[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XDTQ2S6XAH5SQDMF27AB0W":3,"skill-same:01M6XDTQ2S6XAH5SQDMF27AB0W":64},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":14,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":50,"install":51,"resources":63},"01M6XDTQ2S6XAH5SQDMF27AB0W","paseo-committee",null,"Form a committee of two high-reasoning agents to step back, do root cause analysis, and produce a plan. Use when stuck, looping, tunnel-visioning, or facing a hard planning problem.","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-committee\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"paseo committee","paseo","when stuck","when","root cause","high","true","root","form","problem","tunnel","back","root cause analysis","do","use","plan","analysis","produce","reasoning","planning","2026-11-10 10:12:30",false,"---\nname: paseo-committee\ndescription: Form a committee of two high-reasoning agents to step back, do root cause analysis, and produce a plan. Use when stuck, looping, tunnel-visioning, or facing a hard planning problem.\nuser-invocable: true\n---\n\n# Committee Skill\n\nYou are forming a committee to step back from the current problem and get fresh perspective.\n\n**User's additional context:** $ARGUMENTS\n\n---\n\n## Prerequisites\n\nLoad the **Paseo skill** first — it contains the CLI reference for all agent commands and waiting guidelines.\n\n## What Is a Committee\n\nTwo agents — **Opus 4.6** (`--thinking on`) and **GPT 5.4** (`--thinking medium`) — launched in parallel to plan a solution. Fresh context, no implementation baggage, proper root cause analysis.\n\nThey stay alive after planning for Phase 3 review — they hold only the plan, so they catch implementation drift.\n\n**The purpose is to step back, not to double down.** The committee may propose a completely different approach.\n\n## Your Role\n\nYou drive the full lifecycle: plan → implement → review. You are a middleman between the user and the committee. Do not yield back to the user until the cycle is complete. If the user needs to weigh in on a divergence, ask them — but don't stop the process.\n\n## No Anxiety\n\n**Once you call `paseo wait`, trust the wait.** Do not poll logs, read output early, send hurry-up messages, interrupt deep analysis, or give up because it's taking long.\n\nGPT 5.4 can reason for 15–30 minutes. Opus does extended thinking. Long waits mean the agent found something worth thinking about. Let it finish.\n\nIf the CLI has a bug, the user will tell you.\n\n## No-Edits Suffix\n\nEvery prompt to a committee member — initial, follow-up, or review — **must** end with this suffix. They will start editing code if you don't.\n\n```\nNO_EDITS=\"This is analysis only. Do NOT edit, create, or delete any files. Do NOT write code.\"\n```\n\nAll example prompts below include `$NO_EDITS` — always expand it.\n\n## Phase 1: Get a Plan\n\n### Write the prompt\n\nDescribe the **overall problem**, not just the immediate symptom:\n\n- High-level goal and acceptance criteria\n- Constraints\n- Symptoms (if a bug)\n- What you've tried and why it failed\n- Explicitly ask for root cause analysis\n\n```bash\nprompt=\"We're trying to [high-level goal]. Constraints: [X, Y, Z]. Acceptance criteria: [A, B, C].\n\nWe've been stuck on this. Here's what we've tried and why it didn't work:\n- [approach 1] — failed because [reason]\n- [approach 2] — partially worked but [issue]\n\nStep back from these attempts. Do root cause analysis — the fix might not be for [immediate symptom] at all, it might be structural.\n\nUse the think-harder approach: state your assumptions, ask why at least 3 levels deep for each, and check whether you're patching a symptom or removing the problem. What's the right approach?\n\n$NO_EDITS\"\n```\n\n### Launch both members\n\nSame prompt to both, `[Committee]` prefix for identification:\n\n```bash\nopus_id=$(paseo run -d --mode bypassPermissions --provider claude\u002Fopus --thinking on --name \"[Committee] Task description\" \"$prompt\" -q)\ngpt_id=$(paseo run -d --mode full-access --provider codex\u002Fgpt-5.4 --thinking medium --name \"[Committee] Task description\" \"$prompt\" -q)\n```\n\n### Wait for both\n\nWait for **both** agents — not just the first one that finishes.\n\n```bash\npaseo wait \"$opus_id\"\npaseo wait \"$gpt_id\"\n```\n\n### Read and challenge\n\n```bash\npaseo logs \"$opus_id\"\npaseo logs \"$gpt_id\"\n```\n\n**Do not accept output at face value.** Use the **think-harder** framework to challenge their output. Before synthesizing:\n\n1. **Ask \"why\" 2–3 levels deep.** \"Fix X because Y is broken\" — why is Y broken? Is Y a root cause or a consequence?\n2. **Challenge assumptions.** If the plan assumes something about the code, make the agent verify it.\n3. **Symptom vs cause.** \"Are we fixing the consequence or the cause?\"\n4. **Probe alternatives.** \"What did you consider and reject?\"\n\n```bash\npaseo send \"$opus_id\" \"You said [X]. Why does [underlying thing] happen in the first place? Are we patching a symptom? $NO_EDITS\"\npaseo wait \"$opus_id\"\npaseo logs \"$opus_id\"\n```\n\nKeep pushing until the plan addresses the root cause.\n\n### Synthesize and confirm\n\n- Convergence → merge into unified plan.\n- Significant divergence → involve the user.\n\nSend the merged plan back for confirmation. Multi-turn if needed — keep going until consensus.\n\n```bash\npaseo send \"$opus_id\" \"Merged plan: [plan]. Concerns? $NO_EDITS\"\npaseo send \"$gpt_id\" \"Merged plan: [plan]. Concerns? $NO_EDITS\"\n```\n\n## Phase 2: Implement\n\nImplement the plan yourself — unless the user said **\"delegate\"**, in which case launch an implementer:\n\n```bash\nimpl_id=$(paseo run -d --mode full-access --provider codex\u002Fgpt-5.4 --name \"[Impl] Task description\" \"Implement the following plan end-to-end. [plan]\" -q)\npaseo wait \"$impl_id\"\n```\n\nCommittee agents stay clean — not involved in implementation.\n\n## Phase 3: Review\n\nSend the committee the changes for review. They anchor against the plan and catch drift.\n\n```bash\nreview_prompt=\"Implementation is done. Review changes against the plan. Flag drift or missing pieces. $NO_EDITS\"\n\npaseo send \"$opus_id\" \"$review_prompt\"\npaseo send \"$gpt_id\" \"$review_prompt\"\n\npaseo wait \"$opus_id\"\npaseo wait \"$gpt_id\"\n\npaseo logs \"$opus_id\"\npaseo logs \"$gpt_id\"\n```\n\n### Iterate\n\nSend committee feedback to the implementer (or apply yourself). Repeat Phase 2 → 3 until the committee confirms the implementation matches the plan.\n\nAfter ~10 iterations without convergence, start a fresh committee with full context of what was tried — the current committee's context may have drifted too far.\n","# Committee Skill\n\nYou are forming a committee to step back from the current problem and get fresh perspective.\n\n**User's additional context:** $ARGUMENTS\n\n---\n\n## Prerequisites\n\nLoad the **Paseo skill** first — it contains the CLI reference for all agent commands and waiting guidelines.\n\n## What Is a Committee\n\nTwo agents — **Opus 4.6** (`--thinking on`) and **GPT 5.4** (`--thinking medium`) — launched in parallel to plan a solution. Fresh context, no implementation baggage, proper root cause analysis.\n\nThey stay alive after planning for Phase 3 review — they hold only the plan, so they catch implementation drift.\n\n**The purpose is to step back, not to double down.** The committee may propose a completely different approach.\n\n## Your Role\n\nYou drive the full lifecycle: plan → implement → review. You are a middleman between the user and the committee. Do not yield back to the user until the cycle is complete. If the user needs to weigh in on a divergence, ask them — but don't stop the process.\n\n## No Anxiety\n\n**Once you call `paseo wait`, trust the wait.** Do not poll logs, read output early, send hurry-up messages, interrupt deep analysis, or give up because it's taking long.\n\nGPT 5.4 can reason for 15–30 minutes. Opus does extended thinking. Long waits mean the agent found something worth thinking about. Let it finish.\n\nIf the CLI has a bug, the user will tell you.\n\n## No-Edits Suffix\n\nEvery prompt to a committee member — initial, follow-up, or review — **must** end with this suffix. They will start editing code if you don't.\n\n```\nNO_EDITS=\"This is analysis only. Do NOT edit, create, or delete any files. Do NOT write code.\"\n```\n\nAll example prompts below include `$NO_EDITS` — always expand it.\n\n## Phase 1: Get a Plan\n\n### Write the prompt\n\nDescribe the **overall problem**, not just the immediate symptom:\n\n- High-level goal and acceptance criteria\n- Constraints\n- Symptoms (if a bug)\n- What you've tried and why it failed\n- Explicitly ask for root cause analysis\n\n```bash\nprompt=\"We're trying to [high-level goal]. Constraints: [X, Y, Z]. Acceptance criteria: [A, B, C].\n\nWe've been stuck on this. Here's what we've tried and why it didn't work:\n- [approach 1] — failed because [reason]\n- [approach 2] — partially worked but [issue]\n\nStep back from these attempts. Do root cause analysis — the fix might not be for [immediate symptom] at all, it might be structural.\n\nUse the think-harder approach: state your assumptions, ask why at least 3 levels deep for each, and check whether you're patching a symptom or removing the problem. What's the right approach?\n\n$NO_EDITS\"\n```\n\n### Launch both members\n\nSame prompt to both, `[Committee]` prefix for identification:\n\n```bash\nopus_id=$(paseo run -d --mode bypassPermissions --provider claude\u002Fopus --thinking on --name \"[Committee] Task description\" \"$prompt\" -q)\ngpt_id=$(paseo run -d --mode full-access --provider codex\u002Fgpt-5.4 --thinking medium --name \"[Committee] Task description\" \"$prompt\" -q)\n```\n\n### Wait for both\n\nWait for **both** agents — not just the first one that finishes.\n\n```bash\npaseo wait \"$opus_id\"\npaseo wait \"$gpt_id\"\n```\n\n### Read and challenge\n\n```bash\npaseo logs \"$opus_id\"\npaseo logs \"$gpt_id\"\n```\n\n**Do not accept output at face value.** Use the **think-harder** framework to challenge their output. Before synthesizing:\n\n1. **Ask \"why\" 2–3 levels deep.** \"Fix X because Y is broken\" — why is Y broken? Is Y a root cause or a consequence?\n2. **Challenge assumptions.** If the plan assumes something about the code, make the agent verify it.\n3. **Symptom vs cause.** \"Are we fixing the consequence or the cause?\"\n4. **Probe alternatives.** \"What did you consider and reject?\"\n\n```bash\npaseo send \"$opus_id\" \"You said [X]. Why does [underlying thing] happen in the first place? Are we patching a symptom? $NO_EDITS\"\npaseo wait \"$opus_id\"\npaseo logs \"$opus_id\"\n```\n\nKeep pushing until the plan addresses the root cause.\n\n### Synthesize and confirm\n\n- Convergence → merge into unified plan.\n- Significant divergence → involve the user.\n\nSend the merged plan back for confirmation. Multi-turn if needed — keep going until consensus.\n\n```bash\npaseo send \"$opus_id\" \"Merged plan: [plan]. Concerns? $NO_EDITS\"\npaseo send \"$gpt_id\" \"Merged plan: [plan]. Concerns? $NO_EDITS\"\n```\n\n## Phase 2: Implement\n\nImplement the plan yourself — unless the user said **\"delegate\"**, in which case launch an implementer:\n\n```bash\nimpl_id=$(paseo run -d --mode full-access --provider codex\u002Fgpt-5.4 --name \"[Impl] Task description\" \"Implement the following plan end-to-end. [plan]\" -q)\npaseo wait \"$impl_id\"\n```\n\nCommittee agents stay clean — not involved in implementation.\n\n## Phase 3: Review\n\nSend the committee the changes for review. They anchor against the plan and catch drift.\n\n```bash\nreview_prompt=\"Implementation is done. Review changes against the plan. Flag drift or missing pieces. $NO_EDITS\"\n\npaseo send \"$opus_id\" \"$review_prompt\"\npaseo send \"$gpt_id\" \"$review_prompt\"\n\npaseo wait \"$opus_id\"\npaseo wait \"$gpt_id\"\n\npaseo logs \"$opus_id\"\npaseo logs \"$gpt_id\"\n```\n\n### Iterate\n\nSend committee feedback to the implementer (or apply yourself). Repeat Phase 2 → 3 until the committee confirms the implementation matches the plan.\n\nAfter ~10 iterations without convergence, start a fresh committee with full context of what was tried — the current committee's context may have drifted too far.\n",{"name":5,"description":7,"user-invocable":44},true,"main","7a38d8e7073e61c16eda85681cb32fb68a8657a5","skills-store\u002Fcodex\u002Fpaseo-committee","https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router","https:\u002F\u002Fgithub.com\u002Fsapsapshen","2026-04-14 21:12:12",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":44},[53,56,59],{"tool":54,"command":55},"npx","npx skills add sapsapshen\u002Fai-memory-router --skill paseo-committee",{"tool":57,"command":58},"bunx","bunx skills add sapsapshen\u002Fai-memory-router --skill paseo-committee",{"tool":60,"command":61},"pnpm","pnpm dlx skills add sapsapshen\u002Fai-memory-router --skill paseo-committee","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcodex\u002Fpaseo-committee\u002FSKILL.md",[],[65,75,82,90,96,104],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":74},"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":74},"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":86,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":74},"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":91,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":74},"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":100,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":74},"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":108,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":74},"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",[],[]]