[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718C9M1KTZJKX41NXCF54RD":3,"skill-same:01M718C9M1KTZJKX41NXCF54RD":63},{"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":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":6,"updatedAt":48,"install":49,"resources":62},"01M718C9M1KTZJKX41NXCF54RD","submit-solution",null,"Guide a workshop attendee through committing their starter-agent decomposition and opening a PR with their solution + workshop feedback. Invoke when the user says \"submit\", \"I'm done\", \"open a PR\", or asks how to share their solution.","anthropics\u002Fcwc-workshops","anthropics","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F76263028?v=4","01M697XGDPXJAVQ8391V2BCYTE","Anthropic","01M718C167JSRVRHKR28E40JYN",2309,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops\u002Fblob\u002Fmain\u002Fagent-decomposition\u002F.claude\u002Fskills\u002Fsubmit-solution\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35],"submit solution","submit","user","guide","opening a pr","how","decomposition","starter","with","share","done","when","invoke","open","how to","pr","feedback","2026-11-10 10:12:30",false,"---\nname: submit-solution\ndescription: Guide a workshop attendee through committing their starter-agent decomposition and opening a PR with their solution + workshop feedback. Invoke when the user says \"submit\", \"I'm done\", \"open a PR\", or asks how to share their solution.\n---\n\u003C!-- Copyright 2026 Anthropic PBC -->\n\u003C!-- SPDX-License-Identifier: Apache-2.0 -->\n\n\n# Submit your StockPilot solution\n\nYou're helping a workshop attendee package up their `agents\u002Fstarter\u002Fagent.py`\ndecomposition and open a PR. The PR is how facilitators see what approaches\npeople took, and the description doubles as the workshop feedback form.\n\n## Step 1 — Ask about their experience first\n\nBefore touching git, ask these three questions (use AskUserQuestion or just\nconversational):\n\n1. **Which subagent approach did you go with for cycle 3?**\n   (callable_agents \u002F spawn_subagent \u002F inline \u002F something else)\n2. **What was the hardest part of the workshop?**\n   (a specific cycle, a concept, the tooling, the timing)\n3. **One thing you'd change about it?**\n\nHold onto their answers — they go in the PR body.\n\n## Step 2 — Show them what they're submitting\n\n```bash\ngit diff main -- agent-decomposition\u002Fagents\u002Fstarter\u002Fagent.py\n```\n\nWalk through the diff briefly: which tools they dropped, which skills they\nenabled, which subagent approach they wired. If the diff is empty, they\nhaven't edited starter — ask if they worked in a different file.\n\nAlso grab their final eval score:\n\n```bash\nls -t evals\u002Freports\u002F*\u002Fstarter.json | head -1 | xargs cat | python -c \"import json,sys; d=json.load(sys.stdin); print(f'{d[\\\"score\\\"]:.0%}')\"\n```\n\n## Step 3 — Commit and push\n\n```bash\ngit checkout -b solution\u002F\u003Ctheir-name-or-handle>\ngit add agent-decomposition\u002Fagents\u002Fstarter\u002Fagent.py\ngit commit -m \"Workshop solution: \u003Csubagent approach>, \u003Cscore>%\"\ngit push -u origin solution\u002F\u003Ctheir-name-or-handle>\n```\n\nAsk for their name\u002Fhandle if you don't have it. If they don't have push\nrights to `anthropics\u002Fcwc-workshops`, have them fork first\n(`gh repo fork --clone=false`) and push to their fork.\n\n## Step 4 — Open the PR with feedback in the body\n\n```bash\ngh pr create --title \"Workshop solution — \u003Cname>\" --body-file -\n```\n\nPR body template (fill from step 1 + step 2):\n\n```markdown\n## My decomposition\n\n- Subagent approach: \u003Ccallable_agents | spawn_subagent | inline | other>\n- Final eval score: \u003CNN>%\n- Tools I dropped: \u003Clist>\n- Skills I enabled: \u003Clist>\n\n## Workshop feedback\n\n**Hardest part:** \u003Ctheir answer>\n\n**One thing I'd change:** \u003Ctheir answer>\n\n**Anything else:** \u003Cfree text — leave blank if nothing>\n```\n\n## Step 5 — Confirm\n\nGive them the PR URL and thank them. Mention that facilitators read every\nPR and the feedback directly shapes the next run of this workshop.\n\n## Don't\n\n- Don't open the PR before they've seen the diff and the body\n- Don't skip the feedback questions to \"save time\" — that's the point\n- Don't include `evals\u002Freports\u002F` or `.stockpilot_ids.json` in the commit\n","\u003C!-- Copyright 2026 Anthropic PBC -->\n\u003C!-- SPDX-License-Identifier: Apache-2.0 -->\n\n\n# Submit your StockPilot solution\n\nYou're helping a workshop attendee package up their `agents\u002Fstarter\u002Fagent.py`\ndecomposition and open a PR. The PR is how facilitators see what approaches\npeople took, and the description doubles as the workshop feedback form.\n\n## Step 1 — Ask about their experience first\n\nBefore touching git, ask these three questions (use AskUserQuestion or just\nconversational):\n\n1. **Which subagent approach did you go with for cycle 3?**\n   (callable_agents \u002F spawn_subagent \u002F inline \u002F something else)\n2. **What was the hardest part of the workshop?**\n   (a specific cycle, a concept, the tooling, the timing)\n3. **One thing you'd change about it?**\n\nHold onto their answers — they go in the PR body.\n\n## Step 2 — Show them what they're submitting\n\n```bash\ngit diff main -- agent-decomposition\u002Fagents\u002Fstarter\u002Fagent.py\n```\n\nWalk through the diff briefly: which tools they dropped, which skills they\nenabled, which subagent approach they wired. If the diff is empty, they\nhaven't edited starter — ask if they worked in a different file.\n\nAlso grab their final eval score:\n\n```bash\nls -t evals\u002Freports\u002F*\u002Fstarter.json | head -1 | xargs cat | python -c \"import json,sys; d=json.load(sys.stdin); print(f'{d[\\\"score\\\"]:.0%}')\"\n```\n\n## Step 3 — Commit and push\n\n```bash\ngit checkout -b solution\u002F\u003Ctheir-name-or-handle>\ngit add agent-decomposition\u002Fagents\u002Fstarter\u002Fagent.py\ngit commit -m \"Workshop solution: \u003Csubagent approach>, \u003Cscore>%\"\ngit push -u origin solution\u002F\u003Ctheir-name-or-handle>\n```\n\nAsk for their name\u002Fhandle if you don't have it. If they don't have push\nrights to `anthropics\u002Fcwc-workshops`, have them fork first\n(`gh repo fork --clone=false`) and push to their fork.\n\n## Step 4 — Open the PR with feedback in the body\n\n```bash\ngh pr create --title \"Workshop solution — \u003Cname>\" --body-file -\n```\n\nPR body template (fill from step 1 + step 2):\n\n```markdown\n## My decomposition\n\n- Subagent approach: \u003Ccallable_agents | spawn_subagent | inline | other>\n- Final eval score: \u003CNN>%\n- Tools I dropped: \u003Clist>\n- Skills I enabled: \u003Clist>\n\n## Workshop feedback\n\n**Hardest part:** \u003Ctheir answer>\n\n**One thing I'd change:** \u003Ctheir answer>\n\n**Anything else:** \u003Cfree text — leave blank if nothing>\n```\n\n## Step 5 — Confirm\n\nGive them the PR URL and thank them. Mention that facilitators read every\nPR and the feedback directly shapes the next run of this workshop.\n\n## Don't\n\n- Don't open the PR before they've seen the diff and the body\n- Don't skip the feedback questions to \"save time\" — that's the point\n- Don't include `evals\u002Freports\u002F` or `.stockpilot_ids.json` in the commit\n",{"name":5,"description":7},"main","2c65d16c6de16f8f24117d539a712ea706b5dee7","agent-decomposition\u002F.claude\u002Fskills\u002Fsubmit-solution",713,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops","https:\u002F\u002Fgithub.com\u002Fanthropics","https:\u002F\u002Fanthropic.com","2026-11-05 02:53:17",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add anthropics\u002Fcwc-workshops --skill submit-solution",{"tool":55,"command":56},"bunx","bunx skills add anthropics\u002Fcwc-workshops --skill submit-solution",{"tool":58,"command":59},"pnpm","pnpm dlx skills add anthropics\u002Fcwc-workshops --skill submit-solution","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops\u002Fblob\u002Fmain\u002Fagent-decomposition\u002F.claude\u002Fskills\u002Fsubmit-solution\u002FSKILL.md",true,[],[64,94,113,124,150,168],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":80,"publishedAt":36},"01M718CS4VJNEW3SRN5S3MG35W","postmortem-report","How the SRE team writes a postmortem PDF. Use this whenever asked for a postmortem, an incident report, a write-up to share, or a PDF of what happened.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops\u002Fblob\u002Fmain\u002Fship-your-first-managed-agent\u002Fskills\u002Fpostmortem-report\u002FSKILL.md",[70,75],{"categoryNo":71,"categoryName":72,"taxonomyType":73,"taxonomyTypeDesc":74},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[81,82,83,28,84,85,86,87,88,89,90,91,24,92,93],"postmortem report","postmortem","report","what happened","team","use","incident report","up","write","incident","for","PDF","sre",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":36},"01M718CPE2QT7TQMYAG56R19JW","incident-triage-runbook","The SRE team's runbook for triaging production latency and error-rate incidents. Use this whenever investigating an incident, a latency spike, elevated error rates, or when asked \"what caused X\" about a production service.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops\u002Fblob\u002Fmain\u002Fship-your-first-managed-agent\u002Fskills\u002Fincident-triage-runbook\u002FSKILL.md",[],[101,102,103,90,104,105,93,106,91,107,108,85,30,86,109,110,111,112],"runbook","triage","incident triage","incident triage runbook","error","latency","about","incidents","service","spike","Production","rate",{"skillNo":114,"name":115,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":36},"01M718CMK6R22RHEBDN1VW1YB5","eval-audit-and-sweep","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops\u002Fblob\u002Fmain\u002Frightmodel\u002F.claude\u002Fskills\u002Feval-audit-and-sweep\u002FSKILL.md",[],[119,120,121,122,123],"sweep","audit","eval audit and sweep","eval audit","eval",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":133,"publishedAt":36},"01M718CJ7RTEG518SSEJMH3H8H","edgartools-sec-data","How to pull SEC EDGAR data with the edgartools Python package — company lookup, filings, XBRL financial statements, and filing sections like Item 1A risk factors. Use whenever a task involves SEC filings, 10-K\u002F10-Q data, or company financials.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops\u002Fblob\u002Fmain\u002Fresearch-desk\u002Fskills\u002Fedgartools\u002FSKILL.md",[130],{"categoryNo":131,"categoryName":132,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000033","数据分析师",[134,135,136,137,138,139,24,27,140,86,141,33,142,143,144,145,146,147,148,149],"edgartools","edgartools sec data","data","lookup","filing","financial statements","task","package","python","company","company lookup","filings","risk","sec edgar","financials","pull",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":159,"publishedAt":36},"01M718CF9KPNBKPWFJN27XDN6A","workshop","Workshop coach for the Research Desk (SEC agents) workshop. Use when the user types \u002Fworkshop, asks for a workshop act or module (\"act 2\", \"next act\", \"where am I\"), wants a TODO(workshop-N) implemented or explained, or asks for help following WORKSHOP.md.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops\u002Fblob\u002Fmain\u002Fresearch-desk\u002F.claude\u002Fskills\u002Fworkshop\u002FSKILL.md",[156],{"categoryNo":157,"categoryName":158,"taxonomyType":73,"taxonomyTypeDesc":74},"01JBSEEDCAT000000000000021","资料检索与研究",[152,160,30,86,161,162,91,163,164,21,165,166,167],"todo","module","coach","types","research","act","help","next",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":175,"publishedAt":36},"01M718CD3EBG31CBH0KSPVX0YR","weekly-report","Structure and data sources for the weekly inventory report. Load this when the task is \"weekly report\", \"Monday report\", or \"summarize inventory status\".","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops\u002Fblob\u002Fmain\u002Fagent-decomposition\u002F.claude\u002Fskills\u002Fweekly-report\u002FSKILL.md",[174],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},[176,177,83,30,178,140,179,136,180,181,91,182,183,184,185],"Weekly Report","weekly","summarize","load","status","inventory","data sources","monday","structure","sources"]