[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EF8K2FWMNS2SW1ES3B037V":3,"skill-same:01M7EF8K2FWMNS2SW1ES3B037V":70},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":47},"01M7EF8K2FWMNS2SW1ES3B037V","bindcraft",null,"Guide CUDA-enabled BindCraft protein-binder design from target PDB preparation through AF2\u002FMPNN\u002FPyRosetta execution, filtering, output analysis, and conservative troubleshooting.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fbindcraft\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bindcraft\ndescription: \"Guide CUDA-enabled BindCraft protein-binder design from target PDB\n  preparation through AF2\u002FMPNN\u002FPyRosetta execution, filtering, output analysis,\n  and conservative troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# BindCraft\n\nBindCraft is a GPU-first de-novo protein-binder design pipeline that combines\nAlphaFold2 backpropagation, ProteinMPNN sequence redesign, AF2 complex\u002Fmonomer\nvalidation, and PyRosetta relaxation and interface scoring. Use this skill to\nplan and operate a reproducible campaign; do not treat it as a generic CPU\nprotein-design library.\n\n## Route the request\n\n- **Prepare or repair a target PDB and target JSON:** read\n  [target-preparation](sub-skills\u002Ftarget-preparation\u002FSKILL.md). It covers chain\n  selection, hotspot syntax, binder lengths, and safe validation.\n- **Install prerequisites, choose presets, build a launch, run or resume a\n  campaign:** read [design-pipeline](sub-skills\u002Fdesign-pipeline\u002FSKILL.md).\n  It owns CUDA\u002FJAX, AF2-weight, MPNN, PyRosetta, direct, and SLURM decisions.\n- **Inspect results, rejection causes, scores, and ranked binders:** read\n  [results-analysis](sub-skills\u002Fresults-analysis\u002FSKILL.md). It owns output\n  reconciliation and conservative metric interpretation.\n\nBefore using any route, read [installation](references\u002Finstallation.md) for\nexternal prerequisites and licensing, [configuration](references\u002Fconfiguration.md)\nfor the three JSON families, and [troubleshooting](references\u002Ftroubleshooting.md)\nfor cross-cutting failures. Read [repo-provenance](references\u002Frepo-provenance.md)\nwhen checking whether this graph matches a repository revision.\n\n## Minimal operating contract\n\n1. Work on Linux with Python 3.10 and an NVIDIA GPU. The main design path\n   requires a CUDA-visible JAX runtime; a CPU import is not a valid substitute.\n2. Obtain the AlphaFold2 parameter bundle, configure its directory, and ensure\n   DSSP and DAlphaBall are readable\u002Fexecutable. BindCraft's installer downloads\n   large external artifacts; review and run setup commands manually rather than\n   blindly executing a bundled installer.\n3. Install ColabDesign and PyRosetta in a private, compatible environment.\n   PyRosetta may have commercial-license restrictions; resolve those before a\n   production run.\n4. Validate the target JSON and PDB, then use the design route's command builder\n   to print a direct or SLURM command. The builder never executes or submits.\n5. Use a distinct writable `design_path` per campaign. Expect hundreds or\n   thousands of target-dependent trajectories for difficult targets; monitor\n   GPU memory, disk use, `failure_csv.csv`, and acceptance rate.\n6. Rank and select candidates from recorded artifacts, not from confidence\n   metrics alone. BindCraft documents `Average_i_pTM` as a useful binding\n   binary\u002Franking signal, not an affinity measurement.\n\n## Safe helpers\n\n- From the generated skill root, `python scripts\u002Fcheck_bindcraft_env.py` reports\n  import\u002Fbackend\u002Fasset readiness and never installs, downloads, or launches a\n  design.\n- From the generated skill root, `python scripts\u002Fvalidate_bindcraft_config.py`\n  checks the target, filter, and advanced JSON contracts without editing them.\n- The focused routes link additional read-only target and results helpers. All\n  paths in examples are placeholders that must be replaced on the launch host.\n\n## Non-goals and stop conditions\n\nThis graph does not download AF2 weights, submit SLURM jobs, run a full design\ncampaign, promise a binder, or infer experimental affinity. Stop and repair the\nspecific prerequisite when CUDA\u002FJAX, ColabDesign, PyRosetta, AF2 weights, DSSP,\nDAlphaBall, PDB chains, settings, output permissions, or disk\u002FVRAM capacity are\nnot verified. A successful JSON\u002FPDB check or generated command is not evidence\nthat the GPU design loop will complete.\n","# BindCraft\n\nBindCraft is a GPU-first de-novo protein-binder design pipeline that combines\nAlphaFold2 backpropagation, ProteinMPNN sequence redesign, AF2 complex\u002Fmonomer\nvalidation, and PyRosetta relaxation and interface scoring. Use this skill to\nplan and operate a reproducible campaign; do not treat it as a generic CPU\nprotein-design library.\n\n## Route the request\n\n- **Prepare or repair a target PDB and target JSON:** read\n  [target-preparation](sub-skills\u002Ftarget-preparation\u002FSKILL.md). It covers chain\n  selection, hotspot syntax, binder lengths, and safe validation.\n- **Install prerequisites, choose presets, build a launch, run or resume a\n  campaign:** read [design-pipeline](sub-skills\u002Fdesign-pipeline\u002FSKILL.md).\n  It owns CUDA\u002FJAX, AF2-weight, MPNN, PyRosetta, direct, and SLURM decisions.\n- **Inspect results, rejection causes, scores, and ranked binders:** read\n  [results-analysis](sub-skills\u002Fresults-analysis\u002FSKILL.md). It owns output\n  reconciliation and conservative metric interpretation.\n\nBefore using any route, read [installation](references\u002Finstallation.md) for\nexternal prerequisites and licensing, [configuration](references\u002Fconfiguration.md)\nfor the three JSON families, and [troubleshooting](references\u002Ftroubleshooting.md)\nfor cross-cutting failures. Read [repo-provenance](references\u002Frepo-provenance.md)\nwhen checking whether this graph matches a repository revision.\n\n## Minimal operating contract\n\n1. Work on Linux with Python 3.10 and an NVIDIA GPU. The main design path\n   requires a CUDA-visible JAX runtime; a CPU import is not a valid substitute.\n2. Obtain the AlphaFold2 parameter bundle, configure its directory, and ensure\n   DSSP and DAlphaBall are readable\u002Fexecutable. BindCraft's installer downloads\n   large external artifacts; review and run setup commands manually rather than\n   blindly executing a bundled installer.\n3. Install ColabDesign and PyRosetta in a private, compatible environment.\n   PyRosetta may have commercial-license restrictions; resolve those before a\n   production run.\n4. Validate the target JSON and PDB, then use the design route's command builder\n   to print a direct or SLURM command. The builder never executes or submits.\n5. Use a distinct writable `design_path` per campaign. Expect hundreds or\n   thousands of target-dependent trajectories for difficult targets; monitor\n   GPU memory, disk use, `failure_csv.csv`, and acceptance rate.\n6. Rank and select candidates from recorded artifacts, not from confidence\n   metrics alone. BindCraft documents `Average_i_pTM` as a useful binding\n   binary\u002Franking signal, not an affinity measurement.\n\n## Safe helpers\n\n- From the generated skill root, `python scripts\u002Fcheck_bindcraft_env.py` reports\n  import\u002Fbackend\u002Fasset readiness and never installs, downloads, or launches a\n  design.\n- From the generated skill root, `python scripts\u002Fvalidate_bindcraft_config.py`\n  checks the target, filter, and advanced JSON contracts without editing them.\n- The focused routes link additional read-only target and results helpers. All\n  paths in examples are placeholders that must be replaced on the launch host.\n\n## Non-goals and stop conditions\n\nThis graph does not download AF2 weights, submit SLURM jobs, run a full design\ncampaign, promise a binder, or infer experimental affinity. Stop and repair the\nspecific prerequisite when CUDA\u002FJAX, ColabDesign, PyRosetta, AF2 weights, DSSP,\nDAlphaBall, PDB chains, settings, output permissions, or disk\u002FVRAM capacity are\nnot verified. A successful JSON\u002FPDB check or generated command is not evidence\nthat the GPU design loop will complete.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Fbindcraft",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":26},[37,40,43],{"tool":38,"command":39},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill bindcraft",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill bindcraft",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill bindcraft","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fbindcraft\u002FSKILL.md",[48,54,58,62,66],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fconfiguration.md","REFERENCE","参考文档",3322,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fbindcraft\u002Freferences\u002Fconfiguration.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Finstallation.md",3359,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fbindcraft\u002Freferences\u002Finstallation.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Frepo-provenance.md",1568,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fbindcraft\u002Freferences\u002Frepo-provenance.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Frepo-routing-metadata.json",328,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fbindcraft\u002Freferences\u002Frepo-routing-metadata.json",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Ftroubleshooting.md",4075,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fbindcraft\u002Freferences\u002Ftroubleshooting.md",[71,78,85,92,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7EXRM12046G0GM1WGMMFXCN","ci-cd-and-automation","Automates CI\u002FCD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fci-cd-and-automation\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7EXRFYYSJ3Y15AGPDDEWWQD","chrome-devtools","Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to `--slim` mode (MCP configuration).","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fchrome-devtools\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7EXR6EYPE4X5X1BTAE6QJRV","chrome-cdp","Drive a real Chrome via the Chrome DevTools Protocol (CDP). Ensures a\ndebuggable Chrome is running (launching it if needed) so the agent can\nnavigate, read page content, inspect the DOM, run JavaScript, and take\nscreenshots — without the user typing any launch command. Includes a\nfirst-class \"review a live running app\" flow: point Chrome at the app under\ndevelopment and inspect\u002Fscreenshot the REAL page (what a static-artifact tool\ncannot do). Backed by Glimpse and the chrome-devtools MCP server. Use when\nasked to \"use chrome\", \"open chrome\", \"drive my browser\", \"read the page in\nchrome\", \"review the running app\", \"screenshot the app\", or \"\u002Fchrome-cdp\".","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fchrome-cdp\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":96,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7EXR1Y7E79KQKG4J798XGH6","check-identity-pack","Run an AFP 100-point or AUSTRAC safe-harbour identity check over a set of documents, and report exactly what's missing. Use when the user asks to check identity documents, verify someone's ID for onboarding, or assess whether a document pack satisfies Australian identity requirements.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fcheck-identity-pack\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7EXQXW7C7PGREJW9ZZTZ16H","changelog","Auto-generates a changelog from git commits, sprint data, and design documents. Produces both internal and player-facing versions.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fchangelog\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M7EXQMH2ZME3ANN8Q8MEWPFB","cellxgene-census","Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs\u002Fdownloads, embeddings, spatial Census data, or reference atlas comparisons across organisms, tissues, diseases, assays, and cell types. For analyzing your own local single-cell data use scanpy, anndata, or scvi-tools.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fcellxgene-census\u002FSKILL.md",[],[]]