{"_id":"@dzhechkov/skills-book-digitizer","_rev":"16-d87341592dd627c6bf65a912b32eb9b8","name":"@dzhechkov/skills-book-digitizer","dist-tags":{"latest":"0.2.20"},"versions":{"0.1.0":{"name":"@dzhechkov/skills-book-digitizer","version":"0.1.0","keywords":["agent-skills","agentskills.io","skill-pack","claude-code","knowledge-extraction","book","pdf","methodology","agentdb"],"author":{"name":"dzhechko"},"license":"MIT","_id":"@dzhechkov/skills-book-digitizer@0.1.0","maintainers":[{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"}],"homepage":"https://github.com/djd1m/dz-harness-hub/tree/main/packages/@dzhechkov/skills-book-digitizer#readme","bugs":{"url":"https://github.com/djd1m/dz-harness-hub/issues"},"dist":{"shasum":"207d89e85d9682a013056c1b83877208be68087b","tarball":"https://registry.npmjs.org/@dzhechkov/skills-book-digitizer/-/skills-book-digitizer-0.1.0.tgz","fileCount":11,"integrity":"sha512-tnKXqN8kbLvX4TT844AV0O5eYK+nnJEy7XLYvDuYCtS3EzSLj1p6FSY9GuatnilJpfVXNzH/Qz1W5AbZo9VLmw==","signatures":[{"sig":"MEYCIQCDjkvIjdXA+ZIICafC7LnNFA1jLVTrlUIXFOBCMRKA7gIhAPqzUcwJg/d0meQ0hwr95RoOf3K7xoAyJWtw3TCA4G+v","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":58690},"gitHead":"6c3b446694f8a62d5558cd6095edceb66d92c844","_npmUser":{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"},"repository":{"url":"git+https://github.com/djd1m/dz-harness-hub.git","type":"git","directory":"packages/@dzhechkov/skills-book-digitizer"},"_npmVersion":"10.9.4","description":"Canonical book-digitizer skill pack — 6 skills that turn an engineering book/textbook/monograph into an installable skill pack whose skills make AI coders work within the book's methodologies: digitize-book (orchestrator), book-ingest, book-knowledge-extr","directories":{},"_nodeVersion":"22.22.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/skills-book-digitizer_0.1.0_1783097150650_0.27291146941634015","host":"s3://npm-registry-packages-npm-production"}},"0.1.1":{"name":"@dzhechkov/skills-book-digitizer","version":"0.1.1","keywords":["agent-skills","agentskills.io","skill-pack","claude-code","knowledge-extraction","book","pdf","methodology","agentdb"],"author":{"name":"dzhechko"},"license":"MIT","_id":"@dzhechkov/skills-book-digitizer@0.1.1","maintainers":[{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"}],"homepage":"https://github.com/djd1m/dz-harness-hub/tree/main/packages/@dzhechkov/skills-book-digitizer#readme","bugs":{"url":"https://github.com/djd1m/dz-harness-hub/issues"},"dist":{"shasum":"dc0a15f7eb0d4eb49966a17e3649769f384b5f2e","tarball":"https://registry.npmjs.org/@dzhechkov/skills-book-digitizer/-/skills-book-digitizer-0.1.1.tgz","fileCount":11,"integrity":"sha512-+VLSfqCOLr3FfO7bZ3YYG4tYwbdpO1VcSanRu2UT+hRODrwk1QH8Fq0CTGaGKJD7kWkzh31bUzDhCH7Ro48Oug==","signatures":[{"sig":"MEYCIQCLwIhzsW1yh3DyNjo4gwqknNLCdc7lAOgkvnpZGgz6QAIhALKQGCao9lY89PDGgi1nSNfDiNp274PzLClMNPL3gdfV","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":60365},"gitHead":"4c3cc0ed80ef8b39178fbffa4e757ce14c30253d","_npmUser":{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"},"repository":{"url":"git+https://github.com/djd1m/dz-harness-hub.git","type":"git","directory":"packages/@dzhechkov/skills-book-digitizer"},"_npmVersion":"10.9.4","description":"Canonical book-digitizer skill pack — 6 skills that turn an engineering book/textbook/monograph into an installable skill pack whose skills make AI coders work within the book's methodologies: digitize-book (orchestrator), book-ingest, book-knowledge-extr","directories":{},"_nodeVersion":"22.22.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/skills-book-digitizer_0.1.1_1783098976877_0.537868901553405","host":"s3://npm-registry-packages-npm-production"}},"0.2.0":{"name":"@dzhechkov/skills-book-digitizer","version":"0.2.0","keywords":["agent-skills","agentskills.io","skill-pack","claude-code","knowledge-extraction","book","pdf","methodology","agentdb"],"author":{"name":"dzhechko"},"license":"MIT","_id":"@dzhechkov/skills-book-digitizer@0.2.0","maintainers":[{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"}],"homepage":"https://github.com/djd1m/dz-harness-hub/tree/main/packages/@dzhechkov/skills-book-digitizer#readme","bugs":{"url":"https://github.com/djd1m/dz-harness-hub/issues"},"dist":{"shasum":"3f2e0371bff0410963e9e797abf0d97a8c63fc9b","tarball":"https://registry.npmjs.org/@dzhechkov/skills-book-digitizer/-/skills-book-digitizer-0.2.0.tgz","fileCount":12,"integrity":"sha512-+4ppxGc/MwvJgXQPhnrwV2lSLQOBD1QYKWm6vm7m4hYPfPIREcpTz9o0AM+jzY33arsoVDvqByYPrCWpquLzQQ==","signatures":[{"sig":"MEUCIALGYTsWZqoMxjYIEhdsPO/Rtwk20zhxnqt9zpfjMK+XAiEA8CPPw2KTYeED1ukRmnt6C+WbIiC3PrSu2Nx4bXiDxAw=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":73785},"gitHead":"5f6222c0848ec87ad26274a362f766a0eeb19ec3","_npmUser":{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"},"repository":{"url":"git+https://github.com/djd1m/dz-harness-hub.git","type":"git","directory":"packages/@dzhechkov/skills-book-digitizer"},"_npmVersion":"10.9.4","description":"Canonical book-digitizer skill pack — 6 skills that turn an engineering book/textbook/monograph into an installable skill pack whose skills make AI coders work within the book's methodologies: digitize-book (orchestrator), book-ingest, book-knowledge-extr","directories":{},"_nodeVersion":"22.22.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/skills-book-digitizer_0.2.0_1783099784853_0.981418257539437","host":"s3://npm-registry-packages-npm-production"}},"0.2.2":{"name":"@dzhechkov/skills-book-digitizer","version":"0.2.2","keywords":["agent-skills","agentskills.io","skill-pack","claude-code","knowledge-extraction","book","pdf","methodology","agentdb"],"author":{"name":"dzhechko"},"license":"MIT","_id":"@dzhechkov/skills-book-digitizer@0.2.2","maintainers":[{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"}],"homepage":"https://github.com/djd1m/dz-harness-hub/tree/main/packages/@dzhechkov/skills-book-digitizer#readme","bugs":{"url":"https://github.com/djd1m/dz-harness-hub/issues"},"dist":{"shasum":"c536d02e6039541b73dcaf4624b62a392204d915","tarball":"https://registry.npmjs.org/@dzhechkov/skills-book-digitizer/-/skills-book-digitizer-0.2.2.tgz","fileCount":12,"integrity":"sha512-RBKb1l/GLFGULWQlP8CSD9D6X5g4jIAYdq8c3QnHMn48+7wuyic/rP7r3xg2Mt+HB5D3hNXySCWVrKgsWNczcQ==","signatures":[{"sig":"MEUCIQCwrfPyYHnNvR0yruVoBJU9Gkgus1Qlf2a37zGYgs3d8AIgSfAuTByg5PnqGkkNM0DPdoymPo+LDGL+zVZjYjv+UiQ=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":78094},"_from":"file:dzhechkov-skills-book-digitizer-0.2.2.tgz","_npmUser":{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"},"_resolved":"/tmp/6b99b49fd2068a88abc2a65806f902fb/dzhechkov-skills-book-digitizer-0.2.2.tgz","_integrity":"sha512-RBKb1l/GLFGULWQlP8CSD9D6X5g4jIAYdq8c3QnHMn48+7wuyic/rP7r3xg2Mt+HB5D3hNXySCWVrKgsWNczcQ==","repository":{"url":"git+https://github.com/djd1m/dz-harness-hub.git","type":"git","directory":"packages/@dzhechkov/skills-book-digitizer"},"_npmVersion":"10.9.4","description":"Canonical book-digitizer skill pack — 6 skills that turn an engineering book/textbook/monograph into an installable skill pack whose skills make AI coders work within the book's methodologies: digitize-book (orchestrator), book-ingest, book-knowledge-extr","directories":{},"_nodeVersion":"22.22.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/skills-book-digitizer_0.2.2_1783109230793_0.6060505778154079","host":"s3://npm-registry-packages-npm-production"}},"0.2.4":{"name":"@dzhechkov/skills-book-digitizer","version":"0.2.4","keywords":["agent-skills","agentskills.io","skill-pack","claude-code","knowledge-extraction","book","pdf","methodology","agentdb"],"author":{"name":"dzhechko"},"license":"MIT","_id":"@dzhechkov/skills-book-digitizer@0.2.4","maintainers":[{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"}],"homepage":"https://github.com/djd1m/dz-harness-hub/tree/main/packages/@dzhechkov/skills-book-digitizer#readme","bugs":{"url":"https://github.com/djd1m/dz-harness-hub/issues"},"dist":{"shasum":"d34f75eea765efa799ef0c67c71d6eff60af0530","tarball":"https://registry.npmjs.org/@dzhechkov/skills-book-digitizer/-/skills-book-digitizer-0.2.4.tgz","fileCount":13,"integrity":"sha512-n+tpLxKPoiZYhJYsNsDyGWGqSonVCe4N1Ae9X1+PI1+PzPrKVKRo3ozsd2iO6s97X6I5jfsxLbZrp6ezHEoPGQ==","signatures":[{"sig":"MEQCIF7huwI620Q0dy6NodFU0/EDkOMo4buJtszHDcpGuCftAiBH/jKbMXD1dN2OEWLGUVT3eTOfQtAW/0U+9jA8uBJIow==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":89407},"_from":"file:dzhechkov-skills-book-digitizer-0.2.4.tgz","_npmUser":{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"},"_resolved":"/tmp/943213edde5bf43086645d6d6bad1079/dzhechkov-skills-book-digitizer-0.2.4.tgz","_integrity":"sha512-n+tpLxKPoiZYhJYsNsDyGWGqSonVCe4N1Ae9X1+PI1+PzPrKVKRo3ozsd2iO6s97X6I5jfsxLbZrp6ezHEoPGQ==","repository":{"url":"git+https://github.com/djd1m/dz-harness-hub.git","type":"git","directory":"packages/@dzhechkov/skills-book-digitizer"},"_npmVersion":"10.9.4","description":"Canonical book-digitizer skill pack — 6 skills that turn an engineering book/textbook/monograph into an installable skill pack whose skills make AI coders work within the book's methodologies: digitize-book (orchestrator), book-ingest, book-knowledge-extr","directories":{},"_nodeVersion":"22.22.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/skills-book-digitizer_0.2.4_1783110853217_0.9567911995849661","host":"s3://npm-registry-packages-npm-production"}},"0.2.6":{"name":"@dzhechkov/skills-book-digitizer","version":"0.2.6","keywords":["agent-skills","agentskills.io","skill-pack","claude-code","knowledge-extraction","book","pdf","methodology","agentdb"],"author":{"name":"dzhechko"},"license":"MIT","_id":"@dzhechkov/skills-book-digitizer@0.2.6","maintainers":[{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"}],"homepage":"https://github.com/djd1m/dz-harness-hub/tree/main/packages/@dzhechkov/skills-book-digitizer#readme","bugs":{"url":"https://github.com/djd1m/dz-harness-hub/issues"},"dist":{"shasum":"8647f711bd929786b41a7b9c8db1f4ae3ec9e2de","tarball":"https://registry.npmjs.org/@dzhechkov/skills-book-digitizer/-/skills-book-digitizer-0.2.6.tgz","fileCount":14,"integrity":"sha512-9cM8UZnHhEuOt5NqIotghm4aS7B/0fXuUgd8ZjlO0vJKFET/lOTUgd9M6+wkJA3wkCoT+3XOVx4pMgyUXr2swg==","signatures":[{"sig":"MEUCIDxLY2DWCvo8MNToGb7C3ib8jD6vCLdL8naQQ+0CHFWQAiEA+KQGJnxp5Sfr5XERY+GndoqOgpFdvll646HGoztOluo=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":100981},"_from":"file:dzhechkov-skills-book-digitizer-0.2.6.tgz","_npmUser":{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"},"_resolved":"/tmp/647f91281b43bfd543f1b7c3e44ec0f1/dzhechkov-skills-book-digitizer-0.2.6.tgz","_integrity":"sha512-9cM8UZnHhEuOt5NqIotghm4aS7B/0fXuUgd8ZjlO0vJKFET/lOTUgd9M6+wkJA3wkCoT+3XOVx4pMgyUXr2swg==","repository":{"url":"git+https://github.com/djd1m/dz-harness-hub.git","type":"git","directory":"packages/@dzhechkov/skills-book-digitizer"},"_npmVersion":"10.9.4","description":"Canonical book-digitizer skill pack — 8 skills that turn an engineering book/textbook/monograph into an installable skill pack whose skills make AI coders work within the book's methodologies: digitize-book (orchestrator), book-ingest, book-knowledge-extr","directories":{},"_nodeVersion":"22.22.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/skills-book-digitizer_0.2.6_1783147064121_0.5929376467108884","host":"s3://npm-registry-packages-npm-production"}},"0.2.8":{"name":"@dzhechkov/skills-book-digitizer","version":"0.2.8","keywords":["agent-skills","agentskills.io","skill-pack","claude-code","knowledge-extraction","book","pdf","methodology","agentdb"],"author":{"name":"dzhechko"},"license":"MIT","_id":"@dzhechkov/skills-book-digitizer@0.2.8","maintainers":[{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"}],"homepage":"https://github.com/djd1m/dz-harness-hub/tree/main/packages/@dzhechkov/skills-book-digitizer#readme","bugs":{"url":"https://github.com/djd1m/dz-harness-hub/issues"},"dist":{"shasum":"0e3cf332ce5998bf3926a0468459b24aa1f41306","tarball":"https://registry.npmjs.org/@dzhechkov/skills-book-digitizer/-/skills-book-digitizer-0.2.8.tgz","fileCount":14,"integrity":"sha512-QWv7KwuoH+dKC9OnqdGhHmrFDYdlwjDAVFu3cgehqLsPQNkZGPzLCPPVJB9Tpe+gsP8eBb4pEucTK7WeyOZL1w==","signatures":[{"sig":"MEQCIC2MA2rg6pzGwTm65P24zov1KwBWWNHgpQGhDnunNasbAiBAm79yW1U8xa7f+JkLKOJMmhegH+yOLxNK36Yqyt++Dw==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":102565},"_from":"file:dzhechkov-skills-book-digitizer-0.2.8.tgz","_npmUser":{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"},"_resolved":"/tmp/2aa9d0337ebf5d2e1a89d1588d7b51a9/dzhechkov-skills-book-digitizer-0.2.8.tgz","_integrity":"sha512-QWv7KwuoH+dKC9OnqdGhHmrFDYdlwjDAVFu3cgehqLsPQNkZGPzLCPPVJB9Tpe+gsP8eBb4pEucTK7WeyOZL1w==","repository":{"url":"git+https://github.com/djd1m/dz-harness-hub.git","type":"git","directory":"packages/@dzhechkov/skills-book-digitizer"},"_npmVersion":"10.9.4","description":"Canonical book-digitizer skill pack — 8 skills that turn an engineering book/textbook/monograph into an installable skill pack whose skills make AI coders work within the book's methodologies: digitize-book (orchestrator), book-ingest, book-knowledge-extr","directories":{},"_nodeVersion":"22.22.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/skills-book-digitizer_0.2.8_1783148639299_0.995328872161207","host":"s3://npm-registry-packages-npm-production"}},"0.2.10":{"name":"@dzhechkov/skills-book-digitizer","version":"0.2.10","keywords":["agent-skills","agentskills.io","skill-pack","claude-code","knowledge-extraction","book","pdf","methodology","agentdb"],"author":{"name":"dzhechko"},"license":"MIT","_id":"@dzhechkov/skills-book-digitizer@0.2.10","maintainers":[{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"}],"homepage":"https://github.com/djd1m/dz-harness-hub/tree/main/packages/@dzhechkov/skills-book-digitizer#readme","bugs":{"url":"https://github.com/djd1m/dz-harness-hub/issues"},"dist":{"shasum":"4da80fccc9f309f89fa7d7990fadbc617c0ea92e","tarball":"https://registry.npmjs.org/@dzhechkov/skills-book-digitizer/-/skills-book-digitizer-0.2.10.tgz","fileCount":14,"integrity":"sha512-/5gWE/wlxmHUjlUPBr5RLGwKW3pRQ+szE9XlR9h1PcCvpKBOnbvIDFvLKFbUlqIz31yW0c3EMHc37R77edSWnw==","signatures":[{"sig":"MEQCIGR3phq51MP4xj75s5JZYCZLkgu1b1eui2Zrf45pNJ5HAiBoFRP7gRmdpIbkzb+xMG44HnbVuKEe6MbT2TecS6FjXQ==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":102887},"_from":"file:dzhechkov-skills-book-digitizer-0.2.10.tgz","_npmUser":{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"},"_resolved":"/tmp/9bc567f5ad1ada32cd8009c1e17a151e/dzhechkov-skills-book-digitizer-0.2.10.tgz","_integrity":"sha512-/5gWE/wlxmHUjlUPBr5RLGwKW3pRQ+szE9XlR9h1PcCvpKBOnbvIDFvLKFbUlqIz31yW0c3EMHc37R77edSWnw==","repository":{"url":"git+https://github.com/djd1m/dz-harness-hub.git","type":"git","directory":"packages/@dzhechkov/skills-book-digitizer"},"_npmVersion":"10.9.4","description":"Canonical book-digitizer skill pack — 8 skills that turn an engineering book/textbook/monograph into an installable skill pack whose skills make AI coders work within the book's methodologies: digitize-book (orchestrator), book-ingest, book-knowledge-extr","directories":{},"_nodeVersion":"22.22.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/skills-book-digitizer_0.2.10_1783151583477_0.17335531348518596","host":"s3://npm-registry-packages-npm-production"}},"0.2.12":{"name":"@dzhechkov/skills-book-digitizer","version":"0.2.12","keywords":["agent-skills","agentskills.io","skill-pack","claude-code","knowledge-extraction","book","pdf","methodology","agentdb"],"author":{"name":"dzhechko"},"license":"MIT","_id":"@dzhechkov/skills-book-digitizer@0.2.12","maintainers":[{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"}],"homepage":"https://github.com/djd1m/dz-harness-hub/tree/main/packages/@dzhechkov/skills-book-digitizer#readme","bugs":{"url":"https://github.com/djd1m/dz-harness-hub/issues"},"dist":{"shasum":"052774c060d57b871c86db944341100872a1ff92","tarball":"https://registry.npmjs.org/@dzhechkov/skills-book-digitizer/-/skills-book-digitizer-0.2.12.tgz","fileCount":14,"integrity":"sha512-RaXRRWMnpKe/s45VxUbbJ1DhnIBVfnnLAIVzBC9QLIVdQrVlLWWr3a5MD1d04Ajj1AfBsHTN+WLK0yZ08Brw9w==","signatures":[{"sig":"MEQCIHw6OZO6dQh9j/PjhP3XhMuH309bsBqxzaYUA941rfpxAiB5SpelA0egoDKhxtudwPAQntmyGOoRKwOFXZ8KI5rzAQ==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":103940},"_from":"file:dzhechkov-skills-book-digitizer-0.2.12.tgz","_npmUser":{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"},"_resolved":"/tmp/5a4e1a71a443f8fbb71838851517d354/dzhechkov-skills-book-digitizer-0.2.12.tgz","_integrity":"sha512-RaXRRWMnpKe/s45VxUbbJ1DhnIBVfnnLAIVzBC9QLIVdQrVlLWWr3a5MD1d04Ajj1AfBsHTN+WLK0yZ08Brw9w==","repository":{"url":"git+https://github.com/djd1m/dz-harness-hub.git","type":"git","directory":"packages/@dzhechkov/skills-book-digitizer"},"_npmVersion":"10.9.4","description":"Canonical book-digitizer skill pack — 8 skills that turn an engineering book/textbook/monograph into an installable skill pack whose skills make AI coders work within the book's methodologies: digitize-book (orchestrator), book-ingest, book-knowledge-extr","directories":{},"_nodeVersion":"22.22.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/skills-book-digitizer_0.2.12_1783152204471_0.13356213255284266","host":"s3://npm-registry-packages-npm-production"}},"0.2.14":{"name":"@dzhechkov/skills-book-digitizer","version":"0.2.14","keywords":["agent-skills","agentskills.io","skill-pack","claude-code","knowledge-extraction","book","pdf","methodology","agentdb"],"author":{"name":"dzhechko"},"license":"MIT","_id":"@dzhechkov/skills-book-digitizer@0.2.14","maintainers":[{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"}],"homepage":"https://github.com/djd1m/dz-harness-hub/tree/main/packages/@dzhechkov/skills-book-digitizer#readme","bugs":{"url":"https://github.com/djd1m/dz-harness-hub/issues"},"dist":{"shasum":"0af623b590bf8739512126f2172257955f47b9bb","tarball":"https://registry.npmjs.org/@dzhechkov/skills-book-digitizer/-/skills-book-digitizer-0.2.14.tgz","fileCount":14,"integrity":"sha512-CIewf3qvQSDwoGkbgs7KZhdlXyTben3G/dEk24Y+niHUBS20AzLRXAONgEvEedi6l3IvcfxWaFWPqU9fsFD4yw==","signatures":[{"sig":"MEUCIAaSkUnSfBCNbwIGYQ1yP3DD+HcwuV5alANPzydU/7SAAiEAxF7rCNZuCFzsnjySbuNXmCYymaapkvyaeTccvB8HBTg=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":104582},"_from":"file:dzhechkov-skills-book-digitizer-0.2.14.tgz","_npmUser":{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"},"_resolved":"/tmp/6cd6b0168e24c214800efaf4677fce4f/dzhechkov-skills-book-digitizer-0.2.14.tgz","_integrity":"sha512-CIewf3qvQSDwoGkbgs7KZhdlXyTben3G/dEk24Y+niHUBS20AzLRXAONgEvEedi6l3IvcfxWaFWPqU9fsFD4yw==","repository":{"url":"git+https://github.com/djd1m/dz-harness-hub.git","type":"git","directory":"packages/@dzhechkov/skills-book-digitizer"},"_npmVersion":"10.9.4","description":"Canonical book-digitizer skill pack — 8 skills that turn an engineering book/textbook/monograph into an installable skill pack whose skills make AI coders work within the book's methodologies: digitize-book (orchestrator), book-ingest, book-knowledge-extr","directories":{},"_nodeVersion":"22.22.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/skills-book-digitizer_0.2.14_1783153132007_0.810052070408543","host":"s3://npm-registry-packages-npm-production"}},"0.2.15":{"name":"@dzhechkov/skills-book-digitizer","version":"0.2.15","keywords":["agent-skills","agentskills.io","skill-pack","claude-code","knowledge-extraction","book","pdf","methodology","agentdb"],"author":{"name":"dzhechko"},"license":"MIT","_id":"@dzhechkov/skills-book-digitizer@0.2.15","maintainers":[{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"}],"homepage":"https://github.com/djd1m/dz-harness-hub/tree/main/packages/@dzhechkov/skills-book-digitizer#readme","bugs":{"url":"https://github.com/djd1m/dz-harness-hub/issues"},"dist":{"shasum":"1f3f267079e2cf75dcc144f052c94d7e94d36ad1","tarball":"https://registry.npmjs.org/@dzhechkov/skills-book-digitizer/-/skills-book-digitizer-0.2.15.tgz","fileCount":16,"integrity":"sha512-ukxHjcdfHQQeISr/7NRGlDPAPgXCfHbZ+bnL3d9QW93l6TeiJ6tNU+BJfROO6EkGjGwZ2jRcIY7bAnFgTSfT6A==","signatures":[{"sig":"MEYCIQCHu6xXglXN4XmurztFQ0L6cn8Dxhh0t1DrOv32qejkOgIhAPYrviu5oKJmKAk5pKA+Ak12AfI5RLhaqVXYm1LpW/vA","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":110357},"_from":"file:dzhechkov-skills-book-digitizer-0.2.15.tgz","scripts":{},"_npmUser":{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"},"_resolved":"/tmp/c02bc054553e95df27888a8c80c4a33e/dzhechkov-skills-book-digitizer-0.2.15.tgz","_integrity":"sha512-ukxHjcdfHQQeISr/7NRGlDPAPgXCfHbZ+bnL3d9QW93l6TeiJ6tNU+BJfROO6EkGjGwZ2jRcIY7bAnFgTSfT6A==","repository":{"url":"git+https://github.com/djd1m/dz-harness-hub.git","type":"git","directory":"packages/@dzhechkov/skills-book-digitizer"},"_npmVersion":"10.9.4","description":"Canonical book-digitizer skill pack — 8 skills that turn an engineering book/textbook/monograph into an installable skill pack whose skills make AI coders work within the book's methodologies: digitize-book (orchestrator), book-ingest, book-knowledge-extr","directories":{},"_nodeVersion":"22.22.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/skills-book-digitizer_0.2.15_1787632919719_0.020018887388040918","host":"s3://npm-registry-packages-npm-production"}},"0.2.16":{"name":"@dzhechkov/skills-book-digitizer","version":"0.2.16","keywords":["agent-skills","agentskills.io","skill-pack","claude-code","knowledge-extraction","book","pdf","methodology","agentdb"],"author":{"name":"dzhechko"},"license":"MIT","_id":"@dzhechkov/skills-book-digitizer@0.2.16","maintainers":[{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"}],"homepage":"https://github.com/djd1m/dz-harness-hub/tree/main/packages/@dzhechkov/skills-book-digitizer#readme","bugs":{"url":"https://github.com/djd1m/dz-harness-hub/issues"},"dist":{"shasum":"cdc27f4aa39f80415e851c112c4a6a54772b252b","tarball":"https://registry.npmjs.org/@dzhechkov/skills-book-digitizer/-/skills-book-digitizer-0.2.16.tgz","fileCount":16,"integrity":"sha512-PpInd94NlPOqE3FqEN/7ZmF4Thf/0soYlHPDtCCP6wfQh4F1d/+MyhT8TwBeGOw2UTfT8zCB0bUwU1/n5hx67Q==","signatures":[{"sig":"MEYCIQCy+yHqaIwBs5vQ8XtgE44Eqbk7jOTCBDG6pxoHiTnKOAIhAK3dDf0W4KMRx9GYCLi8VDYAuIOY0r6jSY7apAdsZ3IS","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":111278},"_from":"file:dzhechkov-skills-book-digitizer-0.2.16.tgz","scripts":{},"_npmUser":{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"},"_resolved":"/tmp/9a3dd21259e7d9dcab17ff74c1c6a311/dzhechkov-skills-book-digitizer-0.2.16.tgz","_integrity":"sha512-PpInd94NlPOqE3FqEN/7ZmF4Thf/0soYlHPDtCCP6wfQh4F1d/+MyhT8TwBeGOw2UTfT8zCB0bUwU1/n5hx67Q==","repository":{"url":"git+https://github.com/djd1m/dz-harness-hub.git","type":"git","directory":"packages/@dzhechkov/skills-book-digitizer"},"_npmVersion":"10.9.4","description":"Canonical book-digitizer skill pack — 8 skills that turn an engineering book/textbook/monograph into an installable skill pack whose skills make AI coders work within the book's methodologies: digitize-book (orchestrator), book-ingest, book-knowledge-extr","directories":{},"_nodeVersion":"22.22.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/skills-book-digitizer_0.2.16_1787944494350_0.6163652253113507","host":"s3://npm-registry-packages-npm-production"}},"0.2.17":{"name":"@dzhechkov/skills-book-digitizer","version":"0.2.17","keywords":["agent-skills","agentskills.io","skill-pack","claude-code","knowledge-extraction","book","pdf","methodology","agentdb"],"author":{"name":"dzhechko"},"license":"MIT","_id":"@dzhechkov/skills-book-digitizer@0.2.17","maintainers":[{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"}],"homepage":"https://github.com/djd1m/dz-harness-hub/tree/main/packages/@dzhechkov/skills-book-digitizer#readme","bugs":{"url":"https://github.com/djd1m/dz-harness-hub/issues"},"dist":{"shasum":"3379f6a6f472c46c32c6c24b0eb44d1510744498","tarball":"https://registry.npmjs.org/@dzhechkov/skills-book-digitizer/-/skills-book-digitizer-0.2.17.tgz","fileCount":16,"integrity":"sha512-oyJaaAAjx4Nbl0R4Ze5YcVm3VmU35hffUUUgEvyEvomsPvwLkP4NbcwxT9hV+UAocDv/VAfXojBNLijJ5KSIJA==","signatures":[{"sig":"MEUCIGTObXO2TWo/ir6/B8/XfeW8tRoo8SOETtyUPN+OUDExAiEA1GcHvFIK2W1SQl+/0E20Eu2LuKV9126FyLfY7nn9RuA=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":111278},"_from":"file:dzhechkov-skills-book-digitizer-0.2.17.tgz","scripts":{},"_npmUser":{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"},"_resolved":"/tmp/0b86eeffe0c0241d85c14026856e8a14/dzhechkov-skills-book-digitizer-0.2.17.tgz","_integrity":"sha512-oyJaaAAjx4Nbl0R4Ze5YcVm3VmU35hffUUUgEvyEvomsPvwLkP4NbcwxT9hV+UAocDv/VAfXojBNLijJ5KSIJA==","repository":{"url":"git+https://github.com/djd1m/dz-harness-hub.git","type":"git","directory":"packages/@dzhechkov/skills-book-digitizer"},"_npmVersion":"10.9.4","description":"Canonical book-digitizer skill pack — 8 skills that turn an engineering book/textbook/monograph into an installable skill pack whose skills make AI coders work within the book's methodologies: digitize-book (orchestrator), book-ingest, book-knowledge-extr","directories":{},"_nodeVersion":"22.22.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/skills-book-digitizer_0.2.17_1787944876184_0.06348747942835198","host":"s3://npm-registry-packages-npm-production"}},"0.2.18":{"name":"@dzhechkov/skills-book-digitizer","version":"0.2.18","keywords":["agent-skills","agentskills.io","skill-pack","claude-code","knowledge-extraction","book","pdf","methodology","agentdb"],"author":{"name":"dzhechko"},"license":"MIT","_id":"@dzhechkov/skills-book-digitizer@0.2.18","maintainers":[{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"}],"homepage":"https://github.com/djd1m/dz-harness-hub/tree/main/packages/@dzhechkov/skills-book-digitizer#readme","bugs":{"url":"https://github.com/djd1m/dz-harness-hub/issues"},"dist":{"shasum":"12e7d43e1ca530b44caa606f51734c6e32c58fbe","tarball":"https://registry.npmjs.org/@dzhechkov/skills-book-digitizer/-/skills-book-digitizer-0.2.18.tgz","fileCount":16,"integrity":"sha512-7Zb1Z72OrB5u/7d6KdpzNuuEkM5fdKAq4aJFC0BzF7wxF0P5R+UdSbh2ZE/5+vFI6cT24uyyiRuLhkJx0l5tTw==","signatures":[{"sig":"MEQCIBgmFkuV4BhgdjuemmL7ztb/D4GNqfMlyP6NaGEhoQubAiBYUaDA1iCdLO3kC5c5iKi/BAIVNPLZdRVhoC57E0MYDg==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":111278},"_from":"file:dzhechkov-skills-book-digitizer-0.2.18.tgz","scripts":{},"_npmUser":{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"},"_resolved":"/tmp/7ff108a478205aaffdeeef73bef25f25/dzhechkov-skills-book-digitizer-0.2.18.tgz","_integrity":"sha512-7Zb1Z72OrB5u/7d6KdpzNuuEkM5fdKAq4aJFC0BzF7wxF0P5R+UdSbh2ZE/5+vFI6cT24uyyiRuLhkJx0l5tTw==","repository":{"url":"git+https://github.com/djd1m/dz-harness-hub.git","type":"git","directory":"packages/@dzhechkov/skills-book-digitizer"},"_npmVersion":"10.9.4","description":"Canonical book-digitizer skill pack — 8 skills that turn an engineering book/textbook/monograph into an installable skill pack whose skills make AI coders work within the book's methodologies: digitize-book (orchestrator), book-ingest, book-knowledge-extr","directories":{},"_nodeVersion":"22.22.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/skills-book-digitizer_0.2.18_1788003785735_0.03520171618892309","host":"s3://npm-registry-packages-npm-production"}},"0.2.19":{"name":"@dzhechkov/skills-book-digitizer","version":"0.2.19","keywords":["agent-skills","agentskills.io","skill-pack","claude-code","knowledge-extraction","book","pdf","methodology","agentdb"],"author":{"name":"dzhechko"},"license":"MIT","_id":"@dzhechkov/skills-book-digitizer@0.2.19","maintainers":[{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"}],"homepage":"https://github.com/djd1m/dz-harness/tree/main/packages/@dzhechkov/skills-book-digitizer#readme","bugs":{"url":"https://github.com/djd1m/dz-harness/issues"},"dist":{"shasum":"bc88686479b0805b8caf9d1a165b659bc65c9ba1","tarball":"https://registry.npmjs.org/@dzhechkov/skills-book-digitizer/-/skills-book-digitizer-0.2.19.tgz","fileCount":16,"integrity":"sha512-GmVQkjjnhOkOS1lZGmSOhBPGBgQveALXCk+Igm0gjXrSqPDVaRLW+ETrDlOEyMbiGE61TkPFoG/ln31z7AYX8A==","signatures":[{"sig":"MEYCIQCVS+tQZWHlp90LXvwsX4VKVC0Pfww7n7csFDD+tfYF0gIhANgIg9c91TywCrAbWvlPLbKcvigW0v/EaSbe+3+Qm4FY","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":111347},"_from":"file:dzhechkov-skills-book-digitizer-0.2.19.tgz","scripts":{},"_npmUser":{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"},"_resolved":"/tmp/adca80be36b7c2fae4aea14e77121101/dzhechkov-skills-book-digitizer-0.2.19.tgz","_integrity":"sha512-GmVQkjjnhOkOS1lZGmSOhBPGBgQveALXCk+Igm0gjXrSqPDVaRLW+ETrDlOEyMbiGE61TkPFoG/ln31z7AYX8A==","repository":{"url":"git+https://github.com/djd1m/dz-harness.git","type":"git","directory":"packages/@dzhechkov/skills-book-digitizer"},"_npmVersion":"10.9.4","description":"Canonical book-digitizer skill pack — 8 skills that turn an engineering book/textbook/monograph into an installable skill pack whose skills make AI coders work within the book's methodologies: digitize-book (orchestrator), book-ingest, book-knowledge-extr","directories":{},"_nodeVersion":"22.22.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/skills-book-digitizer_0.2.19_1788025732879_0.07704038208932218","host":"s3://npm-registry-packages-npm-production"}},"0.2.20":{"_id":"@dzhechkov/skills-book-digitizer@0.2.20","bugs":{"url":"https://github.com/djd1m/dz-harness/issues"},"dist":{"shasum":"2e807d452529ae630b79c7d6cb78c5ca4f69acb4","tarball":"https://registry.npmjs.org/@dzhechkov/skills-book-digitizer/-/skills-book-digitizer-0.2.20.tgz","fileCount":16,"integrity":"sha512-oirHnlISTgYGcQTbhMpHlofAF7CV4VCgRM5u0nAwzqWmuyig0O6cuLeCyTuKfKIgoiAT2Cg9gKc5IFI27IbEWA==","signatures":[{"sig":"MEUCIBZV4Z2mZ4Sg85GY48Azdpc8MNQGbfHJgfbkroj9q/wTAiEAhom0M6oxzgFibdouxwYtEV5rItmt7qhqo2nh0SmLG+E=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEQCIBhggEDH3gUHoZOhmYfyRGqu0JpcJd2tvljZUVJgML6OAiA/KNabXgFSwyf3zV8X1oCqQ8Tc8VVhU/dRtW2eJ1lXNQ=="}],"unpackedSize":117809},"name":"@dzhechkov/skills-book-digitizer","_from":"file:dzhechkov-skills-book-digitizer-0.2.20.tgz","author":{"name":"dzhechko"},"license":"MIT","scripts":{},"version":"0.2.20","_npmUser":{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"},"homepage":"https://github.com/djd1m/dz-harness/tree/main/packages/@dzhechkov/skills-book-digitizer#readme","keywords":["agent-skills","agentskills.io","skill-pack","claude-code","knowledge-extraction","book","pdf","methodology","agentdb"],"_resolved":"/tmp/16ceb69fd52a5dbf922aa1328db8c9bd/dzhechkov-skills-book-digitizer-0.2.20.tgz","_integrity":"sha512-oirHnlISTgYGcQTbhMpHlofAF7CV4VCgRM5u0nAwzqWmuyig0O6cuLeCyTuKfKIgoiAT2Cg9gKc5IFI27IbEWA==","repository":{"url":"git+https://github.com/djd1m/dz-harness.git","type":"git","directory":"packages/@dzhechkov/skills-book-digitizer"},"_npmVersion":"10.9.4","description":"Canonical book-digitizer skill pack — 8 skills that turn an engineering book/textbook/monograph into an installable skill pack whose skills make AI coders work within the book's methodologies: digitize-book (orchestrator), book-ingest, book-knowledge-extr","directories":{},"maintainers":[{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"}],"_nodeVersion":"22.22.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/skills-book-digitizer_0.2.20_1789293570831_0.04422769633278523"}}},"time":{"created":"2026-07-03T16:45:50.431Z","modified":"2026-09-13T09:59:31.129Z","0.1.0":"2026-07-03T16:45:50.786Z","0.1.1":"2026-07-03T17:16:17.051Z","0.2.0":"2026-07-03T17:29:45.011Z","0.2.2":"2026-07-03T20:07:10.947Z","0.2.4":"2026-07-03T20:34:13.348Z","0.2.6":"2026-07-04T06:37:44.262Z","0.2.8":"2026-07-04T07:03:59.422Z","0.2.10":"2026-07-04T07:53:03.616Z","0.2.12":"2026-07-04T08:03:24.609Z","0.2.14":"2026-07-04T08:18:52.154Z","0.2.15":"2026-08-25T04:41:59.883Z","0.2.16":"2026-08-28T19:14:54.506Z","0.2.17":"2026-08-28T19:21:16.362Z","0.2.18":"2026-08-29T11:43:05.962Z","0.2.19":"2026-08-29T17:48:53.010Z","0.2.20":"2026-09-13T09:59:30.948Z"},"bugs":{"url":"https://github.com/djd1m/dz-harness/issues"},"author":{"name":"dzhechko"},"license":"MIT","homepage":"https://github.com/djd1m/dz-harness/tree/main/packages/@dzhechkov/skills-book-digitizer#readme","keywords":["agent-skills","agentskills.io","skill-pack","claude-code","knowledge-extraction","book","pdf","methodology","agentdb"],"repository":{"url":"git+https://github.com/djd1m/dz-harness.git","type":"git","directory":"packages/@dzhechkov/skills-book-digitizer"},"description":"Canonical book-digitizer skill pack — 8 skills that turn an engineering book/textbook/monograph into an installable skill pack whose skills make AI coders work within the book's methodologies: digitize-book (orchestrator), book-ingest, book-knowledge-extr","maintainers":[{"name":"dzhechkov","email":"jechkov.dmitriy@gmail.com"}],"readme":"# @dzhechkov/skills-book-digitizer\n\nTurn an engineering **book / textbook / monograph** into an **installable skill pack** whose skills\nmake AI coders (Claude Code, Codex, …) *work within the book's methodologies* — plus a searchable\nKnowledge Base behind them. dz-original; design & rationale in\n[ADR-001 v2](https://github.com/djd1m/dz-harness-hub/blob/main/features/book-knowledge-digitizer/03_adr/001-book-to-skillpack-pipeline.md)\n(passed a 4-lens adversarial design panel: 28 findings, all folded in).\n\n## What it produces\n\n`book.pdf` → `skills-book-<slug>`: a pack you `dz init --select …` so the agent applies the book's\nmethods at the decisions it's about — e.g. DDIA → `ddia-replication-topology-choice`,\n`ddia-partitioning-strategy`, `ddia-consistency-model-selection`.\n\n## The skills (a checkpointed pipeline + a terminal promote + one sibling)\n\n| Skill | Stage |\n|-------|-------|\n| `digitize-book` | **Orchestrator** — runs the pipeline through up to 6 human checkpoints (CP6 promote-to-brain optional), resumable across sessions |\n| `book-ingest` | PDF → chunked, page-anchored corpus + manifest (deterministic: poppler + heuristics, no LLM) |\n| `book-knowledge-extract` | corpus → **verified** Knowledge Units (map-reduce, dedup, KU-verify entailment, FACTS-verbatim/PROSE-paraphrase regime) |\n| `book-skill-distill` | verified KUs → **decision-moment** skills (slug-prefixed, routing evals + activation gate, KU→skill traceability) |\n| `book-pack-assemble` | skills → installable pack (`references/` deep-lookup + the per-book `brain/<slug>.sqlite` KB slice shipped inside, **private-by-default** distribution, collision gate, Copilot policy) |\n| `book-kb-index` | KUs → the memory layer: `.dz/memory/books.sqlite` (lexical) + shared agentdb (vector) |\n| `book-brain-register` | **Terminal promote (optional, CP6, ADR §5.1)** — promote this project's KUs into the durable **cross-project brain** (`~/.dz/brain/`) via `dz brain add --project . --source <slug>`. Default project-local only; an explicit, IP-relevant opt-in like CP5. The in-pipeline promote (vs the manual `dz brain add`). |\n| `source-brain-ingest` | **Sibling (not a book stage, ADR §6)** — deep-walk a **repo/dir** → the *same* Knowledge Units → the *same* brain via `dz brain add --from-kus … --kind repo`. One brain, two ingest front-ends (books + code). |\n\n## Install & use\n\n```bash\ndz init --target claude-code --select digitize-book\n# then, in your agent:  «оцифруй вот эту книгу — хочу, чтобы агент проектировал по её методикам»\n```\n\nPrerequisites: `poppler-utils` (ingest) and, for the KB, `dz setup --memory agentdb`\n(installs `agentdb` + `better-sqlite3`).\n\n## Usage scenarios\n\nThe digitizer produces three durable artifacts from one book: (1) an installable **skill pack**, (2) a\nper-project **two-store KB** (`book-kb-index` → `.dz/memory/books.sqlite` lexical + shared agentdb\nvector), and (3) a promote path into a durable cross-project **Knowledge Brain** (`~/.dz/brain/`).\nFull design + the RU version: [ADR-001 Knowledge Brain](https://github.com/djd1m/dz-harness-hub/blob/main/features/book-brain/ADR-001-knowledge-brain.md).\n\n### 1. Digitize a book → skills + KB\n\nThe core pipeline. Install the orchestrator, then hand it a PDF; it runs `book-ingest → extract →\ndistill → assemble → book-kb-index` through 5 human checkpoints (CP1–CP5), plus an optional CP6\n`book-brain-register` to promote the book into the cross-project brain (scenario 3).\n\n```bash\ndz init --target claude-code --select digitize-book\n# then, in your agent:  «оцифруй вот эту книгу — хочу, чтобы агент проектировал по её методикам»\n```\n\nOutput: a `skills-book-<slug>` pack (decision-moment skills) **and** the two-store KB behind it. Live\nrun: DDIA → «Высоконагруженные приложения» digitized to **116 Knowledge Units**.\n\n> **Live public example:** [`@dzhechkov/skills-12factor`](https://www.npmjs.com/package/@dzhechkov/skills-12factor)\n> — The Twelve-Factor App (CC BY 4.0) digitized into 12 decision-moment skills, published publicly with\n> attribution. (A copyrighted book like DDIA instead stays `private` per CP5 — see scenario 5.)\n\n#### Install the generated pack into an agent\n\nThe generated pack lives as a local skill-pack directory (`packages/@dzhechkov/skills-book-<slug>`),\nversion-controlled but — for a copyrighted book — **`private: true`, never published to npm** (CP5 / IP).\nInstall its skills into any agent with one command (`dz` discovers the local pack; run it in the\ntarget project, wherever the pack/monorepo is available):\n\n```bash\n# one or more skills (comma-separated), for any target: claude-code | codex | opencode | hermes | openclaude | copilot\ndz init --target claude-code --select ddia-replication-topology-choice,ddia-partitioning-strategy\n\n# the whole pack — list every skill id (dz registry | grep <slug> to see them)\ndz init --target claude-code --select <id1>,<id2>,…\n```\n\nWrites `SKILL.md` into `.claude/skills/<id>/` (compiled to the target's format); the agent then\nactivates each on its decision moment. NB: `npx @dzhechkov/skills-book-<slug>` does **not** work for a\nprivate book pack — it's not on npm; install from a machine that has the pack.\n\n#### Make a portable bundle from them\n\nTo hand the skills to a generic / LangGraph consumer (self-contained, no `dz` needed downstream):\n\n```bash\ndz bundle --select ddia-replication-topology-choice,ddia-partitioning-strategy --out ./ddia-bundle\n```\n\nEmits a self-contained `skills/` tree (+ any cross-skill deps, with a warning if one is missing).\nSame CP5 rule applies: a copyrighted book's bundle stays owner-controlled — share only under your\nlicence decision (permissive/public-domain sources can be shared freely).\n\n### 2. Query one book's knowledge\n\nLexical (FTS5) recall over a single digitized book's KB, in the project that ingested it. `--book`\nnarrows the search to one book slug:\n\n```bash\ndz recall --books --book <slug> \"replication topology\"\n```\n\nPull-based: you ask, you get KU hits back with source + page anchors. No hook, no injection.\n\n### 3. Build a cross-project brain from N books\n\nPromote each project's digitized-book KUs into **one shared brain** (`~/.dz/brain/` — lexical\n`books.sqlite` + vector `agentdb.db`), then query across every ingested book at once. There are two\nways to promote — **in-pipeline** and **manual** — both drive the same `dz brain add`:\n\n- **In-pipeline (preferred): `book-brain-register`** — the optional terminal stage of `digitize-book`,\n  gated at **CP6 (promote?)**. After the pack + project KB are built, the orchestrator offers to promote\n  the book into the brain; the default is *project-local only* and promotion is an explicit, IP-relevant\n  opt-in (like CP5's distribution decision). It runs `dz brain add --project . --source <slug>` for you.\n- **Manual:** run the CLI yourself against a project whose book is already indexed.\n\n```bash\ndz brain add --project . --source <slug>   # promote this project's KUs into the brain (idempotent)\ndz brain list                              # what's in the brain: slug, kind, KU count, corpus version\ndz brain query \"replication topology\"      # cross-source recall over ALL books\ndz brain query \"replication topology\" --source <slug>   # optional: narrow to one book\ndz brain update <slug> --project .         # non-clobbering refresh of a re-digitized book\n```\n\nOne shared store, not per-book packages: you do **not** install anything to query the brain — it\naccretes on `dz brain add`. The *right* book surfaces by **relevance** (KUs rank on one common scale,\neach hit labelled with its source book + page); `--source` is a label filter, not a manual routing\npick. Cross-source is the default — multiple books scoring on a query is a feature (richer grounding),\nnot a bug. The brain is **private by default and never distributed** (ADR §8): CP6 promotes a\ncopyrighted book into your *local* brain only.\n\n### 4. Grounded answering (the hook)\n\n```bash\ndz brain init                            # opt-in: wire the grounding UserPromptSubmit hook (once)\ndz brain ground \"<prompt>\"               # what the hook runs: retrieve + emit citations (or nothing)\n```\n\n`dz brain init` (opt-in) wires a single `UserPromptSubmit` hook that runs `dz brain ground` on each\nprompt. On a *relevant* prompt (relevance-gated, so it stays quiet on unrelated turns) the hook\nmechanically retrieves top-K brain KUs and injects them — with source + page citations — into that\nturn's context, so the agent answers **from the book, not from training data**. Off by default; a\nprompt with no lexical overlap (e.g. \"what's the weather\") injects nothing.\n\nHonesty boundary: the injection is **mechanical** (the hook forces the grounding block into context and\nthe agent literally cannot start the turn without it); \"answering from it\" is **agent discipline** — the\nhook can force the context but not the completion. The hook is **generic and wired once** (one hook over\nthe whole brain across all sources — *not* per book), and needs **no edits to `CLAUDE.md` or governance\nshards** — the injection channel is the hook's stdout (`hookSpecificOutput.additionalContext`).\n\n### 5. Sharing a digitized book\n\nThe `skills-book-<slug>` **pack** (via GitHub / `npx`) carries the behavior — the decision-moment\nskills and `references/` deep-lookup. The design (ADR §8.1, P2) also ships the book's **KB slice inside\nthe pack** under the same CP5 licence decision that gates the pack itself: copyrighted books stay\n`private: true` (structural, mechanically enforced — no auto-publish, no preset entry), permissive\nsources are publishable. Your whole personal **brain is never published** — it is a local accretion you\nback up, not a distributable.\n\n### 6. Как пользоваться оцифрованной книгой (consuming a digitized book)\n\nDigitizing is half the loop. Four ways to make the book's methodology actually shape your work,\nfrom one-off to standing. Vocabulary, once: a **KU** (Knowledge Unit) is one page-anchored piece of\nthe book's know-how; a **kuId** is its stable id (e.g. `ai-apps-ch09-p238-ku05`); the **slug** is\nthe short name the book got at digitization (e.g. `ai-apps`); **CP6** is the pipeline's final\ncheckpoint, where you optionally promote a book from the project KB into the machine-wide brain.\n\nPrerequisites for everything below: `dz` installed, the book digitized (scenario 1), and — for the\n`dz brain` commands — the book promoted into the brain (CP6 approved, or a manual\n`dz brain add --project <ingesting-project> --source <slug>`). `dz brain list` shows what made it in.\n\n**M1 — one answer, grounded (chat).** Ask with «обоснуй по книге <slug>», or pull manually:\n\n```bash\ndz brain query \"evaluation metrics for language agents\" --source ai-apps\ndz brain expand ai-apps-ch09-p238-ku05        # one KU's full stored content\ndz brain ground \"how should I eval my agent?\" --source ai-apps --budget 800 --text\n```\n\n`query` returns ranked KU hits with source + page anchors; `expand` dereferences one kuId to that\nKU's full stored record (name, problem, content, page anchors); `ground --budget N --text` prints a\nready-to-paste grounding block with the top KUs inlined within ~N tokens (per `dz brain --help`).\nWhere the kuId comes from: the plain `query` output prints citations *without* ids — take it from\n`dz brain query … --json` (`hits[].kuId`) or from the `ground --text` block, where every `[Kn]`\nline carries its kuId as the first field.\n\n**M2 — one pipeline run.** Put the obligation in the run's task description itself, e.g.:\n\n> Дизайн обязан свериться с ai-apps через `dz brain query`; ключевые решения цитируют kuId;\n> расхождение с книгой допустимо только с названной причиной.\n\nNo setup; the obligation travels inside the brief, so it works in any pipeline whose agent reads\nthe brief and can run shell commands — and it holds for that run only.\n\n**M3 — whole project, while the hook stays installed.** Wire the opt-in grounding hook once\n(Claude Code projects — the hook lands in that project's `.claude/settings.json`):\n\n```bash\ndz brain init --project <dir> --k 5\n```\n\nPrompts with enough lexical overlap with the brain then get top-K KUs (with citations) injected\nmechanically before the agent answers — scenario 4 above is this same hook, including its honesty\nboundary (the hook forces the context, not the completion). Off by default. To disarm: remove the\n`hooks.UserPromptSubmit` entry whose command contains `brain ground` from that project's\n`.claude/settings.json`.\n\n**M4 — one pipeline, standing.** Add a stage-gate line to the rules/instructions file that\npipeline actually loads — for Claude Code e.g. `.claude/rules/<pipeline>.md`; other harnesses have\ntheir own equivalent (`AGENTS.md`, a system-prompt file): \"the design stage passes only if it cites\n`dz brain query` results (kuIds) or names the reason it diverges.\" No hook install; scoped to one\nworkflow, persisted in that pipeline's rules file.\n\n**The two-store trap (will cost you a 0-hit session).** There are TWO stores:\n`dz brain query|ground|expand` read the **machine-wide brain** (`~/.dz/brain` — only what was\npromoted at CP6 / `dz brain add`), while\n\n```bash\ndz recall --books --book <slug> \"<question>\"\n```\n\nreads the **project-local** book KB (`.dz/memory/books.sqlite` — only books digitized in THIS\nproject). Querying the wrong store answers `0 KU hit(s)` and exits 0 — no error names the mistake.\nRule of thumb: cross-project answers → `brain`; inside the ingesting project → `recall --books`.\nIn doubt, `dz brain list` names what the brain actually holds.\n\n**Worked example.** You digitized \"AI Apps\" as slug `ai-apps` and want a feature pipeline to design\nevals by the book: (1) `dz brain list` — confirm `ai-apps` is there (if not, promote as above);\n(2) start the pipeline the way you normally do — the launch syntax is your pipeline's own — with\nthe M2 obligation line pasted into its task description; (3) the design stage runs\n`dz brain query \"evaluation metrics for language agents\" --source ai-apps`, cites e.g.\n`[ai-apps гл.9 с.239]` (semantic-similarity metrics over exact match), and expands\n`ai-apps-ch09-p238-ku05` for the full text; (4) if this becomes routine, promote M2 → M4 (a rules\nline) or M3 (the hook).\n\n## Design guarantees — structural vs. protocol (stated honestly)\n\nTwo kinds of guarantee, and the difference matters:\n\n- **Structural (mechanically enforced by code/packaging):** generated packs ship `private: true` +\n  restricted `publishConfig` and get **no automatic preset entry** — a book-derived pack cannot be\n  auto-published; distribution is your explicit CP5 decision. `files[]` whitelist + no-`origin`\n  `sources.json`. The ingest is deterministic. The book KB is a separate namespace (book KUs never\n  pollute `dz recommend`). The **word-shingling verbatim-check is now a shipped deterministic gate**\n  (`scripts/shingling-check.mjs`) run at pack assembly: any uncited verbatim run ≥8 words fails the\n  pack (cited ≤25-word quotes with a page anchor are exempt) — the paraphrase rule is mechanically\n  enforced, no longer merely agent-enforced.\n- **Protocol (agent-enforced, fail-open — NOT mechanically proven):** KU provenance is\n  *agent-verified* (an entailment pass re-reads the cited pages) but not cryptographically proven;\n  the FACTS-verbatim / PROSE-paraphrase fidelity regime and the KU→skill traceability are\n  discipline the distill/extract agents follow. Generated skills therefore ship at **`trust_tier`\n  0/1 (\"machine-distilled, unreviewed\")** with a documented promote path (human review against the\n  cited pages, or passing the routing evals).\n\n- **Honest cost** — a 640-page book ≈ 2.5–4M agent-tokens end-to-end; the orchestrator shows the\n  estimate at CP1 and hard-gates the bulk map behind your sample review at CP2.\n\n## Provenance\n\ndz-original (ADR-001). Delegates by reference to `skill-crystallizer` (skill scaffolding/benchmark)\nand `knowledge-extractor` (quality-gate discipline) — see `sources.json`.\n\n## License\n\nMIT © dzhechko.\n\n## Keyword-конвенция для оцифрованных паков (2026-08-25)\n\nКаждый пак, произведённый этим дигитайзером, несёт в `package.json → keywords`:\n- **`dz-digitized`** — общий тег: «получено конвейером дигитайзера» (книга, статья, веб-манифест).\n- **`digitized-monograph`** — подтег ТОЛЬКО для книг/монографий (не для веб-источников вроде 12factor).\n\nПоиск: `npm search keywords:digitized-monograph` (все оцифрованные книги),\n`npm search keywords:dz-digitized` (всё, что произвёл дигитайзер). В реестре — `dz registry --category knowledge`.\n","readmeFilename":"README.md"}