[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAFJMKGJDCF3MWE7A782NX":3,"skill-same:01M6DAFJMKGJDCF3MWE7A782NX":60},{"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":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":14,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":39,"install":40,"resources":53},"01M6DAFJMKGJDCF3MWE7A782NX","game-re-binary",null,"Use when asked to analyze, reverse engineer, or understand an unknown binary, game executable, or DLL. Applies when the goal is mapping the binary structure, finding notable functions, or understanding what a binary does without running it.","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\u002Flibrary\u002Fskills\u002Fgame-re-binary\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28],"game","binary","game re binary","analyze","use","goal","engineer","functions","reverse engineer","structure","2026-11-10 10:12:30",false,"---\nname: game-re-binary\ndescription: Use when asked to analyze, reverse engineer, or understand an unknown binary, game executable, or DLL. Applies when the goal is mapping the binary structure, finding notable functions, or understanding what a binary does without running it.\n---\n\n# Game Binary Static Analysis Pipeline\n\n## Overview\nSystematic three-tool static analysis combining Binary Ninja, Ghidra, and Cheat Engine MCP servers. The order matters — orient before decompiling.\n\n**Never start with decompilation.** Strings + imports give 80% of the picture in seconds.\n\n## Tool Map\n\n| Goal | Tool | MCP prefix |\n|---|---|---|\n| Function list, imports\u002Fexports | Binary Ninja | `mcp__binary-ninja-mcp__` |\n| Decompilation (pseudocode) | Ghidra | `mcp__ghidra-mcp__` |\n| Cross-references, IL | Binary Ninja | `mcp__binary-ninja-mcp__` |\n| String search | Binary Ninja | `list_strings` \u002F `list_strings_filter` |\n| Module enumeration (live) | Cheat Engine | `enum_modules` |\n\n## Pipeline\n\n### Phase 1 — Orient (do first, always)\n```\nselect_binary(binary_path)          # Binary Ninja\nget_binary_status()                 # confirm analysis complete\nget_entry_points()                  # where execution starts\nlist_sections()                     # .text, .rdata, packed\u002Fsuspicious?\n```\n\n### Phase 2 — Map Surface\n```\nlist_imports()                      # external API calls — group by category\nlist_exports()                      # what it exposes\nlist_strings()                      # paths, URLs, error msgs, mutex names\nlist_strings_filter(pattern=\"anti|cheat|hack|inject|hook|detect\")\n```\n\n### Phase 3 — Find Targets\n```\nsearch_functions_by_name(\"init\")    # initialization routines\nsearch_functions_by_name(\"scan\")    # scanning logic\nsearch_functions_by_name(\"check\")   # validation\u002Fdetection\nget_xrefs_to(symbol)                # what calls a suspicious import\n```\n\n### Phase 4 — Decompile Key Functions Only\n```\ndecompile_function(name)            # Ghidra pseudocode\nget_il(address, il_type=\"MLIL\")    # Binary Ninja MLIL for complex logic\nget_function_xrefs(address)         # callers + callees\nget_stack_frame_vars(address)       # local variable layout\n```\n\n## Output Format\n\nProduce a structured report:\n```\n## Binary Summary\n- Arch, bitness, type (EXE\u002FDLL), entry point address\n- Packer detected? (tiny imports + high-entropy section = yes)\n- Notable sections\n\n## Notable Imports (grouped)\n- Network: WSAConnect, send, recv...\n- Process: OpenProcess, VirtualAllocEx, CreateRemoteThread...\n- Debug detection: IsDebuggerPresent, CheckRemoteDebuggerPresent...\n- Crypto: CryptEncrypt, BCryptHashData...\n\n## Interesting Strings\n- Paths, registry keys, mutex names\n- Version\u002Fbuild strings\n- Error messages\n\n## Suspicious Functions\n- Function name\u002Faddress + 5-10 line pseudocode snippet\n\n## Entry Point Flow\n- High-level call chain from entry\n```\n\n## Common Mistakes\n\n| Mistake | Fix |\n|---|---|\n| Decompile everything immediately | Orient with imports\u002Fstrings first — 5 min vs 30 min |\n| Using only one tool | Binary Ninja navigates faster; Ghidra decompiles better |\n| Ignoring section entropy | High entropy + tiny imports = packer — see game-unpack-pe |\n| Missing string cross-references | Use `get_xrefs_to` on the string address, not just search |\n| Not checking exports | DLLs expose logic through exports — start there |\n","# Game Binary Static Analysis Pipeline\n\n## Overview\nSystematic three-tool static analysis combining Binary Ninja, Ghidra, and Cheat Engine MCP servers. The order matters — orient before decompiling.\n\n**Never start with decompilation.** Strings + imports give 80% of the picture in seconds.\n\n## Tool Map\n\n| Goal | Tool | MCP prefix |\n|---|---|---|\n| Function list, imports\u002Fexports | Binary Ninja | `mcp__binary-ninja-mcp__` |\n| Decompilation (pseudocode) | Ghidra | `mcp__ghidra-mcp__` |\n| Cross-references, IL | Binary Ninja | `mcp__binary-ninja-mcp__` |\n| String search | Binary Ninja | `list_strings` \u002F `list_strings_filter` |\n| Module enumeration (live) | Cheat Engine | `enum_modules` |\n\n## Pipeline\n\n### Phase 1 — Orient (do first, always)\n```\nselect_binary(binary_path)          # Binary Ninja\nget_binary_status()                 # confirm analysis complete\nget_entry_points()                  # where execution starts\nlist_sections()                     # .text, .rdata, packed\u002Fsuspicious?\n```\n\n### Phase 2 — Map Surface\n```\nlist_imports()                      # external API calls — group by category\nlist_exports()                      # what it exposes\nlist_strings()                      # paths, URLs, error msgs, mutex names\nlist_strings_filter(pattern=\"anti|cheat|hack|inject|hook|detect\")\n```\n\n### Phase 3 — Find Targets\n```\nsearch_functions_by_name(\"init\")    # initialization routines\nsearch_functions_by_name(\"scan\")    # scanning logic\nsearch_functions_by_name(\"check\")   # validation\u002Fdetection\nget_xrefs_to(symbol)                # what calls a suspicious import\n```\n\n### Phase 4 — Decompile Key Functions Only\n```\ndecompile_function(name)            # Ghidra pseudocode\nget_il(address, il_type=\"MLIL\")    # Binary Ninja MLIL for complex logic\nget_function_xrefs(address)         # callers + callees\nget_stack_frame_vars(address)       # local variable layout\n```\n\n## Output Format\n\nProduce a structured report:\n```\n## Binary Summary\n- Arch, bitness, type (EXE\u002FDLL), entry point address\n- Packer detected? (tiny imports + high-entropy section = yes)\n- Notable sections\n\n## Notable Imports (grouped)\n- Network: WSAConnect, send, recv...\n- Process: OpenProcess, VirtualAllocEx, CreateRemoteThread...\n- Debug detection: IsDebuggerPresent, CheckRemoteDebuggerPresent...\n- Crypto: CryptEncrypt, BCryptHashData...\n\n## Interesting Strings\n- Paths, registry keys, mutex names\n- Version\u002Fbuild strings\n- Error messages\n\n## Suspicious Functions\n- Function name\u002Faddress + 5-10 line pseudocode snippet\n\n## Entry Point Flow\n- High-level call chain from entry\n```\n\n## Common Mistakes\n\n| Mistake | Fix |\n|---|---|\n| Decompile everything immediately | Orient with imports\u002Fstrings first — 5 min vs 30 min |\n| Using only one tool | Binary Ninja navigates faster; Ghidra decompiles better |\n| Ignoring section entropy | High entropy + tiny imports = packer — see game-unpack-pe |\n| Missing string cross-references | Use `get_xrefs_to` on the string address, not just search |\n| Not checking exports | DLLs expose logic through exports — start there |\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Fgame-re-binary","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill game-re-binary",{"tool":46,"command":47},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill game-re-binary",{"tool":49,"command":50},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill game-re-binary","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Fgame-re-binary\u002FSKILL.md",true,[54],{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"agents\u002Fopenai.yaml","REFERENCE","参考文档",82,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgitnexus-impact-analysis\u002Fagents\u002Fopenai.yaml",[61,81,111,138,152,168],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":29},"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",[],[68,69,70,71,72,73,74,24,75,23,76,77,78,79,80],"clarify requirements","clarify","requirements","risk","options","task","prompts","scanning","context","repo","injection","execution","file",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":92,"publishedAt":29},"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",[87],{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[93,94,95,96,97,22,98,99,100,101,102,103,104,105,23,106,107,108,109,110],"openmm md","how","decision","pick","linux","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":123,"publishedAt":29},"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",[117,120],{"categoryNo":118,"categoryName":119,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":121,"categoryName":122,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000008","测试与质量",[124,125,126,127,128,129,130,131,132,133,94,134,135,136,137],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":29},"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",[],[140,145,146,147,148,149,150,151],"setup","report","project","installation","project setup","issues","state",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":159,"publishedAt":29},"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",[158],{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},[154,160,73,161,162,163,23,164,165,166,167],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":169,"name":145,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":29},"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",[],[145,147,108,174,149,175],"files","interactive"]