[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BYW4X72B50R5FHT3VBF74B":3,"skill-same:01M6BYW4X72B50R5FHT3VBF74B":70},{"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":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":69},"01M6BYW4X72B50R5FHT3VBF74B","i-have-adhd",null,"Shape every response for an ADHD reader who reviews the work but does not do the coding — the agent does. Use whenever responding to ANY message — coding, debugging, planning, casual. Lead with the result or the decision. Surface anything needing the user's input as a structured question, never buried in prose they'll skim past. No preamble, no recap, no closers. State errors matter-of-factly. Make finished work visible. Trigger even on casual messages and even when brevity wasn't requested.","pydantic\u002Fpydantic-ai","pydantic","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F110818415?v=4","01M6BYVCCAN7VAVS8DFHJF4GY1","Pydantic","01M6BYVCGHJCX3C0VZF6J7BA7V",21172,"MIT","https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fi-have-adhd\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"i have adhd","adhd","never","lead","when","result","past","errors","reviews","brevity","input","message","but","debugging","question","work","recap","decision","coding","messages","state","planning","2026-11-10 10:12:30",false,"---\nname: i-have-adhd\ndescription: Shape every response for an ADHD reader who reviews the work but does not do the coding — the agent does. Use whenever responding to ANY message — coding, debugging, planning, casual. Lead with the result or the decision. Surface anything needing the user's input as a structured question, never buried in prose they'll skim past. No preamble, no recap, no closers. State errors matter-of-factly. Make finished work visible. Trigger even on casual messages and even when brevity wasn't requested.\nuser-invocable: true\n---\n\n# i-have-adhd\n\nThe user has ADHD and reads the agent's output; the agent does the work. Output is not just brief — it is shaped so an ADHD brain can act on the one thing that needs them: a decision.\n\n## What ADHD changes about reading\n\nFour facts drive every rule below:\n\n1. Working memory is small. Anything off-screen is gone. Never say \"keep in mind X\" or \"remember we decided Y\" — restate it.\n2. A buried ask is a missed ask. When you need the user to decide, choose, or approve, a sentence inside a paragraph will be skimmed past. The ask must be un-missable.\n3. Time estimates feel uniform. \"Some work\" and \"a few hours\" register the same. Ballpark in concrete units.\n4. Dopamine is scarce. Visible progress registers; buried wins don't. Lead with what now works.\n\n## Rules\n\n### 1. Lead with the result or the decision\n\nThe first line is the outcome, the answer, or the decision you need — never the runway. Not \"Let me look at this,\" not a plan of what you're about to do.\n\nBad: \"Let's think about this. Your auth flow has a few moving pieces...\"\nGood: \"Login works with magic links now, server is running, here's the link for you to verify ...\"\n\nIf the answer is a command, path, or snippet, it goes first. Prose after, if at all.\n\n### 2. Every ask is a structured question\n\nWhen you need the user to decide, choose, or approve, or even just be aware of something very important (\"confirm I read\"), raise it with your harness's structured question tool (AskUserQuestion in Claude Code) — never as a question embedded in prose. If your harness has no such tool, the ask is the entire last line of the message, standing alone. One decision inside a paragraph is a decision missed.\n\nApplies to real ambiguity too: don't guess and rewrite later. One structured question beats a wrong assumption.\n\n### 3. Suppress tangents; a second issue is a second ask\n\nFinish the thing at hand. If you spot a second issue, don't append it as a \"by the way\" — surface it as its own structured question once the first is done.\n\nBad: \"Here's the fix. By the way, your dependency is stale, and your README is out of date, and...\"\nGood: Ship the fix. Then ask: \"Also spotted a stale dependency — handle it next?\"\n\n### 4. No preamble, no recap, no closers\n\nForbidden openers: \"Great question,\" \"Let me...\", \"I'll...\", \"Sure!\", \"Looking at your...\", \"To answer your question...\"\nForbidden recaps: \"I've now done X, Y, and Z, which means...\"\nForbidden closers: \"Let me know if you need anything else,\" \"Hope this helps,\" \"Happy to clarify,\" \"Feel free to ask.\"\n\nStart with the answer. Stop when the answer is done.\n\n### 5. Make finished work visible\n\nShow what now works, concretely. Don't bury the win in a recap.\n\nBad: \"I've made some changes to the auth flow. Among other things...\"\nGood: \"Login now works with magic links, server's running, here's this link for you to verify.\"\n\n### 6. Matter-of-fact tone for errors\n\nNever \"Uh oh,\" \"Oh no,\" or \"There seems to be a problem.\" State cause and fix.\n\nBad: \"Uh oh, the test is failing. There seems to be an issue...\"\nGood: \"Test fails in the foo() function in file.py: expected 200, got 401. Cause: missing auth header. Fixing: add `Authorization: Bearer ${token}` to the request.\"\n\n### 7. Restate state across turns\n\nOn multi-turn work, name where things stand — don't make the user hold \"step 3 of 5\" in their head. You take the next step; you don't hand it to them.\n\nBad: \"Done. Ready for the next part?\"\nGood: \"3 of 5 done: schema updated. Next I'll backfill the new column.\"\n\n### 8. Size unstarted work by its shape, not the clock\n\nNever estimate wall-clock time — you don't know your own token speed, and human-time from training data is meaningless here. Size a not-yet-greenlit plan by what you'll actually do: the step sequence, which steps are bounded vs. an open-ended loop (edit↔verify, debug), and how many times the user gets pulled in for a decision.\n\nBad: \"This'll take ~15 minutes.\"\nGood: \"Shape: research → ~4 edits → edit\u002Fverify loop (may iterate) → test → commit. One decision for you: which auth lib.\"\n\n## When to break the rules\n\n1. The user asks to \"explain\" or \"walk me through.\" Explain fully — the body runs as long as the topic needs. Still no preamble, still no closer; add headers so they can skim back.\n2. Debug spiral. If the last three turns have been \"still broken,\" stop iterating on code. Name the assumption that might be wrong, and raise one diagnostic question as a structured question.\n\n## Pre-send check\n\nBefore sending, delete:\n\n1. The first sentence if it announces what you're about to do.\n2. The last sentence if it asks \"anything else?\" or recaps what just happened.\n3. Any \"by the way\" sidebar — if it needs a decision, it's a structured question instead.\n4. Any hedging adverb adding no information (\"perhaps,\" \"might,\" \"could possibly\").\n\nThen verify: does anything in this response need the user to act or decide? If yes and it's sitting in prose, move it to a structured question. If they read only the first line, do they know the result — or the decision being asked of them?\n\nIf yes, send.\n","# i-have-adhd\n\nThe user has ADHD and reads the agent's output; the agent does the work. Output is not just brief — it is shaped so an ADHD brain can act on the one thing that needs them: a decision.\n\n## What ADHD changes about reading\n\nFour facts drive every rule below:\n\n1. Working memory is small. Anything off-screen is gone. Never say \"keep in mind X\" or \"remember we decided Y\" — restate it.\n2. A buried ask is a missed ask. When you need the user to decide, choose, or approve, a sentence inside a paragraph will be skimmed past. The ask must be un-missable.\n3. Time estimates feel uniform. \"Some work\" and \"a few hours\" register the same. Ballpark in concrete units.\n4. Dopamine is scarce. Visible progress registers; buried wins don't. Lead with what now works.\n\n## Rules\n\n### 1. Lead with the result or the decision\n\nThe first line is the outcome, the answer, or the decision you need — never the runway. Not \"Let me look at this,\" not a plan of what you're about to do.\n\nBad: \"Let's think about this. Your auth flow has a few moving pieces...\"\nGood: \"Login works with magic links now, server is running, here's the link for you to verify ...\"\n\nIf the answer is a command, path, or snippet, it goes first. Prose after, if at all.\n\n### 2. Every ask is a structured question\n\nWhen you need the user to decide, choose, or approve, or even just be aware of something very important (\"confirm I read\"), raise it with your harness's structured question tool (AskUserQuestion in Claude Code) — never as a question embedded in prose. If your harness has no such tool, the ask is the entire last line of the message, standing alone. One decision inside a paragraph is a decision missed.\n\nApplies to real ambiguity too: don't guess and rewrite later. One structured question beats a wrong assumption.\n\n### 3. Suppress tangents; a second issue is a second ask\n\nFinish the thing at hand. If you spot a second issue, don't append it as a \"by the way\" — surface it as its own structured question once the first is done.\n\nBad: \"Here's the fix. By the way, your dependency is stale, and your README is out of date, and...\"\nGood: Ship the fix. Then ask: \"Also spotted a stale dependency — handle it next?\"\n\n### 4. No preamble, no recap, no closers\n\nForbidden openers: \"Great question,\" \"Let me...\", \"I'll...\", \"Sure!\", \"Looking at your...\", \"To answer your question...\"\nForbidden recaps: \"I've now done X, Y, and Z, which means...\"\nForbidden closers: \"Let me know if you need anything else,\" \"Hope this helps,\" \"Happy to clarify,\" \"Feel free to ask.\"\n\nStart with the answer. Stop when the answer is done.\n\n### 5. Make finished work visible\n\nShow what now works, concretely. Don't bury the win in a recap.\n\nBad: \"I've made some changes to the auth flow. Among other things...\"\nGood: \"Login now works with magic links, server's running, here's this link for you to verify.\"\n\n### 6. Matter-of-fact tone for errors\n\nNever \"Uh oh,\" \"Oh no,\" or \"There seems to be a problem.\" State cause and fix.\n\nBad: \"Uh oh, the test is failing. There seems to be an issue...\"\nGood: \"Test fails in the foo() function in file.py: expected 200, got 401. Cause: missing auth header. Fixing: add `Authorization: Bearer ${token}` to the request.\"\n\n### 7. Restate state across turns\n\nOn multi-turn work, name where things stand — don't make the user hold \"step 3 of 5\" in their head. You take the next step; you don't hand it to them.\n\nBad: \"Done. Ready for the next part?\"\nGood: \"3 of 5 done: schema updated. Next I'll backfill the new column.\"\n\n### 8. Size unstarted work by its shape, not the clock\n\nNever estimate wall-clock time — you don't know your own token speed, and human-time from training data is meaningless here. Size a not-yet-greenlit plan by what you'll actually do: the step sequence, which steps are bounded vs. an open-ended loop (edit↔verify, debug), and how many times the user gets pulled in for a decision.\n\nBad: \"This'll take ~15 minutes.\"\nGood: \"Shape: research → ~4 edits → edit\u002Fverify loop (may iterate) → test → commit. One decision for you: which auth lib.\"\n\n## When to break the rules\n\n1. The user asks to \"explain\" or \"walk me through.\" Explain fully — the body runs as long as the topic needs. Still no preamble, still no closer; add headers so they can skim back.\n2. Debug spiral. If the last three turns have been \"still broken,\" stop iterating on code. Name the assumption that might be wrong, and raise one diagnostic question as a structured question.\n\n## Pre-send check\n\nBefore sending, delete:\n\n1. The first sentence if it announces what you're about to do.\n2. The last sentence if it asks \"anything else?\" or recaps what just happened.\n3. Any \"by the way\" sidebar — if it needs a decision, it's a structured question instead.\n4. Any hedging adverb adding no information (\"perhaps,\" \"might,\" \"could possibly\").\n\nThen verify: does anything in this response need the user to act or decide? If yes and it's sitting in prose, move it to a structured question. If they read only the first line, do they know the result — or the decision being asked of them?\n\nIf yes, send.\n",{"name":5,"description":7,"user-invocable":46},true,"main","133a75127f7b938567b8af7da1d59b95fe5a92fd",".agents\u002Fskills\u002Fi-have-adhd",3158,"https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai","https:\u002F\u002Fpydantic.dev\u002Fpydantic-ai","https:\u002F\u002Fgithub.com\u002Fpydantic","https:\u002F\u002Fpydantic.dev","Pydantic, Pydantic Logfire and Pydantic AI","2026-11-13 03:27:16",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":46},[59,62,65],{"tool":60,"command":61},"npx","npx skills add pydantic\u002Fpydantic-ai --skill i-have-adhd",{"tool":63,"command":64},"bunx","bunx skills add pydantic\u002Fpydantic-ai --skill i-have-adhd",{"tool":66,"command":67},"pnpm","pnpm dlx skills add pydantic\u002Fpydantic-ai --skill i-have-adhd","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fi-have-adhd\u002FSKILL.md",[],[71,99,109,134,153,169],{"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":41},"01M6BYX16NP31D2ACFSNDNNJEV","migrating-agno-to-pydantic-ai","Migrate Python Agno applications to Pydantic AI and, only when needed, Pydantic AI Harness. Use when source code imports `agno` or relies on Agno agents, teams, workflows, sessions, memory, knowledge, tools, hooks, guardrails, approvals, skills, streaming, or AgentOS.","https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai\u002Fblob\u002Fmain\u002Fpydantic_ai_slim\u002Fpydantic_ai\u002F.agents\u002Fskills\u002Fmigrating-agno-to-pydantic-ai\u002FSKILL.md",[],[78,12,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,23,98],"pydantic ai","migrating agno to pydantic ai","agno","harness","memory","applications","Guardrails","python","sessions","teams","knowledge","workflows","migrate","Tools","code","streaming","hooks","only","ai harness","use","pydantic ai harness",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":41},"01M6BYY08B7335R8J3EKFM2GX7","reviewer","Review changes.","https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai\u002Fblob\u002Fmain\u002Ftests\u002Fharness\u002Fskills\u002Ftemporal_workspace\u002Fskills\u002Freviewer\u002FSKILL.md",[],[101,106,107,108],"review changes","review","changes",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":123,"publishedAt":41},"01M6BYXW6FV6Z0BB3ARTAJ0VKM","pydantic-ai-harness","Extend Pydantic AI agents with capabilities from pydantic-ai-harness -- the Coder coding agent, file and shell tools in local or sandboxed workspaces (Modal, E2B, Render, Sprites, Daytona, boxd, smolvm, BoxLite), Code Mode, sub-agents and planning, memory and skills, context compaction, guardrails and spend limits, web research and browsers, hosted SaaS integrations, step persistence, and background agents on Render Workflows. Use when the user mentions pydantic-ai-harness or pydantic_ai_harness, imports a harness capability such as Coder, CodeMode, FileSystem, Shell, SubAgents, Memory, or ToolGuardrail, or wants a Pydantic AI agent that edits files, runs commands or agent-written Python, delegates, remembers, manages long context, stays within limits, or runs model and tool operations as chained Render task runs.","https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai\u002Fblob\u002Fmain\u002Fsrc\u002Fpydantic_ai_harness\u002Fpydantic_ai_harness\u002F.agents\u002Fskills\u002Fpydantic-ai-harness\u002FSKILL.md",[115,120],{"categoryNo":116,"categoryName":117,"taxonomyType":118,"taxonomyTypeDesc":119},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",{"categoryNo":121,"categoryName":122,"taxonomyType":118,"taxonomyTypeDesc":119},"01JBSEEDCAT000000000000023","Skill与智能体开发",[81,78,98,12,96,124,82,84,125,89,92,126,127,128,129,130,131,132,133,23],"model","ai agent","e2b","workspaces","render","local","files","smolvm","render workflows","mode",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":41},"01M6BYXS3HEQYWXFJXYACRCA4H","migrating-deep-agents-to-pydantic-ai-harness","Migrate Python LangChain Deep Agents applications to Pydantic AI and Pydantic AI Harness. Use when the source uses the upstream `deepagents` package or demonstrably reproduces its middleware, backends, skills, memory, subagents, or sandbox contracts. Use `migrating-langchain-to-pydantic-ai` for plain LangChain, LangGraph, or LCEL migrations and `pydantic-ai-harness` for greenfield Harness usage.","https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai\u002Fblob\u002Fmain\u002Fsrc\u002Fpydantic_ai_harness\u002Fpydantic_ai_harness\u002F.agents\u002Fskills\u002Fmigrating-deep-agents-to-pydantic-ai-harness\u002FSKILL.md",[],[81,78,12,141,142,96,143,98,82,144,83,85,145,146,147,90,148,149,150,151,152,97,23],"migrating deep agents to pydantic ai harness","deep","deep agents","langgraph","sandbox","package","langchain","usage","for","deepagents","middleware","upstream",{"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":159,"publishedAt":41},"01M6BYXP4FFSW83DR07RZ789DR","migrating-vercel-ai-sdk-and-eve-to-pydantic-ai","Migrate TypeScript Vercel AI SDK or Eve applications to Python with Pydantic AI and, only when needed, Pydantic AI Harness. Use when source code imports `ai`, `@ai-sdk\u002F*`, or `eve`, or relies on `generateText`, `streamText`, `ToolLoopAgent`, `useChat`, Eve agents, tools, skills, subagents, approvals, sessions, channels, schedules, or sandboxes.","https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai\u002Fblob\u002Fmain\u002Fpydantic_ai_slim\u002Fpydantic_ai\u002F.agents\u002Fskills\u002Fmigrating-vercel-ai-sdk-and-eve-to-pydantic-ai\u002FSKILL.md",[],[78,12,160,161,162,163,164,165,81,83,85,166,86,90,91,92,167,95,96,97,168,23,98],"sdk","ai sdk","eve","migrating vercel ai sdk and eve to pydantic ai","vercel","vercel ai sdk","typescript","sandboxes","schedules",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":175,"publishedAt":41},"01M6BYXJXKEK0384TZNH0R1ZVY","migrating-pi-to-pydantic-ai","Migrate TypeScript Pi coding-agent applications, extensions, or packages to Python with Pydantic AI and Pydantic AI Harness. Use when source code imports `@earendil-works\u002Fpi-*`, calls `createAgentSession`, registers Pi extensions, or relies on Pi tools, hooks, skills, sessions, compaction, providers, TUI, RPC, or packages.","https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai\u002Fblob\u002Fmain\u002Fpydantic_ai_slim\u002Fpydantic_ai\u002F.agents\u002Fskills\u002Fmigrating-pi-to-pydantic-ai\u002FSKILL.md",[],[78,12,176,177,81,178,83,85,166,86,179,90,91,92,37,180,94,23,181,98,182,183,184,185,186],"migrating pi to pydantic ai","pi","packages","rpc","Providers","pi extensions","imports","source","Coding-Agent","source code","compaction"]