Communitygithub.com

Wiki

持久的、自我維護的 Markdown 知識庫,可跨工作階段累積知識(Karpathy 模型)。

Wiki 是什麼?

此技能實作了一個靈感來自 Andrej Karpathy「LLM Wiki」概念的持久化 Markdown 知識庫。它專門為 AI 代理程式(如 Claude Code)設計,允許 LLM 在專案目錄中直接建立、查詢和維護結構化的知識頁面,而無需依賴向量嵌入或外部資料庫。主要功能包括透過 `wiki_ingest` 和 `wiki_add` 新增頁面、利用基於關鍵字和標籤的 `wiki_query` 進行精確檢索、使用 `wiki_lint` 進行健康檢查,以及透過 `wiki_list`、`wiki_read` 和 `wiki_delete` 進行標準文件管理。頁面以帶有 YAML 前置中繼資料的 Markdown 格式儲存在 `.omc/wiki/` 目錄中,並支援使用 `[[page-name]]` 語法的交叉參考。此外,還會在工作階段結束時自動將重要發現記錄為「session-log」頁面。此工具對於透過保持跨會話的知識來維護專案架構、決策記錄和偵錯歷史記錄至關重要,確保 LLM 從一個工作階段到下一個工作階段擁有連貫且不斷增長的上下文。

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

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

Wiki 是做什麼的?

持久、自我維護的專案與工作階段知識 Markdown 知識庫。靈感來自 Karpathy 的 LLM Wiki 概念。

操作

匯入(Ingest)

將知識處理到 Wiki 頁面中。單次匯入可以影響多個頁面。

wiki_ingest({ title: "Auth Architecture", content: "...", tags: ["auth", "architecture"], category: "architecture" })

查詢(Query)

依關鍵字和標籤搜尋所有 Wiki 頁面。回傳相符的頁面及片段 — 您(LLM)需根據結果中的引用來綜合回答。

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

檢查(Lint)

對 Wiki 執行健康檢查。偵測孤立頁面、過時內容、斷裂的交叉參考、過大的頁面以及結構矛盾。

wiki_lint()

快速新增(Quick Add)

快速新增一個頁面(比匯入更簡單)。

wiki_add({ title: "Page Title", content: "...", tags: ["tag1"], category: "decision" })

列出 / 讀取 / 刪除

wiki_list()           # 顯示所有頁面(讀取 index.md)
wiki_read({ page: "auth-architecture" })  # 讀取特定頁面
wiki_delete({ page: "outdated-page" })    # 刪除一個頁面

日誌(Log)

透過讀取 .omc/wiki/log.md 來檢視 Wiki 操作歷史。

分類

頁面按類別組織:architecture、decision、pattern、debugging、environment、session-log

儲存

  • 頁面:.omc/wiki/*.md(帶有 YAML 前置中繼資料的 Markdown)
  • 索引:.omc/wiki/index.md(自動維護的目錄)
  • 日誌:.omc/wiki/log.md(僅追加的操作記錄)

交叉參考

使用 [[page-name]] Wiki 連結語法在頁面之間建立交叉參考。

自動擷取

在工作階段結束時,重要的發現會自動擷取為 session-log 頁面。透過 .omc-config.json 中的 wiki.autoCapture 進行設定(預設:啟用)。

嚴格限制

  • 不使用向量嵌入 — 查詢僅使用關鍵字 + 標籤匹配
  • Wiki 頁面預設會被 git 忽略(.omc/wiki/ 為專案本地端)

模型路由

  • haiku — 快速查詢、輕量級檢查、狹窄的文件工作
  • sonnet — 標準實作、偵錯與審查
  • opus — 架構、深度分析、共識規劃與高風險審查
  • fable — Claude Fable 5(高於 Opus);在 Task 呼叫中明確傳遞,或透過 agents.<name>.model 為每個代理程式固定
  • 使用 /model 選擇的工作階段模型僅適用於主迴圈。除非 Task 呼叫明確傳遞 model 參數,或透過 agents.<name>.model 覆寫代理程式,否則委派的代理程式會以其固定的階層運作。若要在委派工作上使用 Fable,請使用上述兩種方式之一;僅在 /model 中選擇 Fable 並不會改變委派行為。

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

相關技能