[{"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",1559,"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",474,"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.","2026-11-11 14:40:14",{"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",[81,89,96,103,128,153],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":88},"01M746ZWACVKMZ1BJXJZHYJSSX","migrate-to-e2e","Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for \u002Fmigrate-to-e2e, \"migrate our tests to e2e\", \"port these Maestro flows\", \"move our TesterArmy tests\", or when a project has an e2e config and an older suite still running.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fmigrate-to-e2e\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":88},"01M746ZPTAX1Q0FBKAB1CYND7E","e2e","Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fe2e\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":88},"01M746ZJN784HVHMDP9MQGCSGG","create-verification-skill","Generate a project-local verify-\u003Capp> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for \u002Fcreate-verification-skill, \"make a verification skill for this repo\", or when a project has no scripted way to prove UI behavior.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fcreate-verification-skill\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":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":44},"01M716A6ETNB9B1SQ3GXZC75VR","deja-search","deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-search\u002FSKILL.md",[],[110,111,112,113,114,115,116,117,118,119,35,120,121,122,123,124,125,33,126,127],"search","deja search","never","error","ready","memory","re","decide","fix","design","when","you","done","reviewer","io","change","merge","past",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":44},"01M716A3J2W5SENSE9VGMXB375","deja-reflect","End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-reflect\u002FSKILL.md",[],[135,136,137,124,138,139,140,141,142,143,144,145,146,147,115,148,149,150,151,152],"deja reflect","reflect","review","with","record","github","next","https","node","Rules","decisions","brew","remember","project rules","project","session","end","reflection",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":166,"publishedAt":44},"01M715T3RR4BAYSR57HPPTJ0PF","revid","Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftmakersas\u002Frevid-skills\u002Fskills\u002Frevid\u002FSKILL.md",[159,162,163],{"categoryNo":160,"categoryName":161,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":164,"categoryName":165,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",[155,167,168,169,170,171,172,149,173,116,174,175,32,176,120,177,178,179,180,181],"URL","Video","short-form","standalone","PDF","viral","tiktok","short","social","song","image","mcp server","schedule","api","publish"]