[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DCQC9F50MHMVVYZ5NMFHYP":3,"skill-same:01M6DCQC9F50MHMVVYZ5NMFHYP":74},{"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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":14,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":59,"install":60,"resources":73},"01M6DCQC9F50MHMVVYZ5NMFHYP","mcp-code-orchestrate",null,"Use when one task needs the SAME tool-call shape repeated across MANY items - an xref-walk over dozens of functions, a descriptor sweep over many SMILES, batch-resolving or screening a list of papers, or aggregating one query across several MCP servers. Write ONE script (Python via the Bash tool) that calls the underlying provider CLIs, native libraries, or MCP stdio, filters and aggregates IN-CODE, and returns ONLY the distilled result, instead of N model round-trips that each bloat context with raw tool output. This is Anthropic's code-execution-with-MCP pattern (up to ~98.7% fewer tokens on fan-out work). Decision rule - reach for it once you would otherwise make more than about 5 same-shape tool calls. Not for a single tool call.","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\u002Fplatform\u002Frouting\u002Ffixtures\u002Fhome\u002F.agents\u002Fskills\u002Fmcp-code-orchestrate\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"mcp code orchestrate","code","orchestrate","MCP","list","across","pattern","aggregates","query","filters","up","only","context","write","work","decision","model","Bash","batch","libraries","2026-11-10 10:12:30",false,"---\nname: mcp-code-orchestrate\ndescription: Use when one task needs the SAME tool-call shape repeated across MANY items - an xref-walk over dozens of functions, a descriptor sweep over many SMILES, batch-resolving or screening a list of papers, or aggregating one query across several MCP servers. Write ONE script (Python via the Bash tool) that calls the underlying provider CLIs, native libraries, or MCP stdio, filters and aggregates IN-CODE, and returns ONLY the distilled result, instead of N model round-trips that each bloat context with raw tool output. This is Anthropic's code-execution-with-MCP pattern (up to ~98.7% fewer tokens on fan-out work). Decision rule - reach for it once you would otherwise make more than about 5 same-shape tool calls. Not for a single tool call.\nlicense: MIT\n---\n\n# MCP Code Orchestrate\n\n> **The 98.7% fan-out token-cut.** When you would otherwise call the same MCP\n> tool N times and let every raw result land in the context window, write **one\n> script** that does the loop, filters\u002Faggregates **in code**, and returns only\n> the distilled answer. Anthropic's \"Code execution with MCP\" reports a single\n> example dropping from ~150,000 tokens of tool chatter to ~2,000 (≈98.7% fewer)\n> by moving the fan-out into code instead of the model loop.\n\n## The pattern in one breath\n\nDirect tool-calling is right for **one** call: ask, get the answer, done. It is\n*pathological* for **fan-out** — \"enumerate-then-filter\" across the 39-server MCP\nfleet — because:\n\n1. Every tool *definition* you load is paid for on every turn (catalogue tax).\n2. Every tool *result* (a 4 KB JSON blob × N functions \u002F molecules \u002F papers)\n   is dumped verbatim into context, and the model re-reads all of it each turn.\n3. The model is doing a mechanical loop (iterate, test a predicate, collect hits)\n   that a `for` loop does for free, deterministically, off-context.\n\nThe fix: the agent writes **one Python script** (run via the **Bash** tool) that\ncalls the *underlying* provider — its native CLI\u002Flibrary when one exists, else\nthe MCP server over stdio\u002FHTTP — loops over all the items, applies the filter in\ncode, and **prints only the distilled result** (a shortlist, a count, the 12\nhits out of 4,000). Raw payloads stay on disk \u002F in process memory; only the\nanswer enters the conversation.\n\n### Decision rule (use this \u002F don't)\n### How a script reaches a provider — three access modes\n### 1. Native CLI or Python library (best — zero MCP overhead)\n### 2. MCP server over stdio (one session, many calls)\n### Example: spawn once, loop many.\n### sess = MCPSession([\"npx\", \"-y\", \"mcp-searxng@1.8.0\"],\n### env={**os.environ, \"SEARXNG_URL\": \"http:\u002F\u002F127.0.0.1:8890\"})\n### hits = [sess.call(\"searxng_web_search\", {\"query\": q}) for q in queries]\n### sess.close()\n### 3. MCP server over HTTP (already-running servers)\n### Concrete recipes\n### (a) RE xref-walk — find the hot functions across a whole binary\n","# MCP Code Orchestrate\n\n> **The 98.7% fan-out token-cut.** When you would otherwise call the same MCP\n> tool N times and let every raw result land in the context window, write **one\n> script** that does the loop, filters\u002Faggregates **in code**, and returns only\n> the distilled answer. Anthropic's \"Code execution with MCP\" reports a single\n> example dropping from ~150,000 tokens of tool chatter to ~2,000 (≈98.7% fewer)\n> by moving the fan-out into code instead of the model loop.\n\n## The pattern in one breath\n\nDirect tool-calling is right for **one** call: ask, get the answer, done. It is\n*pathological* for **fan-out** — \"enumerate-then-filter\" across the 39-server MCP\nfleet — because:\n\n1. Every tool *definition* you load is paid for on every turn (catalogue tax).\n2. Every tool *result* (a 4 KB JSON blob × N functions \u002F molecules \u002F papers)\n   is dumped verbatim into context, and the model re-reads all of it each turn.\n3. The model is doing a mechanical loop (iterate, test a predicate, collect hits)\n   that a `for` loop does for free, deterministically, off-context.\n\nThe fix: the agent writes **one Python script** (run via the **Bash** tool) that\ncalls the *underlying* provider — its native CLI\u002Flibrary when one exists, else\nthe MCP server over stdio\u002FHTTP — loops over all the items, applies the filter in\ncode, and **prints only the distilled result** (a shortlist, a count, the 12\nhits out of 4,000). Raw payloads stay on disk \u002F in process memory; only the\nanswer enters the conversation.\n\n### Decision rule (use this \u002F don't)\n### How a script reaches a provider — three access modes\n### 1. Native CLI or Python library (best — zero MCP overhead)\n### 2. MCP server over stdio (one session, many calls)\n### Example: spawn once, loop many.\n### sess = MCPSession([\"npx\", \"-y\", \"mcp-searxng@1.8.0\"],\n### env={**os.environ, \"SEARXNG_URL\": \"http:\u002F\u002F127.0.0.1:8890\"})\n### hits = [sess.call(\"searxng_web_search\", {\"query\": q}) for q in queries]\n### sess.close()\n### 3. MCP server over HTTP (already-running servers)\n### Concrete recipes\n### (a) RE xref-walk — find the hot functions across a whole binary\n",{"name":5,"license":15,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","platform\u002Frouting\u002Ffixtures\u002Fhome\u002F.agents\u002Fskills\u002Fmcp-code-orchestrate","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill mcp-code-orchestrate",{"tool":66,"command":67},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill mcp-code-orchestrate",{"tool":69,"command":70},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill mcp-code-orchestrate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fplatform\u002Frouting\u002Ffixtures\u002Fhome\u002F.agents\u002Fskills\u002Fmcp-code-orchestrate\u002FSKILL.md",true,[],[75,96,121,148,162,177],{"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":49},"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",[],[82,83,84,85,86,87,88,89,90,91,41,92,93,94,95],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","use","repo","injection","execution","file",{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":103,"publishedAt":49},"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",[102],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[104,105,44,106,107,108,109,110,111,112,113,114,115,116,91,117,118,119,120,32],"openmm md","how","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":133,"publishedAt":49},"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",[127,130],{"categoryNo":128,"categoryName":129,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":131,"categoryName":132,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[134,135,136,137,138,139,140,141,142,143,105,144,145,146,147],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":49},"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",[],[150,155,156,157,158,159,160,161],"setup","report","project","installation","project setup","issues","state",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":169,"publishedAt":49},"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",[168],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[164,170,87,171,172,173,91,174,43,175,176],"start issue","issue","ready","work on issue","user","work on","development",{"skillNo":178,"name":155,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"publishedAt":49},"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",[],[155,157,119,183,159,184],"files","interactive"]