[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MMCEJEAQ87RH67Y5K46FS3":3,"skill-same:01M6MMCEJEAQ87RH67Y5K46FS3":80},{"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":28,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":59,"updatedAt":60,"install":61,"resources":73},"01M6MMCEJEAQ87RH67Y5K46FS3","runtype-admin",null,"Inspect, debug, or manage a live Runtype account through MCP or CLI; mutate only within the requested scope.","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-admin\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"admin","runtype admin","runtype","MCP","cli","debug","debugging","only","manage","task","live","scope","operation","true","inspect","2026-11-10 10:12:30",false,"---\nname: runtype-admin\ndescription: 'Inspect, debug, or manage a live Runtype account through MCP or CLI; mutate only within the requested scope.'\nuser-invocable: true\nargument-hint: '[live account operation or debugging task]'\n---\n\n# Runtype Admin\n\nUse this skill for live account operations. Every mutation changes the user's Runtype\nworkspace unless you run it against a disposable test account.\n\n## Before you start\n\nRuntype has two hosted MCP servers. Both accept browser sign-in on the first call, or a\nRuntype API key sent as `Authorization: Bearer \u003Ckey>`.\n\n| Server        | URL                                       | Tools                                                                                                                                                             |\n| ------------- | ----------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Standard MCP  | `https:\u002F\u002Fapi.runtype.com\u002Fv1\u002Fmcp\u002Fprotocol` | One named tool per operation, such as `get_me`, `list_agents`, and `list_runs`                                                                                    |\n| Code Mode MCP | `https:\u002F\u002Fcode.runtype.com\u002Fmcp`            | `search`, `execute`, `get_platform_documentation`, `search_documentation`, `get_build_instructions`, `generate_persona_embed_code`, `get_persona_theme_reference` |\n\nTo check which server is connected, look at the tool list. Code Mode lists only the seven\ntools in the table. Call `get_me` (on Code Mode, `execute` with\n`async (runtype) => runtype.getMe()`) to confirm the organization before you change anything.\n\n## Operating rules\n\n- Read freely once you have identified the resource ID with a `list_*` or `get_*` call.\n- Write to a single resource only when the user asked for that change. Follow\n  [Update resources safely](#update-resources-safely).\n- Use the `runtype-build-product` skill for builds that span several resources.\n- Get explicit confirmation before destructive, bulk, or hard-to-reverse actions. When you\n  ask, state what else is removed and offer the reversible alternative:\n  - `delete_product` removes the product's surfaces, surface items, and surface keys. It\n    keeps the flows and agents.\n  - `bulk_delete_records` and `delete_conversation` are irreversible.\n  - `delete_schedule` also deletes the schedule's run history. Use `pause_schedule` instead.\n  - `delete_messaging_conversation` deletes the transcript. Close the thread with\n    `update_messaging_conversation` instead.\n- Never claim a mutation succeeded unless the tool result confirms it.\n- Never show secret values. Use metadata only.\n\n## Standard MCP tools\n\nDiscover before you act:\n\n- Identity and inventory: `get_me`, `list_products`, `list_agents`, `list_flows`,\n  `list_tools`, `list_records`, `list_collections`, `list_skills`, `list_schedules`,\n  `list_secrets`, `list_conversations`, `list_model_configs`, `list_model_configs_grouped`,\n  `list_provider_keys`.\n- Debugging: `list_runs`, `trace_execution`, `trace_conversation`, `list_logs`,\n  `get_log_stats`, `list_schedule_runs`, `get_record_results`, `get_record_step_results`,\n  `get_record_costs`.\n- Validation: `validate_flow`, `validate_code`, `validate_product`,\n  `validate_product_flow`, `validate_product_agent`, `validate_product_surface`,\n  `validate_product_tool`.\n- Test runs: `execute_agent`, `run_flow`.\n- Evals and batches: `create_eval_suite`, `run_eval_suite`, `add_eval_cases`,\n  `add_eval_case_from_execution`, `submit_eval`, `list_eval_batches`, `get_eval_results`,\n  `compare_eval`, `compare_eval_record`, `analyze_eval_steps`, `submit_batch`,\n  `get_batch_status`, `get_batch_summary`, `cancel_batch`.\n- Versions and releases: `list_flow_versions`, `get_published_flow_version`,\n  `publish_flow_version`, `list_agent_versions`, `get_published_agent_version`,\n  `publish_agent_version`, `list_agent_aliases`, `rollback_agent_alias`,\n  `list_agent_deployments`.\n\nSurfaces belong to a product. List or change them with the product ID in hand.\n\nUse `list_model_configs` to see which models the account can run. `list_available_models`\nis the platform catalog: its `isEnabled` and `isDefault` fields are always null or false,\nso it cannot tell you whether a model is enabled.\n\nLarge inventories (`list_products`, `list_agents`, `list_flows`, `list_tools`,\n`list_records`, `list_collections`, `list_skills`, and `list_schedules`) return compact\nstring previews by default. Use that shape to find the resource, then call the matching\n`get_*` tool. Pass `view: \"full\"` only when you need complete strings across the whole\npage. `list_agents` also accepts `agent_type` (`runtype`, `external`, or\n`claude_managed`) when you know the type.\n\n## Code Mode MCP\n\nCall `search` first when you are unsure which method to use:\n\n\u003C!-- prettier-ignore -->\n```js\n(spec) => spec.categories\n```\n\nThen inspect one method:\n\n\u003C!-- prettier-ignore -->\n```js\n(spec) => spec.methods.updateAgent\n```\n\nCall `execute` and shape the result inside the function. Filter, project, and aggregate\nbefore you return data, so large responses do not fill the context:\n\n\u003C!-- prettier-ignore -->\n```js\nasync (runtype) => {\n  const { data } = await runtype.listProducts({ limit: 20 })\n  return data.map((p) => ({ id: p.id, name: p.name }))\n}\n```\n\nPass an arrow function with one parameter, such as `async (runtype) => ...`. Do not add a\nleading semicolon: the call fails with a syntax or validation error.\n\n## Use the CLI\n\nSign in with `runtype auth login`, or set `RUNTYPE_API_KEY`. The CLI calls either MCP\nserver directly:\n\n```bash\nruntype mcp tools\nruntype mcp call list_runs -F limit=20 --json\nruntype mcp call execute --server code -F code=@query.js --json\n```\n\nUse `-f key=value` for string values and `-F key=value` for JSON values. For log reads,\n`runtype logs list` and `runtype logs stats` take the same filters as `list_logs`, such as\n`--execution`, `--agent`, `--status`, and `--from`.\n\n## Debug a failed run\n\n1. Find the run with `list_runs`. Filter by `agent_id`, `flow_id`, `conversation_id`,\n   `surface_id`, `record_id`, or `batch_execution_id`, and pass `status: \"failed\"`.\n   Subagent and nested-flow runs fold under their parent in the unfiltered list. Pass\n   `include_children` to list them flat. `list_runs` covers the last 24 hours unless you pass `from`. For a schedule, start\n   with `list_schedule_runs`.\n2. Pull the trace for that run: `trace_execution`, or `trace_conversation` for a\n   multi-turn conversation.\n3. Use `list_logs` after the trace. Filter by execution ID, conversation ID, level, status,\n   or category. `list_logs` and `get_log_stats` search only the last 24 hours unless you\n   pass `from` or `minutes_ago`. An empty result says nothing about older runs.\n4. Inspect the referenced flow, agent, surface, tools, and secrets.\n5. Validate the corrected payload.\n6. Apply the smallest change. Re-run the same input with `execute_agent` or `run_flow`,\n   then capture the case with `add_eval_case_from_execution` or `add_eval_cases`.\n\nCommon causes:\n\n- A missing secret. Check with `check_secrets`.\n- A secret referenced in any form other than `{{secret:NAME}}`. `{{_internal.*}}`\n  variables are blocked at runtime.\n- An unresolved template variable.\n- A tool schema that does not match the call.\n- A wrong surface behavior setting.\n- A model timeout.\n\nTo stop a failing schedule, call `pause_schedule`. `run_schedule_now` counts toward the\ndaily execution limit.\n\n## Take over a messaging thread\n\nMessaging threads (Slack, iMessage, SMS, email, Telegram) are separate from assistant\nconversations. Their IDs start with `mconv_`, and `list_conversations` does not return\nthem.\n\n1. Find the thread with `list_messaging_conversations`. Filter by `surface_id`, `status`,\n   or `agent_mode`.\n2. Call `takeover_messaging_conversation`. If another operator took it over at the same\n   time, the call returns 409 and names that operator.\n3. Reply with `send_messaging_message`.\n4. Call `resume_messaging_conversation` to hand the thread back to the agent.\n\nA takeover lapses after the surface's idle timeout (24 hours by default) without an\noperator reply. To start a fresh conversation on an SMS or iMessage surface, close the\nthread with `update_messaging_conversation`. Do not delete it.\n\n## Update resources safely\n\n- Read the current configuration before you update it.\n- Keep fields that the request does not mention.\n- Validate before you update when a validator exists.\n- Follow pagination cursors on list tools. On `list_runs` and `list_logs`, stop paging when\n  `pagination.cursorReset` is true: the response is page one again, and its cursor loops\n  forever.\n- Use `get_platform_documentation` for exact contracts, such as schemas, routes, and the\n  tool catalog (`topic=\"platform-catalog\"`). Use `search_documentation` for how-to\n  questions. On Code Mode, use `search` to find method signatures.\n- Use `get_platform_documentation(topic=\"dashboard-links\")` when you give the user links.\n- Use `get_secret_intake_manifest`, `submit_secret_intake`, and `check_secrets` so that\n  credential values never pass through the conversation.\n- When `get_tool`, `create_tool`, or `update_tool` returns `connection.status:\n  \"needs_connection\"` for an OAuth2 MCP tool, give the user `connection.connectUrl` and ask\n  them to click Connect. Call `get_tool` again to confirm `\"connected\"`. Never ask for OAuth\n  tokens in chat.\n\n## Roll back a change\n\nBefore you change a flow or agent, note its published version with\n`get_published_flow_version` or `get_published_agent_version`.\n\n- Flow: find the earlier version with `list_flow_versions`, then publish it with\n  `publish_flow_version`.\n- Agent: publish the earlier version with `publish_agent_version`. If the agent uses\n  release aliases, call `rollback_agent_alias` and check the result with\n  `list_agent_deployments`.\n\nA rollback restores configuration only. It does not undo messages sent, records written,\nor other external effects.\n\nGet explicit confirmation before you:\n\n- Set `on_conflict` to overwrite a flow or agent that is managed as code. Publishing\n  rejects these by default.\n- Move the `live` alias. This needs the `AGENTS:DEPLOY:LIVE` permission and the alias's\n  current revision as `if_match`.\n\n## Handle permission errors\n\nOn `Permission denied` (HTTP 403), do not retry with guessed IDs. Tell the user which\npermission is missing, or request a new key:\n\n1. Call `request_api_key` with the narrowest `permissions` that cover the task and a\n   specific `reason`. Keep the returned `codeVerifier`. It cannot be recovered.\n2. Wait for a person to approve the request in the dashboard.\n3. Redeem it with `runtype api-keys claim \u003Crequest_id> --verifier \u003CcodeVerifier>`, or with\n   `claim_api_key` using the default `delivery: \"secret\"`.\n\nNever print the key into the conversation.\n\nFor deeper reference, load the `runtype` skill if it is installed. Prefer live MCP\ndocumentation over local files.\n","# Runtype Admin\n\nUse this skill for live account operations. Every mutation changes the user's Runtype\nworkspace unless you run it against a disposable test account.\n\n## Before you start\n\nRuntype has two hosted MCP servers. Both accept browser sign-in on the first call, or a\nRuntype API key sent as `Authorization: Bearer \u003Ckey>`.\n\n| Server        | URL                                       | Tools                                                                                                                                                             |\n| ------------- | ----------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Standard MCP  | `https:\u002F\u002Fapi.runtype.com\u002Fv1\u002Fmcp\u002Fprotocol` | One named tool per operation, such as `get_me`, `list_agents`, and `list_runs`                                                                                    |\n| Code Mode MCP | `https:\u002F\u002Fcode.runtype.com\u002Fmcp`            | `search`, `execute`, `get_platform_documentation`, `search_documentation`, `get_build_instructions`, `generate_persona_embed_code`, `get_persona_theme_reference` |\n\nTo check which server is connected, look at the tool list. Code Mode lists only the seven\ntools in the table. Call `get_me` (on Code Mode, `execute` with\n`async (runtype) => runtype.getMe()`) to confirm the organization before you change anything.\n\n## Operating rules\n\n- Read freely once you have identified the resource ID with a `list_*` or `get_*` call.\n- Write to a single resource only when the user asked for that change. Follow\n  [Update resources safely](#update-resources-safely).\n- Use the `runtype-build-product` skill for builds that span several resources.\n- Get explicit confirmation before destructive, bulk, or hard-to-reverse actions. When you\n  ask, state what else is removed and offer the reversible alternative:\n  - `delete_product` removes the product's surfaces, surface items, and surface keys. It\n    keeps the flows and agents.\n  - `bulk_delete_records` and `delete_conversation` are irreversible.\n  - `delete_schedule` also deletes the schedule's run history. Use `pause_schedule` instead.\n  - `delete_messaging_conversation` deletes the transcript. Close the thread with\n    `update_messaging_conversation` instead.\n- Never claim a mutation succeeded unless the tool result confirms it.\n- Never show secret values. Use metadata only.\n\n## Standard MCP tools\n\nDiscover before you act:\n\n- Identity and inventory: `get_me`, `list_products`, `list_agents`, `list_flows`,\n  `list_tools`, `list_records`, `list_collections`, `list_skills`, `list_schedules`,\n  `list_secrets`, `list_conversations`, `list_model_configs`, `list_model_configs_grouped`,\n  `list_provider_keys`.\n- Debugging: `list_runs`, `trace_execution`, `trace_conversation`, `list_logs`,\n  `get_log_stats`, `list_schedule_runs`, `get_record_results`, `get_record_step_results`,\n  `get_record_costs`.\n- Validation: `validate_flow`, `validate_code`, `validate_product`,\n  `validate_product_flow`, `validate_product_agent`, `validate_product_surface`,\n  `validate_product_tool`.\n- Test runs: `execute_agent`, `run_flow`.\n- Evals and batches: `create_eval_suite`, `run_eval_suite`, `add_eval_cases`,\n  `add_eval_case_from_execution`, `submit_eval`, `list_eval_batches`, `get_eval_results`,\n  `compare_eval`, `compare_eval_record`, `analyze_eval_steps`, `submit_batch`,\n  `get_batch_status`, `get_batch_summary`, `cancel_batch`.\n- Versions and releases: `list_flow_versions`, `get_published_flow_version`,\n  `publish_flow_version`, `list_agent_versions`, `get_published_agent_version`,\n  `publish_agent_version`, `list_agent_aliases`, `rollback_agent_alias`,\n  `list_agent_deployments`.\n\nSurfaces belong to a product. List or change them with the product ID in hand.\n\nUse `list_model_configs` to see which models the account can run. `list_available_models`\nis the platform catalog: its `isEnabled` and `isDefault` fields are always null or false,\nso it cannot tell you whether a model is enabled.\n\nLarge inventories (`list_products`, `list_agents`, `list_flows`, `list_tools`,\n`list_records`, `list_collections`, `list_skills`, and `list_schedules`) return compact\nstring previews by default. Use that shape to find the resource, then call the matching\n`get_*` tool. Pass `view: \"full\"` only when you need complete strings across the whole\npage. `list_agents` also accepts `agent_type` (`runtype`, `external`, or\n`claude_managed`) when you know the type.\n\n## Code Mode MCP\n\nCall `search` first when you are unsure which method to use:\n\n\u003C!-- prettier-ignore -->\n```js\n(spec) => spec.categories\n```\n\nThen inspect one method:\n\n\u003C!-- prettier-ignore -->\n```js\n(spec) => spec.methods.updateAgent\n```\n\nCall `execute` and shape the result inside the function. Filter, project, and aggregate\nbefore you return data, so large responses do not fill the context:\n\n\u003C!-- prettier-ignore -->\n```js\nasync (runtype) => {\n  const { data } = await runtype.listProducts({ limit: 20 })\n  return data.map((p) => ({ id: p.id, name: p.name }))\n}\n```\n\nPass an arrow function with one parameter, such as `async (runtype) => ...`. Do not add a\nleading semicolon: the call fails with a syntax or validation error.\n\n## Use the CLI\n\nSign in with `runtype auth login`, or set `RUNTYPE_API_KEY`. The CLI calls either MCP\nserver directly:\n\n```bash\nruntype mcp tools\nruntype mcp call list_runs -F limit=20 --json\nruntype mcp call execute --server code -F code=@query.js --json\n```\n\nUse `-f key=value` for string values and `-F key=value` for JSON values. For log reads,\n`runtype logs list` and `runtype logs stats` take the same filters as `list_logs`, such as\n`--execution`, `--agent`, `--status`, and `--from`.\n\n## Debug a failed run\n\n1. Find the run with `list_runs`. Filter by `agent_id`, `flow_id`, `conversation_id`,\n   `surface_id`, `record_id`, or `batch_execution_id`, and pass `status: \"failed\"`.\n   Subagent and nested-flow runs fold under their parent in the unfiltered list. Pass\n   `include_children` to list them flat. `list_runs` covers the last 24 hours unless you pass `from`. For a schedule, start\n   with `list_schedule_runs`.\n2. Pull the trace for that run: `trace_execution`, or `trace_conversation` for a\n   multi-turn conversation.\n3. Use `list_logs` after the trace. Filter by execution ID, conversation ID, level, status,\n   or category. `list_logs` and `get_log_stats` search only the last 24 hours unless you\n   pass `from` or `minutes_ago`. An empty result says nothing about older runs.\n4. Inspect the referenced flow, agent, surface, tools, and secrets.\n5. Validate the corrected payload.\n6. Apply the smallest change. Re-run the same input with `execute_agent` or `run_flow`,\n   then capture the case with `add_eval_case_from_execution` or `add_eval_cases`.\n\nCommon causes:\n\n- A missing secret. Check with `check_secrets`.\n- A secret referenced in any form other than `{{secret:NAME}}`. `{{_internal.*}}`\n  variables are blocked at runtime.\n- An unresolved template variable.\n- A tool schema that does not match the call.\n- A wrong surface behavior setting.\n- A model timeout.\n\nTo stop a failing schedule, call `pause_schedule`. `run_schedule_now` counts toward the\ndaily execution limit.\n\n## Take over a messaging thread\n\nMessaging threads (Slack, iMessage, SMS, email, Telegram) are separate from assistant\nconversations. Their IDs start with `mconv_`, and `list_conversations` does not return\nthem.\n\n1. Find the thread with `list_messaging_conversations`. Filter by `surface_id`, `status`,\n   or `agent_mode`.\n2. Call `takeover_messaging_conversation`. If another operator took it over at the same\n   time, the call returns 409 and names that operator.\n3. Reply with `send_messaging_message`.\n4. Call `resume_messaging_conversation` to hand the thread back to the agent.\n\nA takeover lapses after the surface's idle timeout (24 hours by default) without an\noperator reply. To start a fresh conversation on an SMS or iMessage surface, close the\nthread with `update_messaging_conversation`. Do not delete it.\n\n## Update resources safely\n\n- Read the current configuration before you update it.\n- Keep fields that the request does not mention.\n- Validate before you update when a validator exists.\n- Follow pagination cursors on list tools. On `list_runs` and `list_logs`, stop paging when\n  `pagination.cursorReset` is true: the response is page one again, and its cursor loops\n  forever.\n- Use `get_platform_documentation` for exact contracts, such as schemas, routes, and the\n  tool catalog (`topic=\"platform-catalog\"`). Use `search_documentation` for how-to\n  questions. On Code Mode, use `search` to find method signatures.\n- Use `get_platform_documentation(topic=\"dashboard-links\")` when you give the user links.\n- Use `get_secret_intake_manifest`, `submit_secret_intake`, and `check_secrets` so that\n  credential values never pass through the conversation.\n- When `get_tool`, `create_tool`, or `update_tool` returns `connection.status:\n  \"needs_connection\"` for an OAuth2 MCP tool, give the user `connection.connectUrl` and ask\n  them to click Connect. Call `get_tool` again to confirm `\"connected\"`. Never ask for OAuth\n  tokens in chat.\n\n## Roll back a change\n\nBefore you change a flow or agent, note its published version with\n`get_published_flow_version` or `get_published_agent_version`.\n\n- Flow: find the earlier version with `list_flow_versions`, then publish it with\n  `publish_flow_version`.\n- Agent: publish the earlier version with `publish_agent_version`. If the agent uses\n  release aliases, call `rollback_agent_alias` and check the result with\n  `list_agent_deployments`.\n\nA rollback restores configuration only. It does not undo messages sent, records written,\nor other external effects.\n\nGet explicit confirmation before you:\n\n- Set `on_conflict` to overwrite a flow or agent that is managed as code. Publishing\n  rejects these by default.\n- Move the `live` alias. This needs the `AGENTS:DEPLOY:LIVE` permission and the alias's\n  current revision as `if_match`.\n\n## Handle permission errors\n\nOn `Permission denied` (HTTP 403), do not retry with guessed IDs. Tell the user which\npermission is missing, or request a new key:\n\n1. Call `request_api_key` with the narrowest `permissions` that cover the task and a\n   specific `reason`. Keep the returned `codeVerifier`. It cannot be recovered.\n2. Wait for a person to approve the request in the dashboard.\n3. Redeem it with `runtype api-keys claim \u003Crequest_id> --verifier \u003CcodeVerifier>`, or with\n   `claim_api_key` using the default `delivery: \"secret\"`.\n\nNever print the key into the conversation.\n\nFor deeper reference, load the `runtype` skill if it is installed. Prefer live MCP\ndocumentation over local files.\n",{"name":5,"description":7,"argument-hint":49,"user-invocable":50},"[live account operation or debugging task]",true,"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fruntypelabs\u002Fskills\u002Fskills\u002Fruntype-admin",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":50},[63,66,69],{"tool":64,"command":65},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill runtype-admin",{"tool":67,"command":68},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill runtype-admin",{"tool":70,"command":71},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill runtype-admin","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fruntypelabs\u002Fskills\u002Fskills\u002Fruntype-admin\u002FSKILL.md",[74],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"agents\u002Fopenai.yaml","REFERENCE","参考文档",521,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fruntypelabs\u002Fskills\u002Fskills\u002Fruntype-admin\u002Fagents\u002Fopenai.yaml",[81,91,99,107,115,123],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":86,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":90},"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":95,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":90},"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":103,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":90},"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":111,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":90},"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":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":119,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":90},"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":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":127,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":90},"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",[],[]]