Communitygithub.com

维基

持久化的 Markdown 知识库,可在会话间积累,受 Karpathy 的 LLM Wiki 概念启发。

维基 是什么?

这个“维基”技能是一个为项目构建持久化 Markdown 知识库的强大工具。它使 AI 智能体(如 Claude)能够跨会话工作,系统性地捕获和检索知识,就像人类的项目维基一样。受 Karpathy 的 LLM Wiki 概念启发,它使用简单的基于关键词和标签的搜索(而非向量嵌入),使其高效且对开发者友好。该技能在工作流程中支持读取、查询、写入、删除和审查维基页面的操作,还包含健康检查(lint)和自动日志记录。其设计有助于克服大型语言模型的上下文限制,允许智能体在长时间跨度内“记住”架构决策、调试记录和重要模式,使其成为高级软件开发工作流程(如 Cursor 或 Codex)中的关键组成部分。

兼容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Yeachan-Heo/oh-my-claudecode/tree/main/skills/wiki

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

维基 是做什么的?

持久、自维护的 Markdown 知识库,用于管理项目和会话知识。受 Karpathy 的 LLM Wiki 概念启发。

操作

摄取

将知识处理为维基页面。单次摄取可以涉及多个页面。

wiki_ingest({ title: "认证架构", content: "...", tags: ["auth", "architecture"], category: "architecture" })

查询

通过关键词和标签在所有维基页面中进行搜索。返回匹配的页面及摘要——由您(大型语言模型)根据结果中的引用综合答案。

wiki_query({ query: "authentication", tags: ["auth"], category: "architecture" })

检查

对维基执行健康检查。检测孤立页面、过时内容、损坏的交叉引用、过大的页面以及结构上的矛盾。

wiki_lint()

快速添加

快速添加单个页面(比摄取更简单)。

wiki_add({ title: "页面标题", content: "...", tags: ["tag1"], category: "decision" })

列出 / 读取 / 删除

wiki_list()           # 显示所有页面(读取 index.md)
wiki_read({ page: "auth-architecture" })  # 读取特定页面
wiki_delete({ page: "outdated-page" })    # 删除一个页面

日志

通过读取 .omc/wiki/log.md 查看维基操作历史。

分类

页面按类别组织:architecture、decision、pattern、debugging、environment、session-log

存储

  • 页面:.omc/wiki/*.md(带 YAML 前置元数据的 Markdown)
  • 索引:.omc/wiki/index.md(自动维护的目录)
  • 日志:.omc/wiki/log.md(仅追加的操作记录)

交叉引用

使用 [[page-name]] 维基链接语法在页面之间创建交叉引用。

自动捕获

会话结束时,重要的发现会被自动捕获为会话日志页面。通过 .omc-config.json 中的 wiki.autoCapture 进行配置(默认:启用)。

硬性约束

  • 无向量嵌入——查询仅使用关键词 + 标签匹配
  • 维基页面默认会被 Git 忽略(.omc/wiki/ 是项目本地的)

模型路由

  • haiku — 快速查找、轻量级检查、狭窄的文档工作
  • sonnet — 标准实现、调试和代码审查
  • opus — 架构、深度分析、共识规划和高风险审查
  • fable — Claude Fable 5(高于 Opus);在任务调用时显式传递它,或通过 agents.<name>.model 为每个代理固定使用它
  • 通过 /model 选择的会话模型仅适用于主循环。被委派的代理运行在其固定的层级上,除非任务调用显式传递了 model 参数或通过 agents.<name>.model 覆盖了代理。要在委派的工作上使用 Fable,请使用这两种方式之一;仅在 /model 中选择 Fable 不会改变委派行为。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

agent-doc-discipline

Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and carrying a why, steps before reference, one meaning in one home, no restating what the environment already says. Mandatory at drydock seed generation and the launch C5 sediment pass; opt-in for any other agent-facing doc edit. The companion of minimal-code-discipline: that one disciplines code, this one disciplines papers.

ai-slop-cleaner

Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode

ask

Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, or Cursor via `omc ask`, with artifact capture and no raw CLI assembly

ask-navigator

Shipyard

autopilot

Full autonomous execution from idea to working code

autoresearch

Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behavior

cancel

Cancel any active OMC mode (autopilot, ralph, ultragoal, swarm, ultrapilot, pipeline, team) and clean up retired legacy state

configure-notifications

Configure notification integrations (Telegram, Discord, Slack) via natural language

debug

Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction

deepinit

Deep codebase initialization with hierarchical AGENTS.md documentation

deep-interview

Socratic deep interview with mathematical ambiguity gating before explicit execution approval

drydock

Lay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards) across 5 surfaces (CLAUDE.md, skills, design-system, mcp/cli, shared context) so that every human and agent inherits the same design language and anyone can ship. Run once per repo; re-run with --check to audit drift.

execute

Carry an approved task through to working, verified code

external-context

Invoke parallel document-specialist agents for external web searches and documentation lookup

graph

Deterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash recovery

harbor

Harbor intake for external work — the captain only handles unresolved decisions. Sweeps incoming issues and PRs, verifies every claim before disposition, reuses every decision already made, and hands the maintainer a docket whose pending items each carry one question with options, recommendation, impact and evidence. Agent-autonomous for facts and for actions covered by standing authorization; signed for every new judgment. Never merges.

hud

Configure HUD display options (layout, presets, display elements)

launch

Shipyard

loft

Loft the shape before cutting steel — answer a design question that prose cannot settle by building a throwaway artifact: a pure logic module in a clickable shell, or structurally different UI variants behind one route. The captain reacts to the artifact; the answer folds into the decision; the artifact never docks. Use when a design question stalls in words, when a navigator map carries a loft ticket, or when a spec discussion reaches

minimal-code-discipline

YAGNI-ladder coding discipline for writing changes — existence-first, reuse before writing, dependency ladder, shortest correct diff, with non-negotiables that must never be minimized away

相关技能