- Tool: a typed callable, from built-ins, Orthogonal APIs, MCP servers, external HTTP,\n  custom code, local SDK tools, flows, or subagents.\n- Agent Skill: a versioned SKILL.md context bundle bound to a Runtype agent, which loads\n  it at run time through a `skill:\u003Cslug>` tool. It is a product feature, separate from\n  this coding-assistant skill. Read `get_platform_documentation(topic=\"agent-skills\")`.\n- Surface: where users or machines reach the product, such as `chat`, `api`, `mcp`,\n  `mcp_code`, `webhook`, `email`, `slack`, `schedule`, `sms`, `imessage`, `discord`,\n  `whatsapp`, `telegram`, `messaging`, `a2a`, and `hosted-page`. For the current list,\n  read `get_platform_documentation(topic=\"surface-types\")`.\n- Record: Runtype state and agent memory. Keep the source of truth for data that already\n  lives in another system there.\n- Eval: a saved set of test cases and graders that scores a flow or agent (an eval suite),\n  or a one-time batch that compares variants such as models or prompts. Surface evals in\n  the dashboard also cover routing and channel formatting end to end.\n- FPO template: the portable distribution format for a product.\n\nWhen a product has multiple capabilities on one conversational surface, Runtype can\nprovision an orchestrator that routes each incoming message to the right capability.\nSurfaces and capabilities are many-to-many.\n\n## Reference files\n\nThese local references are fallback context only. Prefer live MCP docs when available.\n\n- `references\u002Fprimitives.md` for the deeper platform model.\n- `references\u002Fmcp-tools.md` for MCP tool groups and selection.\n- `references\u002Fsurfaces.md` for surface traits and prompt implications.\n- `references\u002Fflow-steps.md` for flow step categories and common mistakes.\n- `references\u002Fpersona-widget.md` for Persona embed details.\n- `references\u002Ffpo-templates.md` for template packaging.\n- `references\u002Fworking-modes.md` for dashboard, MCP, REST, SDK, and on-prem tradeoffs.\n- `references\u002Frecipes.md` for worked product shapes.\n\n## Rules\n\n- Do not invent payload shapes. Fetch live docs or validate first.\n- Keep this router short. When you need more detail, fetch\n  `get_platform_documentation(topic=\"platform-catalog\")` or a focused topic, then read\n  the MCP resources that the docs point to.\n- Do not inline secret values. Use `{{secret:KEY}}` and pending-secret intake.\n- Do not copy a whole customer database into records. Store what Runtype needs to\n  correlate and remember.\n- Set an explicit, enabled model on every agent and prompt step. Do not rely on account\n  defaults.\n- Do not report success before you validate (`validate_flow` or `validate_product`) and\n  run a safe test (`execute_agent` or `run_flow`). Say which paths you did not test.\n- Do not use Runtype for generic one-off LLM chat unless the user wants to ship a\n  repeatable product or operational workflow.\n",{"name":5,"description":7,"argument-hint":42,"user-invocable":43},"[Runtype goal or setup question]",true,"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fruntypelabs\u002Fskills\u002Fskills\u002Fruntype",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":43},[56,59,62],{"tool":57,"command":58},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill runtype",{"tool":60,"command":61},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill runtype",{"tool":63,"command":64},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill runtype","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fruntypelabs\u002Fskills\u002Fskills\u002Fruntype\u002FSKILL.md",[67,73,77,81,85,89,93,97,101],{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"agents\u002Fopenai.yaml","REFERENCE","参考文档",512,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fruntypelabs\u002Fskills\u002Fskills\u002Fruntype\u002Fagents\u002Fopenai.yaml",{"path":74,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fflow-steps.md",6472,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fruntypelabs\u002Fskills\u002Fskills\u002Fruntype\u002Freferences\u002Fflow-steps.md",{"path":78,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Ffpo-templates.md",7968,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fruntypelabs\u002Fskills\u002Fskills\u002Fruntype\u002Freferences\u002Ffpo-templates.md",{"path":82,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fmcp-tools.md",33174,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fruntypelabs\u002Fskills\u002Fskills\u002Fruntype\u002Freferences\u002Fmcp-tools.md",{"path":86,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fpersona-widget.md",19540,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fruntypelabs\u002Fskills\u002Fskills\u002Fruntype\u002Freferences\u002Fpersona-widget.md",{"path":90,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fprimitives.md",22661,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fruntypelabs\u002Fskills\u002Fskills\u002Fruntype\u002Freferences\u002Fprimitives.md",{"path":94,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Frecipes.md",21921,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fruntypelabs\u002Fskills\u002Fskills\u002Fruntype\u002Freferences\u002Frecipes.md",{"path":98,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Fsurfaces.md",13539,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fruntypelabs\u002Fskills\u002Fskills\u002Fruntype\u002Freferences\u002Fsurfaces.md",{"path":102,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Fworking-modes.md",8431,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fruntypelabs\u002Fskills\u002Fskills\u002Fruntype\u002Freferences\u002Fworking-modes.md",[106,116,124,132,140,148],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":110,"licenseFileUrl":111,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":115},"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":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":110,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":115},"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":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":110,"licenseFileUrl":128,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":115},"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":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":110,"licenseFileUrl":136,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":115},"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":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":110,"licenseFileUrl":144,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":115},"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":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":110,"licenseFileUrl":152,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":115},"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",[],[]]