用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/nvk/llm-wiki --skill wiki-query命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Manage LLM-compiled wikis: initialize, ingest/import, compile/query, research/audit, collect catalogs, track inventory/datasets/Ideas, review Idea/Project portfolios, manage archives/sessions/feedback, and generate outputs. Activates for /wiki commands; wiki or knowledge-base work; ingest, collect, catalog, compile, query, audit, librarian, inventory, idea, portfolio, business ideas, projects, datasets, archives, sessions, feedback, checkpoints, private adapters, adapter routing, explicit wiki skill-factory requests, personal specialist skills, expert review, specialist selection, provenance, external resource actions, or questions in a directory with .wiki/ or a configured hub.
Manage LLM-compiled wikis in OpenCode: ingest/import, shape/promote Ideas, review portfolios, track inventory/datasets, archive, compile/query/lint/audit, research/plan, manage sessions, private adapters, personal specialists, and outputs. Activates when the user mentions wiki workflows, knowledge-base management, ingestion, collection ingestion, import wiki, collect, catalog, curate, find all, idea, turn idea into project, portfolio, business ideas, projects, inventory, source queue, candidate list, watch list, backlog, dataset, large data, data registry, dataset manifest, compilation, querying, linting, audit, research, librarian, scan quality, article quality, content review, output drift, provenance, archive wiki, archive topic, restore wiki, private adapter, adapter registry, skill-factory, checkpoints, personal specialist, specialist skill, specialist reviewer, expert lens, adapter route, adapter doctor, adapter run, edit an external resource, session capture, capture context, rehydrate, resume from ses
Manage LLM-compiled wikis in Codex: ingest/import, shape/promote Ideas, review portfolios, track inventory/datasets, archive, compile/query/lint/audit, research/plan, manage sessions, private adapters, personal specialists, and outputs. Activates when the user mentions wiki workflows, knowledge-base management, ingestion, collection ingestion, import wiki, collect, catalog, curate, find all, idea, turn idea into project, portfolio, business ideas, projects, inventory, source queue, candidate list, watch list, backlog, dataset, large data, data registry, dataset manifest, compilation, querying, linting, audit, research, librarian, scan quality, article quality, content review, output drift, provenance, archive wiki, archive topic, restore wiki, private adapter, adapter registry, skill-factory, checkpoints, personal specialist, specialist skill, specialist reviewer, expert lens, adapter route, adapter doctor, adapter run, edit an external resource, session capture, capture context, rehydrate, resume from sessio
基于 SOC 职业分类
正在显示 SKILL.md
| name | wiki-query |
| description | Fast, read-only, index-first llm-wiki queries for OpenCode and compatible instruction-file harnesses. |
Use this protocol for fast, read-only questions and inventory lookups. It is the canonical query profile shared by Claude, Codex, Pi, local models, and the portable fallback.
node_modules,
or every sibling topic.--local, or the current project contains .wiki/,
use <cwd>/.wiki and read .wiki/_index.md first.~/.config/llm-wiki/config.json. Expand only a leading ~
in hub_path. If unavailable, try resolved_path, then ~/wiki.<hub>/_index.md and <hub>/wikis.json. Choose exactly one
active topic from its title, aliases, summary, or an explicit --wiki NAME.
Resolve registry paths relative to the hub; if stale, try
<hub>/topics/NAME._index.md, then only the relevant branch
index: wiki/_index.md, raw/_index.md, inventory/_index.md,
datasets/_index.md, or output/_index.md.If topic choice is genuinely ambiguous, list at most three index-derived candidates and ask one short question instead of scanning multiple topics.
wiki/ articles are the default factual layer.raw/ when the user requests primary evidence or compiled coverage is
insufficient.inventory/ is tracking state, not factual evidence, except for questions
about candidates, status, priority, or next actions.