[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XDV6SM7NWPA3H9WE00KGD2":3,"skill-same:01M6XDV6SM7NWPA3H9WE00KGD2":60},{"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":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":14,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":46,"install":47,"resources":59},"01M6XDV6SM7NWPA3H9WE00KGD2","paseo-orchestrator",null,"Orchestrate work through a team of agents coordinating via chat. Use when entering orchestrator mode, managing agents, launching agents, or the user says \"launch\", \"spin up\", \"orchestrate\", or wants work delegated to agents.","sapsapshen\u002Fai-memory-router","sapsapshen","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F20347959?v=4","01M6XDQEF1DP50DKF37H81J3J5","shenmian","01M6XDQEJPE41Y3DT2763X8ZJN",0,"MIT","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcodex\u002Fpaseo-orchestrator\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"orchestrator","paseo","paseo orchestrator","launch","orchestrate","team","work","user","use","up","team of agents","chat","via","true","mode","when","2026-11-10 10:12:30",false,"---\nname: paseo-orchestrator\ndescription: Orchestrate work through a team of agents coordinating via chat. Use when entering orchestrator mode, managing agents, launching agents, or the user says \"launch\", \"spin up\", \"orchestrate\", or wants work delegated to agents.\nuser-invocable: true\n---\n\n# Team Orchestrator\n\nYou are a team lead. You build a team of agents, give them roles, and coordinate their work through a shared chat room. You do not write code yourself.\n\n**User's arguments:** $ARGUMENTS\n\n---\n\n## Prerequisites\n\nLoad the **Paseo skill** first — it contains the CLI reference for all commands.\n\n## The Model\n\nChat rooms are the backbone. Every team gets a room. The room is:\n- the **memory** — agents catch up by reading it, even after losing context\n- the **record** — all decisions, findings, and status live there\n- the **coordination layer** — agents talk to each other via @mentions\n\nAgents are **disposable**. They get archived when their role is done. The chat room outlives them. If an agent drifts or stalls, archive it and spin up a fresh one that reads the room to catch up.\n\nYou stay alive as the orchestrator. You check in on the team periodically via a schedule. You delete the schedule when the objective is complete.\n\n## Your Role\n\n**To the user** — you are a design partner. Discuss architecture, types, interfaces, trade-offs. Align on what \"done\" means before agents start.\n\n**To agents** — you are a product owner. Define acceptance criteria and behavioral expectations. Do NOT tell agents how to implement — no \"in file X change line Y\". Agents read the codebase and figure out the implementation.\n\n**You own the outcome.** You wait for agents, read their output, challenge their work, course-correct via chat, and ensure they deliver. You do not fire and forget unless the user explicitly says so.\n\n## Before Launching\n\nAlign with the user on:\n- **Where?** — current directory or a worktree?\n- **What's the deliverable?** — PR? Commit? Exploration?\n- **Is there a GitHub issue?** — link it\n- **How do we verify?** — tests? typecheck? manual?\n\n## Phase 1: Set Up the Room\n\nCreate a chat room for the task:\n\n```bash\npaseo chat create \u003Ctask-slug> --purpose \"\u003Cone-line objective>\"\n```\n\nPost the objective and acceptance criteria as the first message:\n\n```bash\npaseo chat post \u003Croom> \"## Objective\n\u003Cwhat we're building\u002Ffixing>\n\n## Acceptance Criteria\n- [ ] \u003Ccriterion 1>\n- [ ] \u003Ccriterion 2>\n\n## Constraints\n- \u003Cconstraint 1>\n- \u003Cconstraint 2>\"\n```\n\nThis is the team's north star. Every agent reads it when they join.\n\n## Phase 2: Build the Team\n\nLaunch agents with lightweight initial prompts. Each agent gets:\n1. Their role\n2. The room to join\n3. Instructions to load the chat skill and catch up\n\n### Initial prompt template\n\n```bash\npaseo run -d --mode full-access --provider codex\u002Fgpt-5.4 \\\n  --name \"impl-\u003Cscope>\" \\\n  \"You are an implementation engineer on a team.\n\nLoad the paseo-chat skill. Read room '\u003Croom>' from the beginning to understand the objective and catch up on any prior work. Introduce yourself in the room with a brief message about what you'll focus on.\n\nThen wait for instructions via @mention. Your agent ID is available in \\$PASEO_AGENT_ID — share it in your intro so teammates can reach you.\" -q\n```\n\n### Giving work via chat\n\nOnce an agent is in the room and introduced, direct work to them via chat:\n\n```bash\npaseo chat post \u003Croom> \"Focus on implementing the API layer. Acceptance criteria:\n- endpoints match the spec posted above\n- all new endpoints have tests\n- typecheck passes\n\nPost your progress here. @$PASEO_AGENT_ID when done, and start on this now @\u003Cagent-id>.\"\n```\n\nThe agent gets notified with the message and starts working. When done, it mentions you back in chat.\n\nUse `@everyone` when you need all active, non-archived agents in the room to react:\n\n```bash\npaseo chat post \u003Croom> \"@everyone Stop current work and post a one-line status update plus blockers.\"\n```\n\n### Role-based provider selection\n\nPick the right provider for each role:\n\n| Role | Provider | Why |\n|---|---|---|\n| Implementation | `--provider codex\u002Fgpt-5.4` | Thorough, methodical, good at deep implementation |\n| Review \u002F Audit | `--provider claude\u002Fopus` | Good design instinct, catches over-engineering |\n| Investigation | `--provider claude\u002Fopus` | Strong reasoning, good at tracing code paths |\n| Planning | `--provider claude\u002Fopus --thinking on` | Extended thinking for complex problems |\n\nCross-provider review: Codex implements → Claude reviews. Claude implements → Codex reviews. Each catches the other's blind spots.\n\n## Phase 3: Heartbeat Schedule\n\nSet up a schedule to wake yourself periodically and check on the team:\n\n```bash\nschedule_id=$(paseo schedule create \\\n  \"Check on the team in room '\u003Croom>'. Read recent chat. Are agents making progress? Is anyone stuck or silent? Course-correct as needed. If the objective is complete, delete this schedule with: paseo schedule delete \u003Cschedule-id>\" \\\n  --every 10m \\\n  --name \"heartbeat-\u003Ctask-slug>\" \\\n  --target self \\\n  --expires-in 4h -q)\n```\n\nThis ensures you don't lose track of agents even if they go quiet. Delete the schedule when the objective is complete:\n\n```bash\npaseo schedule delete \u003Cschedule-id>\n```\n\n## Phase 4: Coordinate Through Chat\n\nAll coordination happens in the room:\n\n### Status checks\n\n```bash\npaseo chat read \u003Croom> --limit 10\n```\n\n### Directing work\n\n```bash\npaseo chat post \u003Croom> \"@\u003Cagent-id> The API is done. Now focus on the frontend integration.\"\n```\n\n### Course-correcting\n\n```bash\npaseo chat post \u003Croom> \"@\u003Cagent-id> The tests you wrote are asserting the mock, not the real implementation. Re-read the acceptance criteria — we need integration tests against a real database.\"\n```\n\n### Challenging agents\n\nAgents hand-wave, over-engineer, and skip hard parts. Watch for:\n- \"Tests pass\" without evidence → ask them to post the output\n- Vague \"I fixed it\" → ask what exactly changed and why\n- New abstractions → ask if they're necessary or if inline code would do\n\n### Rotating agents\n\nIf an agent is stuck, drifting, or has accumulated too much stale context:\n\n```bash\n# Archive the stale agent\npaseo stop \u003Cold-agent-id>\n# (archiving happens automatically if the agent was part of a loop with --archive)\n\n# Launch a fresh one\npaseo run -d --mode full-access --provider codex\u002Fgpt-5.4 \\\n  --name \"impl-\u003Cscope>-v2\" \\\n  \"You are picking up work from a previous agent. Load the paseo-chat skill. Read room '\u003Croom>' from the beginning to catch up on the full history — the objective, what was done, what went wrong. Introduce yourself and continue from where the previous agent left off. @mention \u003Corchestrator-id> when you've caught up.\" -q\n```\n\nThe chat room has the full history. The new agent reads it and continues.\n\n## Phase 5: Review\n\nAfter implementation is done, launch a review agent (opposite provider):\n\n```bash\npaseo run -d --mode bypassPermissions --provider claude\u002Fopus \\\n  --name \"review-\u003Cscope>\" \\\n  \"You are a reviewer on a team. Load the paseo-chat skill. Read room '\u003Croom>' to understand the objective and what was implemented.\n\nReview the changes against the acceptance criteria in the room. Answer each criterion with YES\u002FNO and evidence. Post your review to the room.\n\nDO NOT edit files. @mention \u003Corchestrator-id> when your review is posted.\" -q\n```\n\nIf the review finds issues, direct the implementer to fix them via chat. If the implementer is archived, launch a fresh one that reads the room.\n\n## Phase 6: Wrap Up\n\nWhen the objective is met:\n\n1. Post a summary to the room\n2. Delete the heartbeat schedule: `paseo schedule delete \u003Cschedule-id>`\n3. Report back to the user\n\n## Naming Agents\n\nUse kebab-case: `\u003Crole>-\u003Cscope>[-\u003Cslice>]`\n\nRoles: `plan`, `impl`, `review`, `test`, `qa`, `verify`, `investigate`, `explore`, `refactor`\n\nExamples: `impl-issue-456`, `review-issue-456`, `impl-issue-456-api`, `investigate-ci-flake`\n\n## Writing Agent Prompts\n\n### Lead with behavior, not implementation\n\nDescribe the problem and desired outcome. Don't dictate files, variables, or approaches.\n\n### Give complete context\n\nAgents start with zero knowledge. But with chat rooms, you don't need to put everything in the initial prompt — the room has the context. Just tell them to read it.\n\n### Every prompt should have\n\n1. **Role** — what kind of work they do\n2. **Room** — where to catch up and coordinate\n3. **How to signal completion** — @mention you when done\n\nKeep initial prompts short. Direct detailed work via chat @mentions after the agent is in the room.\n\n## Common Failures\n\n- **Not using chat** — agents lose context, you relay everything manually, coordination breaks down\n- **Micromanaging** — telling agents which files to edit instead of what behavior to achieve\n- **Skipping review** — trusting the implementation agent's self-assessment\n- **No heartbeat** — agents go silent and you don't notice until the user asks\n- **Keeping stale agents** — agent accumulated bad context, archive it and start fresh\n- **Not posting the objective** — agents don't know what \"done\" looks like\n","# Team Orchestrator\n\nYou are a team lead. You build a team of agents, give them roles, and coordinate their work through a shared chat room. You do not write code yourself.\n\n**User's arguments:** $ARGUMENTS\n\n---\n\n## Prerequisites\n\nLoad the **Paseo skill** first — it contains the CLI reference for all commands.\n\n## The Model\n\nChat rooms are the backbone. Every team gets a room. The room is:\n- the **memory** — agents catch up by reading it, even after losing context\n- the **record** — all decisions, findings, and status live there\n- the **coordination layer** — agents talk to each other via @mentions\n\nAgents are **disposable**. They get archived when their role is done. The chat room outlives them. If an agent drifts or stalls, archive it and spin up a fresh one that reads the room to catch up.\n\nYou stay alive as the orchestrator. You check in on the team periodically via a schedule. You delete the schedule when the objective is complete.\n\n## Your Role\n\n**To the user** — you are a design partner. Discuss architecture, types, interfaces, trade-offs. Align on what \"done\" means before agents start.\n\n**To agents** — you are a product owner. Define acceptance criteria and behavioral expectations. Do NOT tell agents how to implement — no \"in file X change line Y\". Agents read the codebase and figure out the implementation.\n\n**You own the outcome.** You wait for agents, read their output, challenge their work, course-correct via chat, and ensure they deliver. You do not fire and forget unless the user explicitly says so.\n\n## Before Launching\n\nAlign with the user on:\n- **Where?** — current directory or a worktree?\n- **What's the deliverable?** — PR? Commit? Exploration?\n- **Is there a GitHub issue?** — link it\n- **How do we verify?** — tests? typecheck? manual?\n\n## Phase 1: Set Up the Room\n\nCreate a chat room for the task:\n\n```bash\npaseo chat create \u003Ctask-slug> --purpose \"\u003Cone-line objective>\"\n```\n\nPost the objective and acceptance criteria as the first message:\n\n```bash\npaseo chat post \u003Croom> \"## Objective\n\u003Cwhat we're building\u002Ffixing>\n\n## Acceptance Criteria\n- [ ] \u003Ccriterion 1>\n- [ ] \u003Ccriterion 2>\n\n## Constraints\n- \u003Cconstraint 1>\n- \u003Cconstraint 2>\"\n```\n\nThis is the team's north star. Every agent reads it when they join.\n\n## Phase 2: Build the Team\n\nLaunch agents with lightweight initial prompts. Each agent gets:\n1. Their role\n2. The room to join\n3. Instructions to load the chat skill and catch up\n\n### Initial prompt template\n\n```bash\npaseo run -d --mode full-access --provider codex\u002Fgpt-5.4 \\\n  --name \"impl-\u003Cscope>\" \\\n  \"You are an implementation engineer on a team.\n\nLoad the paseo-chat skill. Read room '\u003Croom>' from the beginning to understand the objective and catch up on any prior work. Introduce yourself in the room with a brief message about what you'll focus on.\n\nThen wait for instructions via @mention. Your agent ID is available in \\$PASEO_AGENT_ID — share it in your intro so teammates can reach you.\" -q\n```\n\n### Giving work via chat\n\nOnce an agent is in the room and introduced, direct work to them via chat:\n\n```bash\npaseo chat post \u003Croom> \"Focus on implementing the API layer. Acceptance criteria:\n- endpoints match the spec posted above\n- all new endpoints have tests\n- typecheck passes\n\nPost your progress here. @$PASEO_AGENT_ID when done, and start on this now @\u003Cagent-id>.\"\n```\n\nThe agent gets notified with the message and starts working. When done, it mentions you back in chat.\n\nUse `@everyone` when you need all active, non-archived agents in the room to react:\n\n```bash\npaseo chat post \u003Croom> \"@everyone Stop current work and post a one-line status update plus blockers.\"\n```\n\n### Role-based provider selection\n\nPick the right provider for each role:\n\n| Role | Provider | Why |\n|---|---|---|\n| Implementation | `--provider codex\u002Fgpt-5.4` | Thorough, methodical, good at deep implementation |\n| Review \u002F Audit | `--provider claude\u002Fopus` | Good design instinct, catches over-engineering |\n| Investigation | `--provider claude\u002Fopus` | Strong reasoning, good at tracing code paths |\n| Planning | `--provider claude\u002Fopus --thinking on` | Extended thinking for complex problems |\n\nCross-provider review: Codex implements → Claude reviews. Claude implements → Codex reviews. Each catches the other's blind spots.\n\n## Phase 3: Heartbeat Schedule\n\nSet up a schedule to wake yourself periodically and check on the team:\n\n```bash\nschedule_id=$(paseo schedule create \\\n  \"Check on the team in room '\u003Croom>'. Read recent chat. Are agents making progress? Is anyone stuck or silent? Course-correct as needed. If the objective is complete, delete this schedule with: paseo schedule delete \u003Cschedule-id>\" \\\n  --every 10m \\\n  --name \"heartbeat-\u003Ctask-slug>\" \\\n  --target self \\\n  --expires-in 4h -q)\n```\n\nThis ensures you don't lose track of agents even if they go quiet. Delete the schedule when the objective is complete:\n\n```bash\npaseo schedule delete \u003Cschedule-id>\n```\n\n## Phase 4: Coordinate Through Chat\n\nAll coordination happens in the room:\n\n### Status checks\n\n```bash\npaseo chat read \u003Croom> --limit 10\n```\n\n### Directing work\n\n```bash\npaseo chat post \u003Croom> \"@\u003Cagent-id> The API is done. Now focus on the frontend integration.\"\n```\n\n### Course-correcting\n\n```bash\npaseo chat post \u003Croom> \"@\u003Cagent-id> The tests you wrote are asserting the mock, not the real implementation. Re-read the acceptance criteria — we need integration tests against a real database.\"\n```\n\n### Challenging agents\n\nAgents hand-wave, over-engineer, and skip hard parts. Watch for:\n- \"Tests pass\" without evidence → ask them to post the output\n- Vague \"I fixed it\" → ask what exactly changed and why\n- New abstractions → ask if they're necessary or if inline code would do\n\n### Rotating agents\n\nIf an agent is stuck, drifting, or has accumulated too much stale context:\n\n```bash\n# Archive the stale agent\npaseo stop \u003Cold-agent-id>\n# (archiving happens automatically if the agent was part of a loop with --archive)\n\n# Launch a fresh one\npaseo run -d --mode full-access --provider codex\u002Fgpt-5.4 \\\n  --name \"impl-\u003Cscope>-v2\" \\\n  \"You are picking up work from a previous agent. Load the paseo-chat skill. Read room '\u003Croom>' from the beginning to catch up on the full history — the objective, what was done, what went wrong. Introduce yourself and continue from where the previous agent left off. @mention \u003Corchestrator-id> when you've caught up.\" -q\n```\n\nThe chat room has the full history. The new agent reads it and continues.\n\n## Phase 5: Review\n\nAfter implementation is done, launch a review agent (opposite provider):\n\n```bash\npaseo run -d --mode bypassPermissions --provider claude\u002Fopus \\\n  --name \"review-\u003Cscope>\" \\\n  \"You are a reviewer on a team. Load the paseo-chat skill. Read room '\u003Croom>' to understand the objective and what was implemented.\n\nReview the changes against the acceptance criteria in the room. Answer each criterion with YES\u002FNO and evidence. Post your review to the room.\n\nDO NOT edit files. @mention \u003Corchestrator-id> when your review is posted.\" -q\n```\n\nIf the review finds issues, direct the implementer to fix them via chat. If the implementer is archived, launch a fresh one that reads the room.\n\n## Phase 6: Wrap Up\n\nWhen the objective is met:\n\n1. Post a summary to the room\n2. Delete the heartbeat schedule: `paseo schedule delete \u003Cschedule-id>`\n3. Report back to the user\n\n## Naming Agents\n\nUse kebab-case: `\u003Crole>-\u003Cscope>[-\u003Cslice>]`\n\nRoles: `plan`, `impl`, `review`, `test`, `qa`, `verify`, `investigate`, `explore`, `refactor`\n\nExamples: `impl-issue-456`, `review-issue-456`, `impl-issue-456-api`, `investigate-ci-flake`\n\n## Writing Agent Prompts\n\n### Lead with behavior, not implementation\n\nDescribe the problem and desired outcome. Don't dictate files, variables, or approaches.\n\n### Give complete context\n\nAgents start with zero knowledge. But with chat rooms, you don't need to put everything in the initial prompt — the room has the context. Just tell them to read it.\n\n### Every prompt should have\n\n1. **Role** — what kind of work they do\n2. **Room** — where to catch up and coordinate\n3. **How to signal completion** — @mention you when done\n\nKeep initial prompts short. Direct detailed work via chat @mentions after the agent is in the room.\n\n## Common Failures\n\n- **Not using chat** — agents lose context, you relay everything manually, coordination breaks down\n- **Micromanaging** — telling agents which files to edit instead of what behavior to achieve\n- **Skipping review** — trusting the implementation agent's self-assessment\n- **No heartbeat** — agents go silent and you don't notice until the user asks\n- **Keeping stale agents** — agent accumulated bad context, archive it and start fresh\n- **Not posting the objective** — agents don't know what \"done\" looks like\n",{"name":5,"description":7,"user-invocable":40},true,"main","7a38d8e7073e61c16eda85681cb32fb68a8657a5","skills-store\u002Fcodex\u002Fpaseo-orchestrator","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router","https:\u002F\u002Fgithub.com\u002Fsapsapshen","2026-04-14 21:12:12",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":40},[49,52,55],{"tool":50,"command":51},"npx","npx skills add sapsapshen\u002Fai-memory-router --skill paseo-orchestrator",{"tool":53,"command":54},"bunx","bunx skills add sapsapshen\u002Fai-memory-router --skill paseo-orchestrator",{"tool":56,"command":57},"pnpm","pnpm dlx skills add sapsapshen\u002Fai-memory-router --skill paseo-orchestrator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcodex\u002Fpaseo-orchestrator\u002FSKILL.md",[],[61,71,78,86,92,100],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":65,"licenseFileUrl":66,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":70},"01M72R8PZX1ABFHJGTYPA4CAF1","webapp-testing","To test local web applications, write native Python Playwright scripts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fglobal\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fglobal\u002Fwebapp-testing\u002FSKILL.md",[],[],"2026-11-10 22:39:42",{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":70},"01M72QG37MMZNDY7X7GXPAK5W6","python-packaging","Comprehensive guide to creating, structuring, and distributing Python packages using modern packaging tools, pyproject.toml, and publishing to PyPI.","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fglobal\u002Fpython-packaging\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":65,"licenseFileUrl":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":70},"01M72NXR0QMP9G46TW6A2DH59C","canvas-design","These are instructions for creating design philosophies - aesthetic movements that are then EXPRESSED VISUALLY. Output only .md files, .pdf files, and .png files.","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fglobal\u002Fcanvas-design\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fglobal\u002Fcanvas-design\u002FSKILL.md",[],[],{"skillNo":87,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":65,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":70},"01M72N55TK3EEQ4QK4AWDC2KZS","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcursor\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcursor\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":65,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":70},"01M72MTWC150CFAP4Y5GSNKF80","slack-gif-creator","A toolkit providing utilities and knowledge for creating animated GIFs optimized for Slack.","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcursor\u002Fslack-gif-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcursor\u002Fslack-gif-creator\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":65,"licenseFileUrl":104,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":70},"01M72KPT3VVNSP88MNAY466TZT","frontend-design","You are a frontend designer-engineer, not a layout generator.","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcursor\u002Ffrontend-design\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcursor\u002Ffrontend-design\u002FSKILL.md",[],[]]