{"id":"2ab3d35a-1be4-4bc8-91b5-8012906b3e16","shortId":"VpJ4Mp","kind":"skill","title":"wiki-query","tagline":"Answer questions using the Obsidian wiki vault. Reads hot cache first, then index, then relevant pages. Synthesizes answers with citations. Files good answers back as wiki pages. Supports quick, standard, and deep modes. Triggers on: what do you know about, query:, what is, expla","description":"# wiki-query: Query the Wiki\n\nThe wiki has already done the synthesis work. Read strategically, answer precisely, and file good answers back so the knowledge compounds.\n\n---\n\n## Query Modes\n\nThree depths. Choose based on the question complexity.\n\n| Mode | Trigger | Reads | Token cost | Best for |\n|------|---------|-------|------------|---------|\n| **Quick** | `query quick: ...` or simple factual Q | hot.md + index.md only | ~1,500 | \"What is X?\", date lookups, quick facts |\n| **Standard** | default (no flag) | hot.md + index + 3-5 pages | ~3,000 | Most questions |\n| **Deep** | `query deep: ...` or \"thorough\", \"comprehensive\" | Full wiki + optional web | ~8,000+ | \"Compare A vs B across everything\", synthesis, gap analysis |\n\n---\n\n## Quick Mode\n\nUse when the answer is likely in the hot cache or index summary.\n\n1. Read `wiki/hot.md`. If it answers the question, respond immediately.\n2. If not, read `wiki/index.md`. Scan descriptions for the answer.\n3. If found in index summary, respond and do not open any pages.\n4. If not found, say \"Not in quick cache. Run as standard query?\"\n\nDo not open individual wiki pages in quick mode.\n\n---\n\n## Standard Query Workflow\n\n1. **Read** `wiki/hot.md` first. It may already have the answer or directly relevant context.\n2. **Read** `wiki/index.md` to find the most relevant pages (scan for titles and descriptions).\n3. **Read** those pages. Follow wikilinks to depth-2 for key entities. No deeper.\n4. **Synthesize** the answer in chat. Cite sources with wikilinks: `(Source: [[Page Name]])`.\n5. **Offer to file** the answer: \"This analysis seems worth keeping. Should I save it as `wiki/questions/answer-name.md`?\"\n6. If the question reveals a **gap**: say \"I don't have enough on X. Want to find a source?\"\n\n---\n\n## Deep Mode\n\nUse for synthesis questions, comparisons, or \"tell me everything about X.\"\n\n1. Read `wiki/hot.md` and `wiki/index.md`.\n2. Identify all relevant sections (concepts, entities, sources, comparisons).\n3. Read every relevant page. No skipping.\n4. If wiki coverage is thin, offer to supplement with web search.\n5. Synthesize a comprehensive answer with full citations.\n6. Always file the result back as a wiki page. Deep answers are too valuable to lose.\n\n---\n\n## Token Discipline\n\nRead the minimum needed:\n\n| Start with | Cost (approx) | When to stop |\n|------------|---------------|--------------|\n| hot.md | ~500 tokens | If it has the answer |\n| index.md | ~1000 tokens | If you can identify 3-5 relevant pages |\n| 3-5 wiki pages | ~300 tokens each | Usually sufficient |\n| 10+ wiki pages | expensive | Only for synthesis across the entire wiki |\n\nIf hot.md has the answer, respond without reading further.\n\n---\n\n## Index Format Reference\n\nThe master index (`wiki/index.md`) looks like:\n\n```markdown\n## Domains\n- [[Domain Name]]: description (N sources)\n\n## Entities\n- [[Entity Name]]: role (first: [[Source]])\n\n## Concepts\n- [[Concept Name]]: definition (status: developing)\n\n## Sources\n- [[Source Title]]: author, date, type\n\n## Questions\n- [[Question Title]]: answer summary\n```\n\nScan the section headers first to determine which sections to read.\n\n---\n\n## Domain Sub-Index Format\n\nEach domain folder has a `_index.md` for focused lookups:\n\n```markdown\n---\ntype: meta\ntitle: \"Entities Index\"\nupdated: YYYY-MM-DD\n---\n# Entities\n\n## People\n- [[Person Name]]: role, org\n\n## Organizations\n- [[Org Name]]: what they do\n\n## Products\n- [[Product Name]]: category\n```\n\nUse sub-indexes when the question is scoped to one domain. Avoid reading the full master index for narrow queries.\n\n---\n\n## Filing Answers Back\n\nGood answers compound into the wiki. Don't let insights disappear into chat history.\n\nWhen filing an answer:\n\n```yaml\n---\ntype: question\ntitle: \"Short descriptive title\"\nquestion: \"The exact query as asked.\"\nanswer_quality: solid\ncreated: YYYY-MM-DD\nupdated: YYYY-MM-DD\ntags: [question, <domain>]\nrelated:\n  - \"[[Page referenced in answer]]\"\nsources:\n  - \"[[wiki/sources/relevant-source.md]]\"\nstatus: developing\n---\n```\n\nThen write the answer as the page body. Include citations. Link every mentioned concept or entity.\n\nAfter filing, add an entry to `wiki/index.md` under Questions and append to `wiki/log.md`.\n\n---\n\n## Gap Handling\n\nIf the question cannot be answered from the wiki:\n\n1. Say clearly: \"I don't have enough in the wiki to answer this well.\"\n2. Identify the specific gap: \"I have nothing on [subtopic].\"\n3. Suggest: \"Want to find a source on this? I can help you search or process one.\"\n4. Do not fabricate. Do not answer from training data if the question is about the specific domain in this wiki.","tags":["wiki","query","claude","obsidian","agricidaniel","agent-skills","ai-second-brain","autonomous-research","claude-code","claude-code-skill","claude-plugin","karpathy-llm-wiki"],"capabilities":["skill","source-agricidaniel","skill-wiki-query","topic-agent-skills","topic-ai-second-brain","topic-autonomous-research","topic-claude-code","topic-claude-code-skill","topic-claude-plugin","topic-karpathy-llm-wiki","topic-knowledge-graph","topic-knowledge-management","topic-llm","topic-multi-agent","topic-obsidian"],"categories":["claude-obsidian"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/AgriciDaniel/claude-obsidian/wiki-query","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add AgriciDaniel/claude-obsidian","source_repo":"https://github.com/AgriciDaniel/claude-obsidian","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 5150 github stars · SKILL.md body (4,598 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T18:52:44.669Z","embedding":null,"createdAt":"2026-05-18T12:53:57.924Z","updatedAt":"2026-05-18T18:52:44.669Z","lastSeenAt":"2026-05-18T18:52:44.669Z","tsv":"'-2':254 '-5':118,410,414 '000':121,135 '1':102,160,218,323,652 '10':422 '1000':403 '2':170,232,328,667 '3':117,120,180,246,337,409,413,677 '300':417 '4':193,260,344,694 '5':273,356 '500':103,395 '6':290,364 '8':134 'across':140,429 'add':630 'alreadi':57,224 'alway':365 'analysi':144,280 'answer':4,21,26,64,69,150,165,179,227,263,278,360,375,401,437,479,555,558,574,588,607,615,648,664,700 'append':638 'approx':390 'ask':587 'author':473 'avoid':545 'b':139 'back':27,70,369,556 'base':80 'best':90 'bodi':619 'cach':13,156,201 'cannot':646 'categori':532 'chat':265,569 'choos':79 'citat':23,363,621 'cite':266 'clear':654 'compar':136 'comparison':316,336 'complex':84 'compound':74,559 'comprehens':129,359 'concept':333,464,465,625 'context':231 'cost':89,389 'coverag':347 'creat':591 'data':703 'date':107,474 'dd':516,595,600 'deep':35,124,126,310,374 'deeper':259 'default':112 'definit':467 'depth':78,253 'descript':176,245,455,580 'determin':487 'develop':469,611 'direct':229 'disappear':567 'disciplin':382 'domain':452,453,492,498,544,711 'done':58 'enough':302,659 'entir':431 'entiti':257,334,458,459,510,517,627 'entri':632 'everi':339,623 'everyth':141,320 'exact':584 'expens':425 'expla':47 'fabric':697 'fact':110 'factual':97 'file':24,67,276,366,554,572,629 'find':236,307,681 'first':14,221,462,485 'flag':114 'focus':504 'folder':499 'follow':250 'format':443,496 'found':182,196 'full':130,362,548 'gap':143,296,641,671 'good':25,68,557 'handl':642 'header':484 'help':688 'histori':570 'hot':12,155 'hot.md':99,115,394,434 'identifi':329,408,668 'immedi':169 'includ':620 'index':16,116,158,184,442,447,495,511,536,550 'index.md':100,402,502 'individu':209 'insight':566 'keep':283 'key':256 'know':42 'knowledg':73 'let':565 'like':152,450 'link':622 'look':449 'lookup':108,505 'lose':380 'markdown':451,506 'master':446,549 'may':223 'mention':624 'meta':508 'minimum':385 'mm':515,594,599 'mode':36,76,85,146,214,311 'n':456 'name':272,454,460,466,520,525,531 'narrow':552 'need':386 'noth':674 'obsidian':8 'offer':274,350 'one':543,693 'open':190,208 'option':132 'org':522,524 'organ':523 'page':19,30,119,192,211,240,249,271,341,373,412,416,424,604,618 'peopl':518 'person':519 'precis':65 'process':692 'product':529,530 'q':98 'qualiti':589 'queri':3,44,50,51,75,93,125,205,216,553,585 'question':5,83,123,167,293,315,476,477,539,577,582,602,636,645,706 'quick':32,92,94,109,145,200,213 'read':11,62,87,161,173,219,233,247,324,338,383,440,491,546 'refer':444 'referenc':605 'relat':603 'relev':18,230,239,331,340,411 'respond':168,186,438 'result':368 'reveal':294 'role':461,521 'run':202 'save':286 'say':197,297,653 'scan':175,241,481 'scope':541 'search':355,690 'section':332,483,489 'seem':281 'short':579 'simpl':96 'skill' 'skill-wiki-query' 'skip':343 'solid':590 'sourc':267,270,309,335,457,463,470,471,608,683 'source-agricidaniel' 'specif':670,710 'standard':33,111,204,215 'start':387 'status':468,610 'stop':393 'strateg':63 'sub':494,535 'sub-index':493,534 'subtop':676 'suffici':421 'suggest':678 'summari':159,185,480 'supplement':352 'support':31 'synthes':20,261,357 'synthesi':60,142,314,428 'tag':601 'tell':318 'thin':349 'thorough':128 'three':77 'titl':243,472,478,509,578,581 'token':88,381,396,404,418 'topic-agent-skills' 'topic-ai-second-brain' 'topic-autonomous-research' 'topic-claude-code' 'topic-claude-code-skill' 'topic-claude-plugin' 'topic-karpathy-llm-wiki' 'topic-knowledge-graph' 'topic-knowledge-management' 'topic-llm' 'topic-multi-agent' 'topic-obsidian' 'train':702 'trigger':37,86 'type':475,507,576 'updat':512,596 'use':6,147,312,533 'usual':420 'valuabl':378 'vault':10 'vs':138 'want':305,679 'web':133,354 'well':666 'wiki':2,9,29,49,53,55,131,210,346,372,415,423,432,562,651,662,714 'wiki-queri':1,48 'wiki/hot.md':162,220,325 'wiki/index.md':174,234,327,448,634 'wiki/log.md':640 'wiki/questions/answer-name.md':289 'wiki/sources/relevant-source.md':609 'wikilink':251,269 'without':439 'work':61 'workflow':217 'worth':282 'write':613 'x':106,304,322 'yaml':575 'yyyi':514,593,598 'yyyy-mm-dd':513,592,597","prices":[{"id":"7856588e-f652-4cc2-a758-448e7fbc1014","listingId":"2ab3d35a-1be4-4bc8-91b5-8012906b3e16","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"AgriciDaniel","category":"claude-obsidian","install_from":"skills.sh"},"createdAt":"2026-05-18T12:53:57.924Z"}],"sources":[{"listingId":"2ab3d35a-1be4-4bc8-91b5-8012906b3e16","source":"github","sourceId":"AgriciDaniel/claude-obsidian/wiki-query","sourceUrl":"https://github.com/AgriciDaniel/claude-obsidian/tree/main/skills/wiki-query","isPrimary":false,"firstSeenAt":"2026-05-18T12:53:57.924Z","lastSeenAt":"2026-05-18T18:52:44.669Z"}],"details":{"listingId":"2ab3d35a-1be4-4bc8-91b5-8012906b3e16","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"AgriciDaniel","slug":"wiki-query","github":{"repo":"AgriciDaniel/claude-obsidian","stars":5150,"topics":["agent-skills","ai","ai-second-brain","autonomous-research","claude-code","claude-code-skill","claude-plugin","karpathy-llm-wiki","knowledge-graph","knowledge-management","llm","multi-agent","obsidian","obsidian-ai","obsidian-plugin","open-source","pkm","rag","second-brain","wiki"],"license":"mit","html_url":"https://github.com/AgriciDaniel/claude-obsidian","pushed_at":"2026-04-24T10:21:48Z","description":"Claude + Obsidian knowledge companion. Persistent, compounding wiki vault based on Karpathy's LLM Wiki pattern. /wiki /save /autoresearch","skill_md_sha":"7bb58f0accf917a410d212ba2247ba85277b33dd","skill_md_path":"skills/wiki-query/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/AgriciDaniel/claude-obsidian/tree/main/skills/wiki-query"},"layout":"multi","source":"github","category":"claude-obsidian","frontmatter":{"name":"wiki-query","description":"Answer questions using the Obsidian wiki vault. Reads hot cache first, then index, then relevant pages. Synthesizes answers with citations. Files good answers back as wiki pages. Supports quick, standard, and deep modes. Triggers on: what do you know about, query:, what is, explain, summarize, find in wiki, search the wiki, based on the wiki, wiki query quick, wiki query deep."},"skills_sh_url":"https://skills.sh/AgriciDaniel/claude-obsidian/wiki-query"},"updatedAt":"2026-05-18T18:52:44.669Z"}}