[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MD0TBTYQ41KV2X102GAGJ9":3,"skill-same:01M6MD0TBTYQ41KV2X102GAGJ9":74},{"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":18,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":50,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M6MD0TBTYQ41KV2X102GAGJ9","cy-orquestrate-issue",null,"Orchestrate GitHub bug resolution through a new CompozyOS managed worktree and Claude Opus 5.5 Medium session per issue. Investigate reported bugs, create missing issues, and dispatch an executor responsible for a detailed PR, green CI, and all CodeRabbit and Greptile feedback. Use when asked to delegate issue resolution; excludes spec task graphs, direct implementation, and review-only work on an existing PR.","compozy\u002Fcompozy","compozy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F205107042?v=4","01M6JWVTXX4DX38AWZ7SPFEKEV","CompozyOS","01M6JWVV2P34GM1PDATVB2EV05",2871,"MIT","https:\u002F\u002Fgithub.com\u002Fcompozy\u002Fcompozy\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcy-orquestrate-issue\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"issue","cy orquestrate issue","new","task","Existing","use","only","missing","managed","issues","ci","delegate","session","work on","for","executor","bugs","green","pr","feedback","orchestrate","2026-11-10 10:12:30",false,"---\nname: cy-orquestrate-issue\ndescription: Orchestrate GitHub bug resolution through a new CompozyOS managed worktree and Claude Opus 5.5 Medium session per issue. Investigate reported bugs, create missing issues, and dispatch an executor responsible for a detailed PR, green CI, and all CodeRabbit and Greptile feedback. Use when asked to delegate issue resolution; excludes spec task graphs, direct implementation, and review-only work on an existing PR.\n---\n\n# Orchestrate Issue Resolution\n\nThe orchestrator investigates and dispatches; a dedicated CompozyOS session implements each issue\nthrough PR delivery.\n\n## Contract and inputs\n\n- Accept issue numbers\u002FURLs or a bug report with screenshots, logs, or reproduction steps. Resolve\n  the repository from the workspace remote; ask only if the target remains ambiguous.\n- Default executor: agent `general`, provider `claude`, model `claude-opus-5-5`, reasoning effort\n  `medium`. Explicit user overrides win. Verify the effective runtime; never silently substitute a\n  model.\n- Create one **new managed worktree and new logical session per issue**. Follow-ups for that issue\n  go to its recorded session. Never repurpose an unrelated active session.\n- An invocation to resolve issues authorizes the scoped issue, branch, push, PR, review replies,\n  and review-remediation work. It does not authorize merge, destructive Git, deleting worktrees,\n  installing reviewers, or changing the user's host runtime. Existing session authorization wins.\n- Default orchestration ends after verified dispatch, with the executor responsible for the full\n  delivery contract. If asked to accompany delivery, supervise until that contract is satisfied.\n  A launch report must say **in progress**, never that the issue is resolved.\n\n## 1. Load the runtime contract\n\nUse the active harness to resolve `compozy__skill_view`. Load the Compozy skill and the full\nreferences selected by its router for tools, worktrees, sessions, and orchestration:\n`references\u002Ftools-and-skills.md`, `references\u002Fnative-tools.md`, `references\u002Fworktrees.md`,\n`references\u002Fruntime-operations.md`, and `references\u002Ftasks-and-orchestration.md`. Reuse complete\ncurrent reads from this session. Follow source-qualified `command_id` and retained-result\ncontinuation instructions when supplied.\n\nDiscover capabilities with `compozy__tool_search` and inspect live descriptors with\n`compozy__tool_info`. The canonical IDs below are discovery keys, not harness invocation names.\nUse the returned references and current schemas. A denied tool\u002Fskill read is not permission to\nbypass policy through CLI or filesystem access.\n\n## 2. Investigate and establish the issue\n\nRead workspace instructions, Git status, the issue and its comments, and the affected code paths.\nReuse prior evidence; perform focused read-only investigation before dispatching a new bug report.\nFor runtime incidents, compare public daemon state and relevant logs with the UI report. Separate\nconfirmed causes, hypotheses, and unverified observations. Do not mutate user sessions to reproduce.\nUse bounded independent explorers only when authorized and useful.\n\nFor a report without an issue, check for duplicates, then create an English GitHub issue containing\nreproduction, actual\u002Fexpected behavior, evidence and code pointers, acceptance criteria, and relevant\nQA\u002Fcompatibility impact, with its type set when it is created: `gh issue create --type \u003CBug|Feature|Task>`,\nor `gh issue edit \u003Cn> --type \u003CT>` immediately after. Verify publication. Sanitize private paths,\ninternal runtime identifiers, credentials, and unrelated log content. Use structured arguments or a body file for multiline text.\nFor an existing issue, reuse it; do not create a duplicate. A closed issue or existing PR requires\nchecking whether work remains before creating another implementation.\n\nSeveral symptoms may belong to one evidenced defect. Keep that scope together; independent issues\nget separate worktrees. Include later user corrections in the same issue's briefing. Avoid a broad\nspec, audit, or unrelated cleanup unless requested.\n\n## 3. Create and bind the executor\n\nRefresh the remote base without changing the root checkout. Use the repository's target branch,\nnormally `origin\u002Fmain`. Keep a compact mapping of issue URL, base SHA, worktree ID\u002Fpath\u002Fbranch,\nsession ID, prompt idempotency key, and eventual PR URL in the orchestration context. Preserve that\nmapping in a handoff when needed; daemon state remains authoritative.\n\nPerform these dependent operations in order:\n\n1. `compozy__worktree_create`: workspace, base ref, unique name such as\n   `issue-\u003Cnumber>-\u003Cslug>`, branch such as `fix\u002Fissue-\u003Cnumber>-\u003Cslug>`.\n2. `compozy__worktree_inspect`: confirm creation reached `ready`, and retain the returned path\u002FID.\n3. `compozy__session_create`: selected agent, descriptive issue name, exact workspace\u002Fworktree ID.\n4. Load [assets\u002Fexecutor-prompt.md](assets\u002Fexecutor-prompt.md), fill every field (including\n   `\u003CORCHESTRATOR_SESSION_ID>`, your own session ID, so the executor can report back), and send the\n   full briefing with the native `compozy__session_prompt` tool, never `compozy session prompt`\n   (the CLI carries no sender identity unless you pass `--from-session auto` or `--from-session \u003Cid>`). Set runtime explicitly on this first prompt:\n   `{\"provider\":\"claude\",\"model\":\"claude-opus-5-5\",\"reasoning_effort\":\"medium\"}` unless overridden.\n   Use unique stable `message_id` and `idempotency_key`; use `wait:false` for background dispatch.\n5. `compozy__session_status`: confirm the prompt is accepted, runtime ready with the requested\n   effective selection, and the session bound to the intended worktree. The executor verifies cwd\n   and branch before editing. Distinguish an accepted prompt from a turn that is executing.\n\nDo not activate a Compozy Goal for the executor; the briefing and its delivery contract drive the\nwork.\n\nIf creation or prompt admission has an ambiguous result, reconcile the worktree\u002Fsession catalog\nagainst the recorded mapping before retrying. Replay the same prompt idempotency key where supported;\ndo not blindly create duplicates. Respect session limits; never change the session type to bypass a\ndenial. This flow uses logical worktree-bound sessions, not the spec-task spawn\u002Flease workflow.\n\nIf a required operation fails, complete independent work and report the precise blocker. Do not\nclaim a pending worktree, unbound runtime, or merely accepted prompt is executing successfully.\n\n## 4. Follow-ups and delivery\n\nSend additional evidence only to the same issue's recorded executor, with native\n`compozy__session_prompt`. Executors usually sit in one long turn, so a `queue` message may wait an\nhour: use `mode: \"steer\"` for anything the executor must see soon, and `queue` only for material it\ncan read at its next boundary (the daemon also injects long-waiting queued messages after\n`session.messaging.queue_promote_after`). Check the reported mode and `disposition`. Answer executor\nmessages with `in_reply_to` set to their `message_id`; use `supersede: true` when a new instruction\nreplaces an unread one. Executors report milestones only, so do not poll them for status and do not\nanswer pure acknowledgments. Consolidate cross-surface impact notes from the PR bodies yourself;\nexecutors must not co-edit shared files such as `docs\u002F_memory\u002Fchange-impact.md`. Do not assume a\nslash-shaped string in an agent prompt activates a skill; require the native operation.\n\nThe executor prompt owns implementation, validation, PR description, and the complete review cycle.\nDo not duplicate its checks or routinely interrupt it for status. If supervising, investigate\nfinished CI failures while other jobs run and inspect new review evidence after relevant pushes.\nAn idle turn alone is neither completion nor a blocker; if the executor stops before delivery, steer\nit with the remaining contract. Do not repair the host or clear runtime records as a shortcut.\n\nReport the issue links, worktree\u002Fbranch and session mapping, verified runtime state, and actual\nlaunch or delivery status concisely. Do not stop the executor or remove its worktree after dispatch.\nAt delivery, verify the PR head, required checks, both reviewers' completed coverage, all finding\ndispositions, and current description. Missing\u002Fred\u002Fpending CI or missing reviewer evidence means\ndelivery is still in progress or externally blocked. No merge unless separately requested.\n","# Orchestrate Issue Resolution\n\nThe orchestrator investigates and dispatches; a dedicated CompozyOS session implements each issue\nthrough PR delivery.\n\n## Contract and inputs\n\n- Accept issue numbers\u002FURLs or a bug report with screenshots, logs, or reproduction steps. Resolve\n  the repository from the workspace remote; ask only if the target remains ambiguous.\n- Default executor: agent `general`, provider `claude`, model `claude-opus-5-5`, reasoning effort\n  `medium`. Explicit user overrides win. Verify the effective runtime; never silently substitute a\n  model.\n- Create one **new managed worktree and new logical session per issue**. Follow-ups for that issue\n  go to its recorded session. Never repurpose an unrelated active session.\n- An invocation to resolve issues authorizes the scoped issue, branch, push, PR, review replies,\n  and review-remediation work. It does not authorize merge, destructive Git, deleting worktrees,\n  installing reviewers, or changing the user's host runtime. Existing session authorization wins.\n- Default orchestration ends after verified dispatch, with the executor responsible for the full\n  delivery contract. If asked to accompany delivery, supervise until that contract is satisfied.\n  A launch report must say **in progress**, never that the issue is resolved.\n\n## 1. Load the runtime contract\n\nUse the active harness to resolve `compozy__skill_view`. Load the Compozy skill and the full\nreferences selected by its router for tools, worktrees, sessions, and orchestration:\n`references\u002Ftools-and-skills.md`, `references\u002Fnative-tools.md`, `references\u002Fworktrees.md`,\n`references\u002Fruntime-operations.md`, and `references\u002Ftasks-and-orchestration.md`. Reuse complete\ncurrent reads from this session. Follow source-qualified `command_id` and retained-result\ncontinuation instructions when supplied.\n\nDiscover capabilities with `compozy__tool_search` and inspect live descriptors with\n`compozy__tool_info`. The canonical IDs below are discovery keys, not harness invocation names.\nUse the returned references and current schemas. A denied tool\u002Fskill read is not permission to\nbypass policy through CLI or filesystem access.\n\n## 2. Investigate and establish the issue\n\nRead workspace instructions, Git status, the issue and its comments, and the affected code paths.\nReuse prior evidence; perform focused read-only investigation before dispatching a new bug report.\nFor runtime incidents, compare public daemon state and relevant logs with the UI report. Separate\nconfirmed causes, hypotheses, and unverified observations. Do not mutate user sessions to reproduce.\nUse bounded independent explorers only when authorized and useful.\n\nFor a report without an issue, check for duplicates, then create an English GitHub issue containing\nreproduction, actual\u002Fexpected behavior, evidence and code pointers, acceptance criteria, and relevant\nQA\u002Fcompatibility impact, with its type set when it is created: `gh issue create --type \u003CBug|Feature|Task>`,\nor `gh issue edit \u003Cn> --type \u003CT>` immediately after. Verify publication. Sanitize private paths,\ninternal runtime identifiers, credentials, and unrelated log content. Use structured arguments or a body file for multiline text.\nFor an existing issue, reuse it; do not create a duplicate. A closed issue or existing PR requires\nchecking whether work remains before creating another implementation.\n\nSeveral symptoms may belong to one evidenced defect. Keep that scope together; independent issues\nget separate worktrees. Include later user corrections in the same issue's briefing. Avoid a broad\nspec, audit, or unrelated cleanup unless requested.\n\n## 3. Create and bind the executor\n\nRefresh the remote base without changing the root checkout. Use the repository's target branch,\nnormally `origin\u002Fmain`. Keep a compact mapping of issue URL, base SHA, worktree ID\u002Fpath\u002Fbranch,\nsession ID, prompt idempotency key, and eventual PR URL in the orchestration context. Preserve that\nmapping in a handoff when needed; daemon state remains authoritative.\n\nPerform these dependent operations in order:\n\n1. `compozy__worktree_create`: workspace, base ref, unique name such as\n   `issue-\u003Cnumber>-\u003Cslug>`, branch such as `fix\u002Fissue-\u003Cnumber>-\u003Cslug>`.\n2. `compozy__worktree_inspect`: confirm creation reached `ready`, and retain the returned path\u002FID.\n3. `compozy__session_create`: selected agent, descriptive issue name, exact workspace\u002Fworktree ID.\n4. Load [assets\u002Fexecutor-prompt.md](assets\u002Fexecutor-prompt.md), fill every field (including\n   `\u003CORCHESTRATOR_SESSION_ID>`, your own session ID, so the executor can report back), and send the\n   full briefing with the native `compozy__session_prompt` tool, never `compozy session prompt`\n   (the CLI carries no sender identity unless you pass `--from-session auto` or `--from-session \u003Cid>`). Set runtime explicitly on this first prompt:\n   `{\"provider\":\"claude\",\"model\":\"claude-opus-5-5\",\"reasoning_effort\":\"medium\"}` unless overridden.\n   Use unique stable `message_id` and `idempotency_key`; use `wait:false` for background dispatch.\n5. `compozy__session_status`: confirm the prompt is accepted, runtime ready with the requested\n   effective selection, and the session bound to the intended worktree. The executor verifies cwd\n   and branch before editing. Distinguish an accepted prompt from a turn that is executing.\n\nDo not activate a Compozy Goal for the executor; the briefing and its delivery contract drive the\nwork.\n\nIf creation or prompt admission has an ambiguous result, reconcile the worktree\u002Fsession catalog\nagainst the recorded mapping before retrying. Replay the same prompt idempotency key where supported;\ndo not blindly create duplicates. Respect session limits; never change the session type to bypass a\ndenial. This flow uses logical worktree-bound sessions, not the spec-task spawn\u002Flease workflow.\n\nIf a required operation fails, complete independent work and report the precise blocker. Do not\nclaim a pending worktree, unbound runtime, or merely accepted prompt is executing successfully.\n\n## 4. Follow-ups and delivery\n\nSend additional evidence only to the same issue's recorded executor, with native\n`compozy__session_prompt`. Executors usually sit in one long turn, so a `queue` message may wait an\nhour: use `mode: \"steer\"` for anything the executor must see soon, and `queue` only for material it\ncan read at its next boundary (the daemon also injects long-waiting queued messages after\n`session.messaging.queue_promote_after`). Check the reported mode and `disposition`. Answer executor\nmessages with `in_reply_to` set to their `message_id`; use `supersede: true` when a new instruction\nreplaces an unread one. Executors report milestones only, so do not poll them for status and do not\nanswer pure acknowledgments. Consolidate cross-surface impact notes from the PR bodies yourself;\nexecutors must not co-edit shared files such as `docs\u002F_memory\u002Fchange-impact.md`. Do not assume a\nslash-shaped string in an agent prompt activates a skill; require the native operation.\n\nThe executor prompt owns implementation, validation, PR description, and the complete review cycle.\nDo not duplicate its checks or routinely interrupt it for status. If supervising, investigate\nfinished CI failures while other jobs run and inspect new review evidence after relevant pushes.\nAn idle turn alone is neither completion nor a blocker; if the executor stops before delivery, steer\nit with the remaining contract. Do not repair the host or clear runtime records as a shortcut.\n\nReport the issue links, worktree\u002Fbranch and session mapping, verified runtime state, and actual\nlaunch or delivery status concisely. Do not stop the executor or remove its worktree after dispatch.\nAt delivery, verify the PR head, required checks, both reviewers' completed coverage, all finding\ndispositions, and current description. Missing\u002Fred\u002Fpending CI or missing reviewer evidence means\ndelivery is still in progress or externally blocked. No merge unless separately requested.\n",{"name":5,"description":7},"main","766345807802b7056b0fc8a026c84de70f23ea84",".agents\u002Fskills\u002Fcy-orquestrate-issue",187,"https:\u002F\u002Fgithub.com\u002Fcompozy\u002Fcompozy","https:\u002F\u002Fcompozy.com","https:\u002F\u002Fgithub.com\u002Fcompozy","An OS for AI agents","2026-11-15 03:55:11",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add compozy\u002Fcompozy --skill cy-orquestrate-issue",{"tool":60,"command":61},"bunx","bunx skills add compozy\u002Fcompozy --skill cy-orquestrate-issue",{"tool":63,"command":64},"pnpm","pnpm dlx skills add compozy\u002Fcompozy --skill cy-orquestrate-issue","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcompozy\u002Fcompozy\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcy-orquestrate-issue\u002FSKILL.md",true,[68],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"assets\u002Fexecutor-prompt.md","ASSET","资产文件",8441,"https:\u002F\u002Fgithub.com\u002Fcompozy\u002Fcompozy\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcy-orquestrate-issue\u002Fassets\u002Fexecutor-prompt.md",[75,107,132,155,166,178],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":80,"sourceHtmlUrl":81,"categories":82,"keywords":88,"publishedAt":40},"01M6MD7W312X49RNEJRKKVKTTD","security-review","Security code review for vulnerabilities. Use when asked to \"security review\", \"find vulnerabilities\", \"check for security issues\", \"audit security\", \"OWASP review\", or review code for injection, XSS, authentication, authorization, cryptography issues. Provides systematic review with confidence-based reporting.","CC-BY-SA-4.0","https:\u002F\u002Fgithub.com\u002Fcompozy\u002Fcompozy\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsecurity-review\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fcompozy\u002Fcompozy\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsecurity-review\u002FSKILL.md",[83],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",[89,90,91,92,93,94,28,95,96,97,98,99,100,101,102,103,104,33,24,22,105,106],"security","security review","review","injection","authentication","code review","Bash","code","xss","audit","systematic","read","reporting","cryptography","owasp","systematic review","when","audit security",{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":118,"publishedAt":40},"01M6MD5K93G1GP8VA56V2FEPZV","lesson-learned","Extract evidence-backed engineering lessons from recent changes or incidents. Use for requested reflection, lesson updates, or retiring an obsolete workflow rule.","https:\u002F\u002Fgithub.com\u002Fcompozy\u002Fcompozy\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flesson-learned\u002FSKILL.md",[113],{"categoryNo":114,"categoryName":115,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000039","教师与教育","PROFESSION","适用职业",[119,120,121,33,122,123,124,125,126,127,128,129,24,130,131],"learned","lesson learned","lesson","changes","evidence","incidents","workflow","engineering","updates","extract","rule","lessons","reflection",{"skillNo":133,"name":9,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":40},"01M6MDPNH3J60VRCGTPHVTHZR8","Operate CompozyOS. Use when working with CompozyOS sessions, agents, native tools, skills, tasks, Loops, Goals, Terminal, desktops and windows, automation, extensions, or configuration. Don't use for unrelated projects.","https:\u002F\u002Fgithub.com\u002Fcompozy\u002Fcompozy\u002Fblob\u002Fmain\u002Fskills\u002Fcompozy\u002FSKILL.md",[],[9,138,139,140,141,33,142,143,24,144,145,146,147,148,149,150,151,152,153,154,105],"sessions","windows","projects","operate","runtime","true","automation","tasks","extensions","with","loops","unrelated","goals","native","terminal","configuration","Tools",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":40},"01M6MDPHKNPQHJ1TF21E1HSFNF","remotion-upgrade","Upgrade Remotion, and related packages","https:\u002F\u002Fgithub.com\u002Fcompozy\u002Fcompozy\u002Fblob\u002Fmain\u002Fpackages\u002Flaunch-video\u002F.agents\u002Fskills\u002Fremotion-upgrade\u002FSKILL.md",[],[162,163,164,165],"remotion upgrade","upgrade","Remotion","packages",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":172,"publishedAt":40},"01M6MDPFT91ZWC7Z09MRNZPAJG","remotion-studio","Preview a Remotion video","https:\u002F\u002Fgithub.com\u002Fcompozy\u002Fcompozy\u002Fblob\u002Fmain\u002Fpackages\u002Flaunch-video\u002F.agents\u002Fskills\u002Fremotion-studio\u002FSKILL.md",[],[173,174,164,175,176,177],"studio","remotion studio","Video","preview","remotion video",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":184,"publishedAt":40},"01M6MDPD5XDZPYB5NAZGKMPXWC","remotion-saas","Build an app with Remotion","https:\u002F\u002Fgithub.com\u002Fcompozy\u002Fcompozy\u002Fblob\u002Fmain\u002Fpackages\u002Flaunch-video\u002F.agents\u002Fskills\u002Fremotion-saas\u002FSKILL.md",[],[185,186,164,147,187,188],"saas","remotion saas","app","build"]