[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HDGFH2FK6Q9T69Z86W0YR":3,"skill-same:01M71HDGFH2FK6Q9T69Z86W0YR":83},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":62,"install":63,"resources":76},"01M71HDGFH2FK6Q9T69Z86W0YR","slack-web",null,"Slack web automation via agent-browser. Use when the user asks to check Slack, read messages, send messages, reply in threads, search Slack, check notifications, react to messages, send DMs, or any Slack communication task. Triggers include \"check my Slack\", \"send a message on Slack\", \"reply to that Slack thread\", \"search Slack for...\", \"what's new on Slack\", \"read my DMs\", \"react to that message\", \"check Slack notifications\", \"message [person] on Slack\".","runecraftai\u002Farcanum","runecraftai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F279098826?v=4","01M71HBGS1RCAJ490RAYST7M00","01M71HBGT1CB94MNS6T6SGAZKW",1,"MIT","https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Ffamiliar\u002Fskills\u002Fslack-web\u002FSKILL.md",[17,22,25],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000005","邮件与沟通","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"slack","web","slack web","for","my","read","communication","message","threads","browser","notifications","react","Bash","web automation","when","new","send","messages","search","agent-browser","2026-11-10 10:12:30",false,"---\nname: slack-web\ndescription: >\n  Slack web automation via agent-browser. Use when the user asks to check Slack,\n  read messages, send messages, reply in threads, search Slack, check notifications,\n  react to messages, send DMs, or any Slack communication task. Triggers include\n  \"check my Slack\", \"send a message on Slack\", \"reply to that Slack thread\",\n  \"search Slack for...\", \"what's new on Slack\", \"read my DMs\", \"react to that message\",\n  \"check Slack notifications\", \"message [person] on Slack\".\nallowed-tools: Bash(agent-browser:*)\n---\n\n# Slack Web Automation\n\nInteract with Slack through its web interface using `agent-browser`.\n\n## Core Workflow\n\nEvery Slack interaction follows this pattern:\n\n1. **Restore session**: `agent-browser state load ~\u002F.slack-auth-state.json`\n2. **Open Slack**: `agent-browser --headed open \"https:\u002F\u002Fapp.slack.com\"`\n3. **Snapshot**: `agent-browser snapshot -i -c` (get refs)\n4. **Interact**: Use refs to click, type, navigate\n5. **Re-snapshot**: After every action — Slack's DOM changes constantly\n\n```bash\n# Restore and open\nagent-browser state load ~\u002F.slack-auth-state.json\nagent-browser --headed open \"https:\u002F\u002Fapp.slack.com\"\nagent-browser wait --load networkidle\nagent-browser set viewport 1920 1080\n\n# Verify logged in (URL should contain \u002Fclient\u002F)\nagent-browser get url\n\n# Navigate with quick switcher\nagent-browser press \"Meta+k\"\nagent-browser wait 500\nagent-browser snapshot -i\nagent-browser fill @eXX \"general\"\nagent-browser wait 1000\nagent-browser snapshot -i\nagent-browser click @eXX\nagent-browser wait --load networkidle\n\n# Read messages\nagent-browser snapshot -c\n```\n\n## Authentication\n\n### First-Time Login (Manual)\n\n```bash\nagent-browser --headed open \"https:\u002F\u002Fapp.slack.com\"\n# PAUSE — tell user to log in manually\n# After login confirmed:\nagent-browser get url  # verify \u002Fclient\u002F in URL\nagent-browser state save ~\u002F.slack-auth-state.json\n```\n\n### Restore Session\n\n```bash\nagent-browser state load ~\u002F.slack-auth-state.json\nagent-browser --headed open \"https:\u002F\u002Fapp.slack.com\"\nagent-browser wait --load networkidle\nagent-browser get url\n# If URL contains \"signin\" → session expired, user must re-login\n```\n\n## Actions\n\n### Read Messages\n\n```bash\n# Navigate to channel (quick switcher is fastest)\nagent-browser press \"Meta+k\"\nagent-browser wait 500\nagent-browser snapshot -i\nagent-browser fill @eXX \"channel-name\"\nagent-browser wait 1000\nagent-browser snapshot -i\nagent-browser click @eXX\nagent-browser wait --load networkidle\n\n# Read\nagent-browser snapshot -c\n```\n\n### Send a Message\n\n```bash\n# In the target channel, find compose box\nagent-browser snapshot -i\n# Look for textbox with \"Message #channel\" placeholder\nagent-browser click @eXX  # compose area\nagent-browser type @eXX \"Your message\"\nagent-browser press \"Enter\"\nagent-browser wait 1000\nagent-browser snapshot -c  # verify sent\n```\n\nUse `type` not `fill` — Slack's compose box is contenteditable.\n\n### Reply to Thread\n\n```bash\nagent-browser snapshot -c\nagent-browser hover @eXX  # hover message to show toolbar\nagent-browser snapshot -i\nagent-browser click @eXX  # reply\u002Fthread button\nagent-browser wait --load networkidle\nagent-browser snapshot -i\nagent-browser click @eXX  # thread compose box\nagent-browser type @eXX \"Thread reply\"\nagent-browser press \"Enter\"\n```\n\n### Send DM\n\n```bash\nagent-browser press \"Meta+k\"\nagent-browser wait 500\nagent-browser snapshot -i\nagent-browser fill @eXX \"Person Name\"\nagent-browser wait 1000\nagent-browser snapshot -i\nagent-browser click @eXX  # person result\nagent-browser wait --load networkidle\nagent-browser snapshot -i\nagent-browser click @eXX  # compose box\nagent-browser type @eXX \"Your DM\"\nagent-browser press \"Enter\"\n```\n\n### Search\n\n```bash\nagent-browser press \"Meta+g\"  # Slack search\nagent-browser wait 500\nagent-browser snapshot -i\nagent-browser fill @eXX \"search query\"\nagent-browser press \"Enter\"\nagent-browser wait --load networkidle\nagent-browser snapshot -c\n```\n\n### React with Emoji\n\n```bash\nagent-browser snapshot -c\nagent-browser hover @eXX  # hover over message\nagent-browser snapshot -i\nagent-browser click @eXX  # emoji\u002Freaction button (smiley icon)\nagent-browser wait 500\nagent-browser snapshot -i\nagent-browser fill @eXX \"thumbsup\"  # emoji search\nagent-browser wait 500\nagent-browser snapshot -i\nagent-browser click @eXX  # emoji result\n```\n\n### Check Notifications\n\n```bash\n# Click \"Activity\" in sidebar or navigate:\nagent-browser snapshot -i -c\nagent-browser click @eXX  # Activity link\nagent-browser wait --load networkidle\nagent-browser snapshot -c\n```\n\n### Check Unreads\n\n```bash\nagent-browser snapshot -i -c\n# Look for bold channel names or \"Unreads\" section\nagent-browser click @eXX  # Unreads link\nagent-browser wait --load networkidle\nagent-browser snapshot -c\n```\n\n## Critical Rules\n\n1. **ALWAYS re-snapshot** after every action — refs invalidate constantly\n2. **Use `--headed`** mode so user can see and intervene\n3. **Set viewport 1920x1080** — Slack hides features at small widths\n4. **Use `Meta+k`** (quick switcher) as primary navigation\n5. **Use `type` not `fill`** for compose boxes (contenteditable)\n6. **Wait after actions**: `agent-browser wait --load networkidle`\n7. **Save auth state often**: `agent-browser state save ~\u002F.slack-auth-state.json`\n\n## Semantic Locator Fallbacks\n\nWhen refs don't match:\n\n```bash\nagent-browser find text \"general\" click\nagent-browser find role textbox fill \"Hello\"\nagent-browser find placeholder \"Message #general\" type \"Hello\"\nagent-browser find role button click --name \"Send\"\n```\n\n## Debugging\n\n```bash\nagent-browser screenshot \u002Ftmp\u002Fslack-debug.png\nagent-browser get url\nagent-browser snapshot  # full unfiltered tree\n```\n\n## Deep-Dive References\n\n| Reference | When to Use |\n|-----------|-------------|\n| [references\u002Fworkflows.md](references\u002Fworkflows.md) | Full workflow examples |\n","# Slack Web Automation\n\nInteract with Slack through its web interface using `agent-browser`.\n\n## Core Workflow\n\nEvery Slack interaction follows this pattern:\n\n1. **Restore session**: `agent-browser state load ~\u002F.slack-auth-state.json`\n2. **Open Slack**: `agent-browser --headed open \"https:\u002F\u002Fapp.slack.com\"`\n3. **Snapshot**: `agent-browser snapshot -i -c` (get refs)\n4. **Interact**: Use refs to click, type, navigate\n5. **Re-snapshot**: After every action — Slack's DOM changes constantly\n\n```bash\n# Restore and open\nagent-browser state load ~\u002F.slack-auth-state.json\nagent-browser --headed open \"https:\u002F\u002Fapp.slack.com\"\nagent-browser wait --load networkidle\nagent-browser set viewport 1920 1080\n\n# Verify logged in (URL should contain \u002Fclient\u002F)\nagent-browser get url\n\n# Navigate with quick switcher\nagent-browser press \"Meta+k\"\nagent-browser wait 500\nagent-browser snapshot -i\nagent-browser fill @eXX \"general\"\nagent-browser wait 1000\nagent-browser snapshot -i\nagent-browser click @eXX\nagent-browser wait --load networkidle\n\n# Read messages\nagent-browser snapshot -c\n```\n\n## Authentication\n\n### First-Time Login (Manual)\n\n```bash\nagent-browser --headed open \"https:\u002F\u002Fapp.slack.com\"\n# PAUSE — tell user to log in manually\n# After login confirmed:\nagent-browser get url  # verify \u002Fclient\u002F in URL\nagent-browser state save ~\u002F.slack-auth-state.json\n```\n\n### Restore Session\n\n```bash\nagent-browser state load ~\u002F.slack-auth-state.json\nagent-browser --headed open \"https:\u002F\u002Fapp.slack.com\"\nagent-browser wait --load networkidle\nagent-browser get url\n# If URL contains \"signin\" → session expired, user must re-login\n```\n\n## Actions\n\n### Read Messages\n\n```bash\n# Navigate to channel (quick switcher is fastest)\nagent-browser press \"Meta+k\"\nagent-browser wait 500\nagent-browser snapshot -i\nagent-browser fill @eXX \"channel-name\"\nagent-browser wait 1000\nagent-browser snapshot -i\nagent-browser click @eXX\nagent-browser wait --load networkidle\n\n# Read\nagent-browser snapshot -c\n```\n\n### Send a Message\n\n```bash\n# In the target channel, find compose box\nagent-browser snapshot -i\n# Look for textbox with \"Message #channel\" placeholder\nagent-browser click @eXX  # compose area\nagent-browser type @eXX \"Your message\"\nagent-browser press \"Enter\"\nagent-browser wait 1000\nagent-browser snapshot -c  # verify sent\n```\n\nUse `type` not `fill` — Slack's compose box is contenteditable.\n\n### Reply to Thread\n\n```bash\nagent-browser snapshot -c\nagent-browser hover @eXX  # hover message to show toolbar\nagent-browser snapshot -i\nagent-browser click @eXX  # reply\u002Fthread button\nagent-browser wait --load networkidle\nagent-browser snapshot -i\nagent-browser click @eXX  # thread compose box\nagent-browser type @eXX \"Thread reply\"\nagent-browser press \"Enter\"\n```\n\n### Send DM\n\n```bash\nagent-browser press \"Meta+k\"\nagent-browser wait 500\nagent-browser snapshot -i\nagent-browser fill @eXX \"Person Name\"\nagent-browser wait 1000\nagent-browser snapshot -i\nagent-browser click @eXX  # person result\nagent-browser wait --load networkidle\nagent-browser snapshot -i\nagent-browser click @eXX  # compose box\nagent-browser type @eXX \"Your DM\"\nagent-browser press \"Enter\"\n```\n\n### Search\n\n```bash\nagent-browser press \"Meta+g\"  # Slack search\nagent-browser wait 500\nagent-browser snapshot -i\nagent-browser fill @eXX \"search query\"\nagent-browser press \"Enter\"\nagent-browser wait --load networkidle\nagent-browser snapshot -c\n```\n\n### React with Emoji\n\n```bash\nagent-browser snapshot -c\nagent-browser hover @eXX  # hover over message\nagent-browser snapshot -i\nagent-browser click @eXX  # emoji\u002Freaction button (smiley icon)\nagent-browser wait 500\nagent-browser snapshot -i\nagent-browser fill @eXX \"thumbsup\"  # emoji search\nagent-browser wait 500\nagent-browser snapshot -i\nagent-browser click @eXX  # emoji result\n```\n\n### Check Notifications\n\n```bash\n# Click \"Activity\" in sidebar or navigate:\nagent-browser snapshot -i -c\nagent-browser click @eXX  # Activity link\nagent-browser wait --load networkidle\nagent-browser snapshot -c\n```\n\n### Check Unreads\n\n```bash\nagent-browser snapshot -i -c\n# Look for bold channel names or \"Unreads\" section\nagent-browser click @eXX  # Unreads link\nagent-browser wait --load networkidle\nagent-browser snapshot -c\n```\n\n## Critical Rules\n\n1. **ALWAYS re-snapshot** after every action — refs invalidate constantly\n2. **Use `--headed`** mode so user can see and intervene\n3. **Set viewport 1920x1080** — Slack hides features at small widths\n4. **Use `Meta+k`** (quick switcher) as primary navigation\n5. **Use `type` not `fill`** for compose boxes (contenteditable)\n6. **Wait after actions**: `agent-browser wait --load networkidle`\n7. **Save auth state often**: `agent-browser state save ~\u002F.slack-auth-state.json`\n\n## Semantic Locator Fallbacks\n\nWhen refs don't match:\n\n```bash\nagent-browser find text \"general\" click\nagent-browser find role textbox fill \"Hello\"\nagent-browser find placeholder \"Message #general\" type \"Hello\"\nagent-browser find role button click --name \"Send\"\n```\n\n## Debugging\n\n```bash\nagent-browser screenshot \u002Ftmp\u002Fslack-debug.png\nagent-browser get url\nagent-browser snapshot  # full unfiltered tree\n```\n\n## Deep-Dive References\n\n| Reference | When to Use |\n|-----------|-------------|\n| [references\u002Fworkflows.md](references\u002Fworkflows.md) | Full workflow examples |\n",{"name":5,"description":54,"allowed-tools":55},"Slack web automation via agent-browser. Use when the user asks to check Slack, read messages, send messages, reply in threads, search Slack, check notifications, react to messages, send DMs, or any Slack communication task. Triggers include \"check my Slack\", \"send a message on Slack\", \"reply to that Slack thread\", \"search Slack for...\", \"what's new on Slack\", \"read my DMs\", \"react to that message\", \"check Slack notifications\", \"message [person] on Slack\".\n","Bash(agent-browser:*)","main","33b040feb49e126600394272a8e321a3cd279e8b","packages\u002Ffamiliar\u002Fskills\u002Fslack-web",0,"https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum","https:\u002F\u002Fgithub.com\u002Frunecraftai","2026-07-29 22:08:52",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add runecraftai\u002Farcanum --skill slack-web",{"tool":69,"command":70},"bunx","bunx skills add runecraftai\u002Farcanum --skill slack-web",{"tool":72,"command":73},"pnpm","pnpm dlx skills add runecraftai\u002Farcanum --skill slack-web","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Ffamiliar\u002Fskills\u002Fslack-web\u002FSKILL.md",true,[77],{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fworkflows.md","REFERENCE","参考文档",3118,"https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Ffamiliar\u002Fskills\u002Fslack-web\u002Freferences\u002Fworkflows.md",[84,112,136,162,183,207],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":92,"publishedAt":49},"01M71HGTN9FRQ3WEZMVVX7C3VZ","using-agent-skills","Discovers and invokes the right @runecraft\u002Fspells skill for the current task. Use when starting a session, when a request is ambiguous about which workflow to apply, or when you need to pick among the 13-skill Arcanum catalog. EN triggers: \u002Fskill, which skill, pick a skill, what skill should I use, skill discovery, meta skill. PT triggers: qual skill, qual habilidade, descobrir skill, qual fluxo usar. Do NOT use for: actual implementation work (route to the specific skill instead), unrelated standalone tasks outside the Arcanum catalog, or runtime-specific configuration (e.g., opencode.json \u002F Claude Code plugin paths).","CC-BY-4.0","https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Fspells\u002Fskills\u002Fusing-agent-skills\u002FSKILL.md",[91],{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},[93,94,95,96,97,98,43,99,100,101,102,103,104,105,106,107,108,109,110,111],"using agent skills","standalone","which","pt","pick","Meta","workflow","you","code","tasks","skill discovery","route","work","unrelated","opencode","request","paths","a skill","ambiguous",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":49},"01M71HGPD6N9JH2G8EVBXJR77X","typescript-patterns","TypeScript best practices and patterns for type-safe, maintainable code. Covers discriminated unions, generics, const assertions, type narrowing, and common anti-patterns. Extends (does not override) project tsconfig. EN triggers: \u002Ftypescript, TypeScript patterns, TS best practices, type safety, discriminated unions, generics, type narrowing. PT triggers: \u002Ftypescript, padrões TypeScript, boas práticas TS, segurança de tipos, unions discriminadas, genéricos. Do NOT use for: JavaScript-only projects, runtime performance, or replacing project tsconfig rules.","https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Fspells\u002Fskills\u002Ftypescript-patterns\u002FSKILL.md",[],[119,120,121,122,123,32,96,124,125,126,127,128,129,130,131,132,133,134,101,135],"typescript","patterns","typescript patterns","do","projects","runtime","project","performance","en","maintainable code","triggers","only","use","assertions","Rules","best practices","common",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":148,"publishedAt":49},"01M71HGJAKX4TFN0PECYPJ9S38","test-driven-development","Drives development with tests — fail first, then make them pass, then refactor. Use when implementing any logic, fixing any bug, or changing any behavior. EN triggers: \u002Ftest, write tests first, TDD, prove it, 80\u002F15\u002F5 pyramid, Beyonce Rule. PT triggers: \u002Fteste, testes primeiro, provar com teste, pirâmide 80\u002F15\u002F5. Do NOT use for: production incident triage (use \u002Fdebug), or cosmetic-only changes with no behavioral surface.","https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Fspells\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[142,145],{"categoryNo":143,"categoryName":144,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":146,"categoryName":147,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",[149,150,151,152,96,153,154,155,130,43,156,157,158,159,160,122,32,127,129,161],"test driven development","development","test","driven","incident","implementing","write tests","write","bug","refactor","behavioral","make","tests",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":168,"publishedAt":49},"01M71HGC1H4JQFJWH613XTJC59","spec-driven","Feature planning and implementation with 4 adaptive phases — Specify, Design, Tasks, Execute. Auto-sizes depth by complexity. Creates atomic tasks with verification criteria, atomic git commits, and requirement traceability. Features an independent Verifier (author != verifier, evidence-or-zero), persistent decision log (STATE.md), and test-coverage-matrix-driven tests, plus a self-improving lessons layer that turns verification failures into reusable project-local guidance. Stack-agnostic. Use when planning features (requirements, design, task breakdown), implementing with verification and atomic commits, or validating\u002Fverifying an implementation against a spec. Triggers (PT\u002FEN): \"specify feature\", \"vamos especificar\", \"discutir feature\", \"discutir este caso\", \"design\", \"design da feature\", \"tarefas\", \"quebrar em tarefas\", \"implementar\", \"build\", \"validar\", \"verify work\", \"UAT\", \"validar implementação\", \"record decision\", \"pause work\", \"pausar trabalho\", \"resume work\", \"retomar trabalho\". Do NOT use for architecture decomposition analysis (use architecture skills) or technical design docs (treat as Complex scope: discuss gray areas + architecture-focused design).","https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Fspells\u002Fskills\u002Fspec-driven\u002FSKILL.md",[],[169,170,152,171,172,173,174,96,125,175,154,176,177,178,179,180,43,181,102,182],"spec driven","spec","coverage","complexity","task breakdown","scope","decision","local","design","self-improving","auto","atomic commits","analysis","architecture",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":193,"publishedAt":49},"01M71HG5CSP04F29HRAG7XVYKG","skill-forge","Designs, authors, validates, and optimizes new Agent Skills from scratch. Use when creating a new skill, packaging a workflow as a skill, improving a skill's triggering accuracy, or evaluating whether a skill improves output quality. Covers the full lifecycle: DISCOVER, DESIGN, AUTHOR, VALIDATE, OPTIMIZE, DELIVER. Produces skills that follow the open SKILL.md format (YAML frontmatter + Markdown body, progressive disclosure, validation loops). EN triggers: \u002Fforge, create a skill, write a skill, build a skill, new skill, author a skill, package this as a skill, validate a skill, improve skill triggering, optimize skill description, evaluate skill quality. PT triggers: \u002Fforge, criar uma skill, escrever uma skill, construir uma skill, nova skill, empacotar como skill, validar skill, melhorar disparo, otimizar descrição de skill. Do NOT use for: discovering which existing skill to apply (use a dispatch\u002Fmeta skill), planning feature implementation, or designing software architecture.","https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Fspells\u002Fskills\u002Fskill-forge\u002FSKILL.md",[189,192],{"categoryNo":190,"categoryName":191,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},[194,195,196,95,197,198,96,199,98,200,201,177,182,202,203,156,204,110,205,206],"forge","skill forge","deliver","new agent","feature implementation","packaging","improve","open","create","de","software","new skill","full",{"skillNo":208,"name":209,"nameZh":6,"description":210,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":211,"categories":212,"keywords":213,"publishedAt":49},"01M71HG1RAQY3GXX0Q5TMW0XD6","shipping-and-launch","Prepares production launches with a pre-launch checklist, staged rollout, monitoring, and a rollback strategy — plus feature flag lifecycle (off → internal → beta → GA). Use when deploying a feature to production for the first time, releasing a significant change, or planning a rollout. EN triggers: \u002Fship, pre-launch checklist, staged rollout, feature flag, rollback plan, monitoring. PT triggers: \u002Fshippar, checklist pré-lançamento, rollout gradual, feature flag, plano de rollback. Do NOT use for: pre-production development work, or one-off internal tools with no user exposure.","https:\u002F\u002Fgithub.com\u002Frunecraftai\u002Farcanum\u002Fblob\u002Fmain\u002Fpackages\u002Fspells\u002Fskills\u002Fshipping-and-launch\u002FSKILL.md",[],[214,215,216,96,217,218,43,219,220,221,222,105,223,224,225,226,203,227,228,229],"shipping and launch","shipping","launch","time","beta","rollout","rollback plan","monitoring","rollback strategy","plan","change","exposure","plano","ship","Tools","pre-launch"]