[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DBWV5REJAPAC5XW5THS3ZT":3,"skill-same:01M6DBWV5REJAPAC5XW5THS3ZT":66},{"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":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":14,"repositoryHtmlUrl":49,"repositoryHomepageUrl":6,"ownerHtmlUrl":50,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":51,"install":52,"resources":65},"01M6DBWV5REJAPAC5XW5THS3ZT","simplest-probe-first",null,"Use BEFORE committing to any expensive or multi-step approach (vision\u002FOCR pipeline, multi-agent fan-out, live RE, big rewrite, long orchestration). Run the cheapest deterministic diagnostic FIRST to check whether a simpler path works. Prevents the waste where hours go into a heavy pipeline a one-command check would have ruled out (e.g. a 10-hour vision run on a PDF with no text layer).","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\u002Fsimplest-probe-first\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"simplest probe first","probe","first","multi-agent","live","deterministic","vision","use","command","check","PDF","text","ocr","pipeline","run","orchestration","go","2026-11-10 10:12:30",false,"---\nname: simplest-probe-first\ndescription: Use BEFORE committing to any expensive or multi-step approach (vision\u002FOCR pipeline, multi-agent fan-out, live RE, big rewrite, long orchestration). Run the cheapest deterministic diagnostic FIRST to check whether a simpler path works. Prevents the waste where hours go into a heavy pipeline a one-command check would have ruled out (e.g. a 10-hour vision run on a PDF with no text layer).\n---\n\n# Simplest-Probe-First\n\nA tunnel-visioned agent commits to the first (often heaviest) approach and never checks the cheap one. Same-context self-talk (\"maybe consider a simpler option\") is unreliable (intrinsic self-correction degrades reasoning — Huang et al., ICLR 2024). The reliable fix is a **deterministic probe**: run a one-command external check whose *result* picks the path for you.\n\n## The rule\nBefore any approach that costs more than a few minutes or spawns agents: name the cheapest falsifiable probe, **RUN it**, and let its result choose the path. If the probe says the simple path works, take it. Never skip the probe because the hard path \"feels right.\"\n\n## Probe table (extend it as you learn)\n| Situation | Cheap probe to run FIRST | If the probe says… |\n|---|---|---|\n| PDF \u002F scanned doc → extract text | `pdffonts file.pdf` or `pdftotext file.pdf -` | empty \u002F no fonts = no text layer → use OCR (ABBYY, the `ocr` MCP, tesseract), NOT a vision-LLM pipeline |\n| Office \u002F HTML doc → text | check for a text layer \u002F try `markitdown` | has text → parse directly, skip OCR and vision |\n| Reverse-engineer a function | static decompile (IDA \u002F Ghidra \u002F Binary Ninja) + xrefs first | static answers it → done; only go live-hook \u002F Frida if static is genuinely insufficient |\n| \"Make X faster\" | profile it once | the profile names the hot path → fix that; do not rewrite blindly |\n| \"Build utility Y\" | `gh search code` + search npm \u002F PyPI \u002F crates | it exists → fork \u002F port \u002F wrap (see the `development-workflow` rule), do not hand-roll |\n| \"Have I solved this before?\" | `mcp__basic-memory__search_notes` + grep `~\u002F.claude\u002F*.md` + project docs | found → reuse the documented approach, do not re-crack it |\n| Big new abstraction \u002F orchestration | state the complexity tier and why a simpler tier fails | can't justify it → use the simpler tier (anti-over-engineering) |\n\n## Output\nState, in one or two lines: the probe you ran, its result, and the path you chose *because of* that result. Then proceed.\n","# Simplest-Probe-First\n\nA tunnel-visioned agent commits to the first (often heaviest) approach and never checks the cheap one. Same-context self-talk (\"maybe consider a simpler option\") is unreliable (intrinsic self-correction degrades reasoning — Huang et al., ICLR 2024). The reliable fix is a **deterministic probe**: run a one-command external check whose *result* picks the path for you.\n\n## The rule\nBefore any approach that costs more than a few minutes or spawns agents: name the cheapest falsifiable probe, **RUN it**, and let its result choose the path. If the probe says the simple path works, take it. Never skip the probe because the hard path \"feels right.\"\n\n## Probe table (extend it as you learn)\n| Situation | Cheap probe to run FIRST | If the probe says… |\n|---|---|---|\n| PDF \u002F scanned doc → extract text | `pdffonts file.pdf` or `pdftotext file.pdf -` | empty \u002F no fonts = no text layer → use OCR (ABBYY, the `ocr` MCP, tesseract), NOT a vision-LLM pipeline |\n| Office \u002F HTML doc → text | check for a text layer \u002F try `markitdown` | has text → parse directly, skip OCR and vision |\n| Reverse-engineer a function | static decompile (IDA \u002F Ghidra \u002F Binary Ninja) + xrefs first | static answers it → done; only go live-hook \u002F Frida if static is genuinely insufficient |\n| \"Make X faster\" | profile it once | the profile names the hot path → fix that; do not rewrite blindly |\n| \"Build utility Y\" | `gh search code` + search npm \u002F PyPI \u002F crates | it exists → fork \u002F port \u002F wrap (see the `development-workflow` rule), do not hand-roll |\n| \"Have I solved this before?\" | `mcp__basic-memory__search_notes` + grep `~\u002F.claude\u002F*.md` + project docs | found → reuse the documented approach, do not re-crack it |\n| Big new abstraction \u002F orchestration | state the complexity tier and why a simpler tier fails | can't justify it → use the simpler tier (anti-over-engineering) |\n\n## Output\nState, in one or two lines: the probe you ran, its result, and the path you chose *because of* that result. Then proceed.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fsimplest-probe-first","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill simplest-probe-first",{"tool":58,"command":59},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill simplest-probe-first",{"tool":61,"command":62},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill simplest-probe-first","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsimplest-probe-first\u002FSKILL.md",true,[],[67,88,117,143,157,173],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":41},"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",[],[74,75,76,77,78,79,80,81,82,31,83,84,85,86,87],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":97,"publishedAt":41},"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",[94],{"categoryNo":95,"categoryName":96,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[98,99,100,101,102,103,104,105,106,107,108,109,110,111,31,112,113,114,115,116],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":129,"publishedAt":41},"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",[123,126],{"categoryNo":124,"categoryName":125,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":127,"categoryName":128,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[130,131,132,133,134,135,136,137,33,138,99,139,140,141,142],"review","visual","visual review","pages","web","false","iteration","take","slides","ui","screenshot","playwright","screenshots",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":41},"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",[],[145,150,151,152,153,154,155,156],"setup","report","project","installation","project setup","issues","state",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":164,"publishedAt":41},"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",[163],{"categoryNo":95,"categoryName":96,"taxonomyType":21,"taxonomyTypeDesc":22},[159,165,79,166,167,168,31,169,170,171,172],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":174,"name":150,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":178,"publishedAt":41},"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",[],[150,152,114,179,154,180],"files","interactive"]