[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MF8R7KTJ78HBJVJWESTA4B":3,"skill-same:01M6MF8R7KTJ78HBJVJWESTA4B":76},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":25,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":13,"repositoryHtmlUrl":59,"repositoryHomepageUrl":6,"ownerHtmlUrl":60,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":61,"install":62,"resources":75},"01M6MF8R7KTJ78HBJVJWESTA4B","book-to-skill",null,"Converts books, documentation folders, and source collections (PDF, EPUB, DOCX, HTML, Markdown, RST, AsciiDoc, RTF, MOBI\u002FAZW) into structured agent skills — extracting named frameworks, principles, techniques, and anti-patterns into a master SKILL.md plus on-demand chapter files, a glossary, a patterns file, and a decision cheatsheet. Use when the user wants to study a document with an agent, apply an author's frameworks while working, turn internal docs or standards into a reusable knowledge base, or package a compiled book skill as a claude-skills plugin.","JiayiV\u002Fquestion_mixing","JiayiV","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54466889?v=4","01M6JFJYYMRZ3QRGP9339JNQ2K","01M6JFJZ35KB0QVT50NAHPJA7G",0,"MIT","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-gemini-skills-book-to-skill-skill-0da11b8f\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"book","book to skill","master","source","books","claude-skills","extracting","knowledge base","patterns","wed","files","docx","anti-patterns","decision","glossary","knowledge","markdown","cheatsheet","documentation","PDF","2026-11-10 10:12:30",false,"---\nname: book-to-skill\ndescription: \"Converts books, documentation folders, and source collections (PDF, EPUB, DOCX, HTML, Markdown, RST, AsciiDoc, RTF, MOBI\u002FAZW) into structured agent skills — extracting named frameworks, principles, techniques, and anti-patterns into a master SKILL.md plus on-demand chapter files, a glossary, a patterns file, and a decision cheatsheet. Use when the user wants to study a document with an agent, apply an author's frameworks while working, turn internal docs or standards into a reusable knowledge base, or package a compiled book skill as a claude-skills plugin.\"\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  author: Alireza Rezvani\n  category: engineering\n  updated: 2026-08-05\n---\n\n# Book-to-Skill Converter\n\nTurn written knowledge into an agent skill by extracting **structure**, not summaries.\n\nA book is crystallized expertise: frameworks, principles, techniques that took years to\ndevelop. Read once, forgotten. The workarounds all fail — PDF search returns page numbers\ninstead of answers, an agent handed the raw file hallucinates or drowns, reading notes rot.\nThis skill compiles a source into a knowledge base the agent loads on demand: a small\nresident core, one chapter file at a time, and never the whole book again.\n\n**What it produces:**\n\n| File | Contents | Budget |\n|------|----------|--------|\n| `SKILL.md` | Core frameworks + chapter index + topic index | \u003C 4,000 tokens (resident) |\n| `chapters\u002FchNN-*.md` | One summary per chapter | 800–3,000 tokens, on demand |\n| `glossary.md` | Every significant term, alphabetized, with chapter | \u003C 1,500 tokens |\n| `patterns.md` | Techniques and design patterns with trade-offs | \u003C 2,000 tokens |\n| `cheatsheet.md` | Decision rules, thresholds, trade-off matrices | \u003C 1,200 tokens |\n\n**Beyond books:** anything referenced often enough to be worth memorizing — internal\ndocumentation, brand systems, standards, specs, research clusters, a folder of RFCs.\n\n---\n\n## Philosophy\n\n**Extract structure, not summaries.** A skill is not a book report. It is a toolkit of\nnamed frameworks, actionable principles, step-by-step techniques, anti-patterns, and the\nauthor's voice.\n\n**Preserve the author's precision.** Framework names are interfaces. \"The 5 Whys\" is not\ninterchangeable with \"ask why a few times\" — the exact formulation is what makes lookup work.\n\n**Layer depth appropriately.** A thin book gets a thin skill. A book with fifteen frameworks\ngets chapter files and a real topic index.\n\n**Never reproduce the source at length.** These are structured notes. Synthesize, compress,\nname — do not copy passages. See `references\u002Frights_and_provenance.md`.\n\n---\n\n## Modes\n\n| Mode | Trigger | Runs |\n|------|---------|------|\n| **1. Full conversion** (default) | One or more paths, no special instruction | Steps 0–10 |\n| **2. Analyze only** | \"analyze\", \"just extract\", \"let me review first\" | Steps 0–3, then stop with an extraction report |\n| **3. Generate from analysis** | User supplies prior analysis notes | Steps 4–10 |\n| **4. Update \u002F fold-in** | New sources + an existing compiled skill | Steps 0–2, then the Update Workflow |\n| **5. Package as plugin** | \"make it a plugin\", \"add it to the repo\" | Step 11 |\n\nMode 5 is this repository's addition. Upstream stops at a bare folder in a personal skills\nhome; Step 11 wraps that folder in a plugin package other skills and agents can route to.\n\n---\n\n## Hard rules\n\n1. **Never convert a source the user cannot show you.** No web-scraping a book, no\n   reconstructing a title from memory. This tool converts files that are already on disk.\n2. **Pre-flight the cost before generating** (Step 2.5). Generation is the expensive part;\n   the user approves it with numbers in front of them.\n3. **Never dump a large source into context.** Over ~50k tokens, probe with `grep`\u002F`sed`\n   and bounded reads (Step 2.6). Re-reading a 200-page book once per chapter costs more\n   than everything else in this workflow combined.\n4. **Validate before anyone loads it** (Step 9.5). A generated skill is untrusted text that\n   an agent will later read as instructions.\n5. **Never widen the generated skill's authority.** Generated frontmatter carries `name` and\n   `description` only — no `allowed-tools`, no model-invocation flags.\n6. **Rights before redistribution.** Compiled notes from a copyrighted work are personal\n   study notes. Packaging one as a shareable plugin requires a stated basis (Step 11).\n7. **State what the skill does not cover.** Every compiled skill's Scope section names its\n   boundary, so the agent says \"the source doesn't cover this\" instead of improvising.\n\n---\n\n## Pipeline\n\n```\nextract_document.py  →  analyze  →  chapter files  →  supporting files  →  SKILL.md\n      (Step 2)          (Step 3)      (Step 7)          (Step 8)          (Step 9)\n                                                                              ↓\n                                       skill_plugin_emitter.py  ←  book_skill_validator.py\n                                              (Step 11)                  (Step 9.5)\n```\n\nAll four tools live in `scripts\u002F` and run on the standard library alone.\n\n---\n\n## Run it\n\n```bash\nSKILL_ROOT=engineering\u002Fbook-to-skill\u002Fskills\u002Fbook-to-skill\nSKILLS_HOME=~\u002F.claude\u002Fskills        # Step 5 picks this; see the workflow reference\nWORKDIR=$(mktemp -d)                # or omit --workdir and capture the path it prints\nSLUG=\u003Cauthor-lastname>-\u003Cconcept>\n\n# 1. extract → $WORKDIR\u002Ffull_text.txt + metadata.json\n#    --mode technical when tables, code or formulas carry meaning\npython3 \"$SKILL_ROOT\u002Fscripts\u002Fextract_document.py\" \u003Cpaths> --mode text --workdir \"$WORKDIR\"\n\n# 2. pre-flight: is this worth converting at all? Wait for approval before generating.\npython3 \"$SKILL_ROOT\u002Fscripts\u002Ftoken_budget_estimator.py\" --full-text \"$WORKDIR\u002Ffull_text.txt\"\n\n# 3. generate — the agent's work: chapters\u002F, glossary, patterns, cheatsheet, SKILL.md\n\n# 4. gate — errors block. Fix and re-run; never rewrite around a finding.\npython3 \"$SKILL_ROOT\u002Fscripts\u002Fbook_skill_validator.py\" \"$SKILLS_HOME\u002F$SLUG\"\npython3 \"$SKILL_ROOT\u002Fscripts\u002Ftoken_budget_estimator.py\" --skill-dir \"$SKILLS_HOME\u002F$SLUG\"\n\n# 5. optional: wrap as a claude-skills plugin so the library can route to it\npython3 \"$SKILL_ROOT\u002Fscripts\u002Fskill_plugin_emitter.py\" --skill-dir \"$SKILLS_HOME\u002F$SLUG\" \\\n    --dest .\u002Fengineering --source-note \"\u003CTitle> by \u003CAuthor>\" --dry-run\n```\n\nEvery path above is a real variable, not a placeholder: run the block as written (with\n`\u003Cpaths>` and `$SLUG` filled in) and it works end to end. Without `--workdir` the extractor\ncreates a private temp directory and prints it — capture that instead.\n\n`extract_document.py --check` reports which extractors are installed and prints the install\ncommand for what is missing. Every tool supports `--help`, `--sample` and `--output json`.\n\n**The full step-by-step procedure — what to ask at each step, the file templates, the\nper-chapter budget matrix, and the update\u002Ffold-in workflow — is in\n[`references\u002Fconversion_workflow.md`](references\u002Fconversion_workflow.md). Read it before\nrunning a conversion.** Summary of the eleven steps:\n\n| Step | Does |\n|------|------|\n| 0–1 | Scope check; resolve paths; detect an update\u002Ffold-in against an existing skill |\n| 1.5 | Ask content type → `BOOK_TYPE` (technical vs. text), which picks the extractor |\n| 2 | Extract → `full_text.txt` + `metadata.json` |\n| 2.5 | Pre-flight cost estimate and worth-converting verdict — **wait for approval** |\n| 2.6 | Over ~50k tokens, probe with `grep`\u002F`sed` instead of reading the source |\n| 3 | Analyze structure (title, author, chapters, themes). Mode 2 stops here. |\n| 4 | Ask purpose → `DEPTH` (reference vs. study). Never ask a second budget question. |\n| 5 | Skill name and destination root; offer update \u002F overwrite \u002F rename on a collision |\n| 6–8 | Create the structure; write chapter files; write glossary, patterns, cheatsheet |\n| 9 | Write the master `SKILL.md` — under 4,000 tokens, indexes intact |\n| 9.5 | Validate. Errors block. |\n| 10 | Clean up the workdir and report |\n| 11 | Optionally package as a plugin, behind the rights gate |\n\n## Validator findings worth knowing\n\n| Rule | Means |\n|------|-------|\n| `index.dead_link` | The chapter index links a file that was never written |\n| `index.topic_dangling` | A topic points at a chapter that does not exist |\n| `budget.over_cap` on SKILL.md | Compaction will truncate the indexes — navigation is the first thing lost |\n| `unicode.invisible` | Extraction should have stripped this; investigate the source |\n| `frontmatter.allowed_tools` | The generated skill is trying to grant itself tool authority |\n\nSafety-family warnings are deliberately broad — a source about prompt injection legitimately\ntrips them. Read each in context; do not auto-silence them.\n\n## Forcing-question library\n\nWalk these one at a time, with a recommended answer, before running a conversion.\n\n1. **\"Is this source worth converting, or should I just read it?\"**\n   *Recommended:* convert when it is > 3× the compiled skill's size **and** you will return\n   to it. One-shot reads are cheaper unconverted. (Step 2.5 verdict.)\n\n2. **\"Reference or study?\"**\n   *Recommended:* reference, unless you intend to internalize the author's reasoning. Study\n   depth roughly doubles generation cost and is only worth it with real worked examples.\n   (Step 4.)\n\n3. **\"Technical or text?\"**\n   *Recommended:* technical only when tables, code, or formulas carry meaning. Docling costs\n   ~1.5s\u002Fpage; picking it for a prose book buys nothing. (Step 1.5.)\n\n4. **\"What will you actually ask this skill?\"**\n   *Recommended:* name three real questions before generating. They tell you what belongs in\n   Core Frameworks and what the topic index must resolve. A skill nobody queries is a\n   summary nobody reads.\n\n5. **\"Do you have the right to redistribute this?\"**\n   *Recommended:* assume not. Keep it local unless the source is public-domain, openly\n   licensed, your organisation's own documentation, or you have written permission.\n   (Step 11 rights gate.)\n\n6. **\"Does this belong beside an existing skill?\"**\n   *Recommended:* check for an existing compiled skill on the same subject first — folding\n   new sources into one skill (Mode 4) beats two skills that half-cover a topic and give\n   the agent no way to choose. (Step 0.)\n\n---\n\n## References\n\n- `references\u002Fconversion_workflow.md` — **the full procedure**: Steps 0–11, the file\n  templates, the per-chapter budget matrix, and the update\u002Ffold-in workflow\n- `references\u002Fknowledge_extraction_canon.md` — why structure beats summary; the extraction\n  taxonomy; what makes a framework survive compression\n- `references\u002Fprogressive_disclosure_budgets.md` — where the token budgets come from and\n  what breaks when they are exceeded\n- `references\u002Fdocument_extraction_pipeline.md` — per-format extractor chains, fallbacks,\n  and the failure modes that produce silently bad text\n- `references\u002Frights_and_provenance.md` — copyright posture, the rights gate, and what\n  provenance a compiled skill must carry\n\n## Related skills\n\n- **`engineering\u002Fwrite-a-skill`** — authoring a skill from your own expertise. Use that when\n  the knowledge is in your head; use this when it is in a document.\n- **`engineering\u002Fskill-security-auditor`** — full security audit of a skill package. Step 9.5\n  is the converter's own gate; the auditor is the repo-wide one.\n- **`engineering\u002Fllm-wiki`** — an incrementally-grown, interlinked vault across many sources.\n  This skill compiles one bounded source set into one skill.\n\n---\n\n*Adapted from [virgiliojr94\u002Fbook-to-skill](https:\u002F\u002Fgithub.com\u002Fvirgiliojr94\u002Fbook-to-skill) (MIT).\nSee `..\u002F..\u002FREADME.md` for the full list of deviations.*\n","# Book-to-Skill Converter\n\nTurn written knowledge into an agent skill by extracting **structure**, not summaries.\n\nA book is crystallized expertise: frameworks, principles, techniques that took years to\ndevelop. Read once, forgotten. The workarounds all fail — PDF search returns page numbers\ninstead of answers, an agent handed the raw file hallucinates or drowns, reading notes rot.\nThis skill compiles a source into a knowledge base the agent loads on demand: a small\nresident core, one chapter file at a time, and never the whole book again.\n\n**What it produces:**\n\n| File | Contents | Budget |\n|------|----------|--------|\n| `SKILL.md` | Core frameworks + chapter index + topic index | \u003C 4,000 tokens (resident) |\n| `chapters\u002FchNN-*.md` | One summary per chapter | 800–3,000 tokens, on demand |\n| `glossary.md` | Every significant term, alphabetized, with chapter | \u003C 1,500 tokens |\n| `patterns.md` | Techniques and design patterns with trade-offs | \u003C 2,000 tokens |\n| `cheatsheet.md` | Decision rules, thresholds, trade-off matrices | \u003C 1,200 tokens |\n\n**Beyond books:** anything referenced often enough to be worth memorizing — internal\ndocumentation, brand systems, standards, specs, research clusters, a folder of RFCs.\n\n---\n\n## Philosophy\n\n**Extract structure, not summaries.** A skill is not a book report. It is a toolkit of\nnamed frameworks, actionable principles, step-by-step techniques, anti-patterns, and the\nauthor's voice.\n\n**Preserve the author's precision.** Framework names are interfaces. \"The 5 Whys\" is not\ninterchangeable with \"ask why a few times\" — the exact formulation is what makes lookup work.\n\n**Layer depth appropriately.** A thin book gets a thin skill. A book with fifteen frameworks\ngets chapter files and a real topic index.\n\n**Never reproduce the source at length.** These are structured notes. Synthesize, compress,\nname — do not copy passages. See `references\u002Frights_and_provenance.md`.\n\n---\n\n## Modes\n\n| Mode | Trigger | Runs |\n|------|---------|------|\n| **1. Full conversion** (default) | One or more paths, no special instruction | Steps 0–10 |\n| **2. Analyze only** | \"analyze\", \"just extract\", \"let me review first\" | Steps 0–3, then stop with an extraction report |\n| **3. Generate from analysis** | User supplies prior analysis notes | Steps 4–10 |\n| **4. Update \u002F fold-in** | New sources + an existing compiled skill | Steps 0–2, then the Update Workflow |\n| **5. Package as plugin** | \"make it a plugin\", \"add it to the repo\" | Step 11 |\n\nMode 5 is this repository's addition. Upstream stops at a bare folder in a personal skills\nhome; Step 11 wraps that folder in a plugin package other skills and agents can route to.\n\n---\n\n## Hard rules\n\n1. **Never convert a source the user cannot show you.** No web-scraping a book, no\n   reconstructing a title from memory. This tool converts files that are already on disk.\n2. **Pre-flight the cost before generating** (Step 2.5). Generation is the expensive part;\n   the user approves it with numbers in front of them.\n3. **Never dump a large source into context.** Over ~50k tokens, probe with `grep`\u002F`sed`\n   and bounded reads (Step 2.6). Re-reading a 200-page book once per chapter costs more\n   than everything else in this workflow combined.\n4. **Validate before anyone loads it** (Step 9.5). A generated skill is untrusted text that\n   an agent will later read as instructions.\n5. **Never widen the generated skill's authority.** Generated frontmatter carries `name` and\n   `description` only — no `allowed-tools`, no model-invocation flags.\n6. **Rights before redistribution.** Compiled notes from a copyrighted work are personal\n   study notes. Packaging one as a shareable plugin requires a stated basis (Step 11).\n7. **State what the skill does not cover.** Every compiled skill's Scope section names its\n   boundary, so the agent says \"the source doesn't cover this\" instead of improvising.\n\n---\n\n## Pipeline\n\n```\nextract_document.py  →  analyze  →  chapter files  →  supporting files  →  SKILL.md\n      (Step 2)          (Step 3)      (Step 7)          (Step 8)          (Step 9)\n                                                                              ↓\n                                       skill_plugin_emitter.py  ←  book_skill_validator.py\n                                              (Step 11)                  (Step 9.5)\n```\n\nAll four tools live in `scripts\u002F` and run on the standard library alone.\n\n---\n\n## Run it\n\n```bash\nSKILL_ROOT=engineering\u002Fbook-to-skill\u002Fskills\u002Fbook-to-skill\nSKILLS_HOME=~\u002F.claude\u002Fskills        # Step 5 picks this; see the workflow reference\nWORKDIR=$(mktemp -d)                # or omit --workdir and capture the path it prints\nSLUG=\u003Cauthor-lastname>-\u003Cconcept>\n\n# 1. extract → $WORKDIR\u002Ffull_text.txt + metadata.json\n#    --mode technical when tables, code or formulas carry meaning\npython3 \"$SKILL_ROOT\u002Fscripts\u002Fextract_document.py\" \u003Cpaths> --mode text --workdir \"$WORKDIR\"\n\n# 2. pre-flight: is this worth converting at all? Wait for approval before generating.\npython3 \"$SKILL_ROOT\u002Fscripts\u002Ftoken_budget_estimator.py\" --full-text \"$WORKDIR\u002Ffull_text.txt\"\n\n# 3. generate — the agent's work: chapters\u002F, glossary, patterns, cheatsheet, SKILL.md\n\n# 4. gate — errors block. Fix and re-run; never rewrite around a finding.\npython3 \"$SKILL_ROOT\u002Fscripts\u002Fbook_skill_validator.py\" \"$SKILLS_HOME\u002F$SLUG\"\npython3 \"$SKILL_ROOT\u002Fscripts\u002Ftoken_budget_estimator.py\" --skill-dir \"$SKILLS_HOME\u002F$SLUG\"\n\n# 5. optional: wrap as a claude-skills plugin so the library can route to it\npython3 \"$SKILL_ROOT\u002Fscripts\u002Fskill_plugin_emitter.py\" --skill-dir \"$SKILLS_HOME\u002F$SLUG\" \\\n    --dest .\u002Fengineering --source-note \"\u003CTitle> by \u003CAuthor>\" --dry-run\n```\n\nEvery path above is a real variable, not a placeholder: run the block as written (with\n`\u003Cpaths>` and `$SLUG` filled in) and it works end to end. Without `--workdir` the extractor\ncreates a private temp directory and prints it — capture that instead.\n\n`extract_document.py --check` reports which extractors are installed and prints the install\ncommand for what is missing. Every tool supports `--help`, `--sample` and `--output json`.\n\n**The full step-by-step procedure — what to ask at each step, the file templates, the\nper-chapter budget matrix, and the update\u002Ffold-in workflow — is in\n[`references\u002Fconversion_workflow.md`](references\u002Fconversion_workflow.md). Read it before\nrunning a conversion.** Summary of the eleven steps:\n\n| Step | Does |\n|------|------|\n| 0–1 | Scope check; resolve paths; detect an update\u002Ffold-in against an existing skill |\n| 1.5 | Ask content type → `BOOK_TYPE` (technical vs. text), which picks the extractor |\n| 2 | Extract → `full_text.txt` + `metadata.json` |\n| 2.5 | Pre-flight cost estimate and worth-converting verdict — **wait for approval** |\n| 2.6 | Over ~50k tokens, probe with `grep`\u002F`sed` instead of reading the source |\n| 3 | Analyze structure (title, author, chapters, themes). Mode 2 stops here. |\n| 4 | Ask purpose → `DEPTH` (reference vs. study). Never ask a second budget question. |\n| 5 | Skill name and destination root; offer update \u002F overwrite \u002F rename on a collision |\n| 6–8 | Create the structure; write chapter files; write glossary, patterns, cheatsheet |\n| 9 | Write the master `SKILL.md` — under 4,000 tokens, indexes intact |\n| 9.5 | Validate. Errors block. |\n| 10 | Clean up the workdir and report |\n| 11 | Optionally package as a plugin, behind the rights gate |\n\n## Validator findings worth knowing\n\n| Rule | Means |\n|------|-------|\n| `index.dead_link` | The chapter index links a file that was never written |\n| `index.topic_dangling` | A topic points at a chapter that does not exist |\n| `budget.over_cap` on SKILL.md | Compaction will truncate the indexes — navigation is the first thing lost |\n| `unicode.invisible` | Extraction should have stripped this; investigate the source |\n| `frontmatter.allowed_tools` | The generated skill is trying to grant itself tool authority |\n\nSafety-family warnings are deliberately broad — a source about prompt injection legitimately\ntrips them. Read each in context; do not auto-silence them.\n\n## Forcing-question library\n\nWalk these one at a time, with a recommended answer, before running a conversion.\n\n1. **\"Is this source worth converting, or should I just read it?\"**\n   *Recommended:* convert when it is > 3× the compiled skill's size **and** you will return\n   to it. One-shot reads are cheaper unconverted. (Step 2.5 verdict.)\n\n2. **\"Reference or study?\"**\n   *Recommended:* reference, unless you intend to internalize the author's reasoning. Study\n   depth roughly doubles generation cost and is only worth it with real worked examples.\n   (Step 4.)\n\n3. **\"Technical or text?\"**\n   *Recommended:* technical only when tables, code, or formulas carry meaning. Docling costs\n   ~1.5s\u002Fpage; picking it for a prose book buys nothing. (Step 1.5.)\n\n4. **\"What will you actually ask this skill?\"**\n   *Recommended:* name three real questions before generating. They tell you what belongs in\n   Core Frameworks and what the topic index must resolve. A skill nobody queries is a\n   summary nobody reads.\n\n5. **\"Do you have the right to redistribute this?\"**\n   *Recommended:* assume not. Keep it local unless the source is public-domain, openly\n   licensed, your organisation's own documentation, or you have written permission.\n   (Step 11 rights gate.)\n\n6. **\"Does this belong beside an existing skill?\"**\n   *Recommended:* check for an existing compiled skill on the same subject first — folding\n   new sources into one skill (Mode 4) beats two skills that half-cover a topic and give\n   the agent no way to choose. (Step 0.)\n\n---\n\n## References\n\n- `references\u002Fconversion_workflow.md` — **the full procedure**: Steps 0–11, the file\n  templates, the per-chapter budget matrix, and the update\u002Ffold-in workflow\n- `references\u002Fknowledge_extraction_canon.md` — why structure beats summary; the extraction\n  taxonomy; what makes a framework survive compression\n- `references\u002Fprogressive_disclosure_budgets.md` — where the token budgets come from and\n  what breaks when they are exceeded\n- `references\u002Fdocument_extraction_pipeline.md` — per-format extractor chains, fallbacks,\n  and the failure modes that produce silently bad text\n- `references\u002Frights_and_provenance.md` — copyright posture, the rights gate, and what\n  provenance a compiled skill must carry\n\n## Related skills\n\n- **`engineering\u002Fwrite-a-skill`** — authoring a skill from your own expertise. Use that when\n  the knowledge is in your head; use this when it is in a document.\n- **`engineering\u002Fskill-security-auditor`** — full security audit of a skill package. Step 9.5\n  is the converter's own gate; the auditor is the repo-wide one.\n- **`engineering\u002Fllm-wiki`** — an incrementally-grown, interlinked vault across many sources.\n  This skill compiles one bounded source set into one skill.\n\n---\n\n*Adapted from [virgiliojr94\u002Fbook-to-skill](https:\u002F\u002Fgithub.com\u002Fvirgiliojr94\u002Fbook-to-skill) (MIT).\nSee `..\u002F..\u002FREADME.md` for the full list of deviations.*\n",{"name":5,"license":14,"metadata":51,"description":7},{"author":52,"updated":53,"version":54,"category":55},"Alireza Rezvani",1785888000000,"1.0.0","engineering","main","068c2486ccc0f8d200a3db4d21ec137064eda3b4","skills\u002Fpublic-02-claude-skills-main-gemini-skills-book-to-skill-skill-0da11b8f","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing","https:\u002F\u002Fgithub.com\u002FJiayiV","2026-08-25 16:30:52",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add JiayiV\u002Fquestion_mixing --skill book-to-skill",{"tool":68,"command":69},"bunx","bunx skills add JiayiV\u002Fquestion_mixing --skill book-to-skill",{"tool":71,"command":72},"pnpm","pnpm dlx skills add JiayiV\u002Fquestion_mixing --skill book-to-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-gemini-skills-book-to-skill-skill-0da11b8f\u002FSKILL.md",true,[],[77,103,131,159,187,222],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":46},"01M6NN9PJS9NHWPDG4QP93BP8F","webmcpify","Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for \"webmcpify\", \"add WebMCP\", or \"expose app actions to AI agents\".","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fwebmcpify\u002FSKILL.md",[],[79,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102],"github","ai agents","web","notes","code","browser","https","actions","manifest","inventory","verify","tool","use","ready","unrelated","app","scope","for","webmcp",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":107,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":46},"01M6NN6KZE5RBN6NGHN2WXV1RE","vardoger-analyze","Use when the user asks to personalize the GitHub Copilot CLI assistant, adapt Copilot to their style, use vardoger, or analyze their Copilot CLI conversation history. Reads the local session directory at `~\u002F.copilot\u002Fsession-state\u002F`, extracts recurring preferences and conventions, and writes a fenced personalization block into `~\u002F.copilot\u002Fcopilot-instructions.md`. Runs entirely on the user's machine via the local `vardoger` CLI (`pipx install vardoger`); no network calls and no uploads. Triggers: 'personalize my copilot', 'analyze my copilot history', 'tailor copilot to me', 'run vardoger', 'update my copilot instructions from history', 'make copilot learn my style'.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fvardoger-analyze\u002FSKILL.md",[],[111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130],"vardoger analyze","analyze","directory","cli","github copilot","copilot","run","update","learn","network","my style","install","conversation","me","local","github copilot cli","pipx","my","at","copilot instructions",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":141,"publishedAt":46},"01M6NN3CZGQP3XAJ04BM1NNYGT","transloadit-media-processing","Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS\u002FMP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ processing robots for file transformation at scale.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftransloadit-media-processing\u002FSKILL.md",[137,140],{"categoryNo":138,"categoryName":139,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[142,143,144,145,146,147,148,149,150,151,152,153,154,96,155,36,156,157,101,158],"transloadit media processing","Media","media processing","processing","MCP","mcp server","documents","subtitles","pipeline","ocr","Video","Audio","mp4","images","transformation","free","hls",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":168,"publishedAt":46},"01M6NN28E92F9GH4WFYQ2H1Y15","terraform-azurerm-set-diff-analyzer","Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. Use when reviewing terraform plan output for Azure resources like Application Gateway, Load Balancer, Firewall, Front Door, NSG, and other resources with Set-type attributes that cause spurious diffs due to internal ordering changes.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fterraform-azurerm-set-diff-analyzer\u002FSKILL.md",[165],{"categoryNo":166,"categoryName":167,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[169,170,171,172,173,174,175,176,177,96,178,179,180,181,182,183,184,185,186,101],"terraform","SET","terraform azurerm set diff analyzer","diff","analyzer","diffs","azure","gateway","firewall","only","resource changes","provider","resources","load balancer","attributes","front","load","balancer",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":204,"publishedAt":46},"01M6NN1QMH2TDYWTH3XY3N5XPV","technical-job-search","Use this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV\u002Fresume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-job-search\u002FSKILL.md",[193,196,201],{"categoryNo":194,"categoryName":195,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":197,"categoryName":198,"taxonomyType":199,"taxonomyTypeDesc":200},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",{"categoryNo":202,"categoryName":203,"taxonomyType":199,"taxonomyTypeDesc":200},"01JBSEEDCAT000000000000038","人力资源",[205,206,207,208,209,210,211,212,112,213,96,214,215,216,217,218,219,220,101,221],"search","Job Search","technical job search","technical","writing","tasks","email","parsing","interview","up","engineer","general","activate","do","task","cv","letter",{"skillNo":223,"name":224,"nameZh":6,"description":225,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":226,"categories":227,"keywords":228,"publishedAt":46},"01M6NMZFA67XYS1GS09WT42235","steno-mode","Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says \"steno mode\", \"shorthand mode\", \"compressed responses\", \"token reduction\", \"brief structured output\", or invokes \u002Fsteno. Supports four compression levels: lite, brief, court, machine. Do not trigger for requests needing polished prose such as onboarding\u002Ftutorial content, stakeholder or customer-facing copy, or teaching-focused explanations.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fsteno-mode\u002FSKILL.md",[],[229,230,231,232,233,208,234,96,218,235,236,237,238,239,240,241,242,243,101,244],"steno mode","mode","customer","brief","first","tutorial","teaching","tokens","as","trigger","structured output","machine","output","court","requests","response compression"]