[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DBY3Y8B9KBPGFPHD1QPW5B":3,"skill-same:01M6DBY3Y8B9KBPGFPHD1QPW5B":56},{"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":23,"publishedAt":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":14,"repositoryHtmlUrl":39,"repositoryHomepageUrl":6,"ownerHtmlUrl":40,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":41,"install":42,"resources":55},"01M6DBY3Y8B9KBPGFPHD1QPW5B","source-command-aside",null,"Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsource-command-aside\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[24,25,26,27,28,29,30],"command","source command aside","work","question","context","resume","task","2026-11-10 10:12:30",false,"---\nname: \"source-command-aside\"\ndescription: \"Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.\"\n---\n\n# source-command-aside\n\nUse this skill when the user asks to run the migrated source command `aside`.\n\n## Command Template\n\n# Aside Command\n\nAsk a question mid-task and get an immediate, focused answer — then continue right where you left off. The current task, files, and context are never modified.\n\n## When to Use\n\n- You're curious about something while Codex is working and don't want to lose momentum\n- You need a quick explanation of code Codex is currently editing\n- You want a second opinion or clarification on a decision without derailing the task\n- You need to understand an error, concept, or pattern before Codex proceeds\n- You want to ask something unrelated to the current task without starting a new session\n\n## Usage\n\n```\n\u002Faside \u003Cyour question>\n\u002Faside what does this function actually return?\n\u002Faside is this pattern thread-safe?\n\u002Faside why are we using X instead of Y here?\n\u002Faside what's the difference between foo() and bar()?\n\u002Faside should we be worried about the N+1 query we just added?\n```\n\n## Process\n\n### Step 1: Freeze the current task state\n\nBefore answering anything, mentally note:\n- What is the active task? (what file, feature, or problem was being worked on)\n- What step was in progress at the moment `\u002Faside` was invoked?\n- What was about to happen next?\n\nDo NOT touch, edit, create, or delete any files during the aside.\n\n### Step 2: Answer the question directly\n\nAnswer the question in the most concise form that is still complete and useful.\n\n- Lead with the answer, not the reasoning\n- Keep it short — if a full explanation is needed, offer to go deeper after the task\n- If the question is about the current file or code being worked on, reference it precisely (file path and line number if relevant)\n- If answering requires reading a file, read it — but read only, never write\n\nFormat the response as:\n\n```\nASIDE: [restate the question briefly]\n\n[Your answer here]\n\n— Back to task: [one-line description of what was being done]\n```\n\n### Step 3: Resume the main task\n\nAfter delivering the answer, immediately continue the active task from the exact point it was paused. Do not ask for permission to resume unless the aside answer revealed a blocker or a reason to reconsider the current approach (see Edge Cases).\n\n---\n\n## Edge Cases\n\n**No question provided (`\u002Faside` with nothing after it):**\nRespond:\n```\nASIDE: no question provided\n\nWhat would you like to know? (ask your question and I'll answer without losing the current task context)\n\n— Back to task: [one-line description of what was being done]\n```\n\n**Question reveals a potential problem with the current task:**\nFlag it clearly before resuming:\n```\nASIDE: [answer]\n\n⚠️ Note: This answer suggests [issue] with the current approach. Want to address this before continuing, or proceed as planned?\n```\nWait for the user's decision before resuming.\n\n**Question is actually a task redirect (not a side question):**\nIf the question implies changing what is being built (e.g., `\u002Faside actually, let's use Redis instead`), clarify:\n```\nASIDE: That sounds like a direction change, not just a side question.\nDo you want to:\n  (a) Answer this as information only and keep the current plan\n  (b) Pause the current task and change approach\n```\nWait for the user's answer — do not make assumptions.\n\n**Question is about the currently open file or code:**\nAnswer from the live context. If the file was read earlier in the session, reference it directly. If not, read it now (read-only) and answer with a file:line reference.\n\n**No active task (nothing in progress when `\u002Faside` is invoked):**\nStill use the standard wrapper so the response shape stays consistent:\n```\nASIDE: [restate the question briefly]\n\n[Your answer here]\n\n— Back to task: no active task to resume\n```\n\n**Question requires a long answer:**\nGive the essential answer concisely, then offer:\n```\nThat's the short version. Want a deeper explanation after we finish [current task]?\n```\n\n**Multiple `\u002Faside` questions in a row:**\nAnswer each one in sequence. After the last answer, resume the main task. Do not lose task state across a chain of asides.\n\n**Aside answer implies a code change is needed:**\nNote the change needed but do not make it during the aside:\n```\nASIDE: [answer]\n\n? Worth fixing: [what should be changed]. I'll flag this after the current task unless you want to address it now.\n```\n\n**Question is ambiguous or too vague:**\nAsk one clarifying question — the shortest question that gets the information needed to answer. Do not ask multiple questions.\n\n---\n\n## Example Output\n\n```\nUser: \u002Faside what does fetchWithRetry() actually do?\n\nASIDE: what does fetchWithRetry() do?\n\nfetchWithRetry() (src\u002Fapi\u002Fretry.ts:12) attempts the request up to 3 times with\nexponential backoff (250ms → 500ms → 1s). It only retries on 5xx responses and\nnetwork errors — 4xx errors are treated as final and not retried.\n\n— Back to task: refactoring the auth middleware in src\u002Fmiddleware\u002Fauth.ts\n```\n\n```\nUser: \u002Faside is the approach we're taking thread-safe?\n\nASIDE: is the current approach thread-safe?\n\nNo — the shared cache object in src\u002Fcache\u002Fstore.ts:34 is mutated without locking.\nUnder concurrent requests this is a race condition. It's low risk in a single-process\nNode.js server but would be a real problem with worker threads or clustering.\n\n⚠️ Note: This could affect the feature we're building. Want to address this now or continue and fix it in a follow-up?\n```\n\n---\n\n## Notes\n\n- Never modify files during an aside — read-only access only\n- The aside is a conversation pause, not a new task — the original task must always resume\n- Keep answers focused: the goal is to unblock the user quickly, not to deliver a lecture\n- If an aside sparks a larger discussion, finish the current task first unless the aside reveals a blocker\n- Asides are not saved to session files unless explicitly relevant to the task outcome\n","# source-command-aside\n\nUse this skill when the user asks to run the migrated source command `aside`.\n\n## Command Template\n\n# Aside Command\n\nAsk a question mid-task and get an immediate, focused answer — then continue right where you left off. The current task, files, and context are never modified.\n\n## When to Use\n\n- You're curious about something while Codex is working and don't want to lose momentum\n- You need a quick explanation of code Codex is currently editing\n- You want a second opinion or clarification on a decision without derailing the task\n- You need to understand an error, concept, or pattern before Codex proceeds\n- You want to ask something unrelated to the current task without starting a new session\n\n## Usage\n\n```\n\u002Faside \u003Cyour question>\n\u002Faside what does this function actually return?\n\u002Faside is this pattern thread-safe?\n\u002Faside why are we using X instead of Y here?\n\u002Faside what's the difference between foo() and bar()?\n\u002Faside should we be worried about the N+1 query we just added?\n```\n\n## Process\n\n### Step 1: Freeze the current task state\n\nBefore answering anything, mentally note:\n- What is the active task? (what file, feature, or problem was being worked on)\n- What step was in progress at the moment `\u002Faside` was invoked?\n- What was about to happen next?\n\nDo NOT touch, edit, create, or delete any files during the aside.\n\n### Step 2: Answer the question directly\n\nAnswer the question in the most concise form that is still complete and useful.\n\n- Lead with the answer, not the reasoning\n- Keep it short — if a full explanation is needed, offer to go deeper after the task\n- If the question is about the current file or code being worked on, reference it precisely (file path and line number if relevant)\n- If answering requires reading a file, read it — but read only, never write\n\nFormat the response as:\n\n```\nASIDE: [restate the question briefly]\n\n[Your answer here]\n\n— Back to task: [one-line description of what was being done]\n```\n\n### Step 3: Resume the main task\n\nAfter delivering the answer, immediately continue the active task from the exact point it was paused. Do not ask for permission to resume unless the aside answer revealed a blocker or a reason to reconsider the current approach (see Edge Cases).\n\n---\n\n## Edge Cases\n\n**No question provided (`\u002Faside` with nothing after it):**\nRespond:\n```\nASIDE: no question provided\n\nWhat would you like to know? (ask your question and I'll answer without losing the current task context)\n\n— Back to task: [one-line description of what was being done]\n```\n\n**Question reveals a potential problem with the current task:**\nFlag it clearly before resuming:\n```\nASIDE: [answer]\n\n⚠️ Note: This answer suggests [issue] with the current approach. Want to address this before continuing, or proceed as planned?\n```\nWait for the user's decision before resuming.\n\n**Question is actually a task redirect (not a side question):**\nIf the question implies changing what is being built (e.g., `\u002Faside actually, let's use Redis instead`), clarify:\n```\nASIDE: That sounds like a direction change, not just a side question.\nDo you want to:\n  (a) Answer this as information only and keep the current plan\n  (b) Pause the current task and change approach\n```\nWait for the user's answer — do not make assumptions.\n\n**Question is about the currently open file or code:**\nAnswer from the live context. If the file was read earlier in the session, reference it directly. If not, read it now (read-only) and answer with a file:line reference.\n\n**No active task (nothing in progress when `\u002Faside` is invoked):**\nStill use the standard wrapper so the response shape stays consistent:\n```\nASIDE: [restate the question briefly]\n\n[Your answer here]\n\n— Back to task: no active task to resume\n```\n\n**Question requires a long answer:**\nGive the essential answer concisely, then offer:\n```\nThat's the short version. Want a deeper explanation after we finish [current task]?\n```\n\n**Multiple `\u002Faside` questions in a row:**\nAnswer each one in sequence. After the last answer, resume the main task. Do not lose task state across a chain of asides.\n\n**Aside answer implies a code change is needed:**\nNote the change needed but do not make it during the aside:\n```\nASIDE: [answer]\n\n? Worth fixing: [what should be changed]. I'll flag this after the current task unless you want to address it now.\n```\n\n**Question is ambiguous or too vague:**\nAsk one clarifying question — the shortest question that gets the information needed to answer. Do not ask multiple questions.\n\n---\n\n## Example Output\n\n```\nUser: \u002Faside what does fetchWithRetry() actually do?\n\nASIDE: what does fetchWithRetry() do?\n\nfetchWithRetry() (src\u002Fapi\u002Fretry.ts:12) attempts the request up to 3 times with\nexponential backoff (250ms → 500ms → 1s). It only retries on 5xx responses and\nnetwork errors — 4xx errors are treated as final and not retried.\n\n— Back to task: refactoring the auth middleware in src\u002Fmiddleware\u002Fauth.ts\n```\n\n```\nUser: \u002Faside is the approach we're taking thread-safe?\n\nASIDE: is the current approach thread-safe?\n\nNo — the shared cache object in src\u002Fcache\u002Fstore.ts:34 is mutated without locking.\nUnder concurrent requests this is a race condition. It's low risk in a single-process\nNode.js server but would be a real problem with worker threads or clustering.\n\n⚠️ Note: This could affect the feature we're building. Want to address this now or continue and fix it in a follow-up?\n```\n\n---\n\n## Notes\n\n- Never modify files during an aside — read-only access only\n- The aside is a conversation pause, not a new task — the original task must always resume\n- Keep answers focused: the goal is to unblock the user quickly, not to deliver a lecture\n- If an aside sparks a larger discussion, finish the current task first unless the aside reveals a blocker\n- Asides are not saved to session files unless explicitly relevant to the task outcome\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fsource-command-aside","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill source-command-aside",{"tool":48,"command":49},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill source-command-aside",{"tool":51,"command":52},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill source-command-aside","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsource-command-aside\u002FSKILL.md",true,[],[57,77,108,135,149,164],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":31},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[64,65,66,67,68,30,69,70,71,72,28,73,74,75,76],"clarify requirements","clarify","requirements","risk","options","prompts","goal","scanning","use","repo","injection","execution","file",{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":88,"publishedAt":31},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[83],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[89,90,91,92,93,94,95,96,97,98,99,100,101,102,72,103,104,105,106,107],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":120,"publishedAt":31},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[114,117],{"categoryNo":115,"categoryName":116,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":118,"categoryName":119,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000008","测试与质量",[121,122,123,124,125,126,127,128,129,130,90,131,132,133,134],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":31},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[137,142,143,144,145,146,147,148],"setup","report","project","installation","project setup","issues","state",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":156,"publishedAt":31},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[155],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},[151,157,30,158,159,160,72,161,26,162,163],"start issue","issue","ready","work on issue","user","work on","development",{"skillNo":165,"name":142,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":169,"publishedAt":31},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[142,144,105,170,146,171],"files","interactive"]