mermaid-diagrams

Sematkan diagram Mermaid dalam halaman wiki yang dihasilkan. Gunakan setiap kali mendokumentasikan alur runtime atau permintaan, urutan panggilan, state machine atau siklus hidup, model data…

npx skills add https://github.com/langchain-ai/openwiki --skill mermaid-diagrams

Mermaid Diagrams In Generated Wiki Pages

Diagrams are part of high-quality wiki generation, not decoration. Where a flow, lifecycle, or data model is easier to grasp visually, embed a Mermaid diagram in a fenced ```mermaid block on the most relevant page.

Choosing a diagram type

  • sequenceDiagram for runtime and request flows across components (auth flows, request lifecycles, agent tool loops).
  • stateDiagram-v2 for lifecycles and state machines (job states, connection states, run phases).
  • erDiagram for the data model: entities and their relationships.
  • flowchart TD for branching control flow and decision logic.

Discipline

  • Ground every diagram in inspected source. Do not invent participants, states, entities, or relationships the code does not support.
  • Cover the high-value cases: add a diagram wherever a page documents a request or runtime flow, a call sequence, a lifecycle or state machine, or a data model. A repository wiki usually has several such diagrams, not one overall. Skip pages that are navigation, reference tables, or pure configuration.
  • Still prefer a few strong diagrams over decorating every page: one accurate diagram on the page that needs it beats a diagram forced onto every page.
  • Give each diagram a one-line caption directly below it stating what it shows.
  • OpenWiki validates every mermaid fence after your run and converts fences that fail to parse into plain text fences. A degraded diagram is a quality failure; follow the syntax rules below so it does not happen.

Syntax safety

These rules prevent the most common render breakages. When in doubt, rephrase the label.

  • Never place semicolons or pipes inside node, message, or edge labels.
  • Never place unescaped angle brackets in labels; write "returns Promise of User" instead of "returns Promise".
  • In flowchart, wrap any label containing parentheses, brackets, or other punctuation in double quotes: A["calls foo(bar)"].
  • In flowchart, never use the bare word end as a node id, and never start a node id with o or x followed by a dash (both are edge-marker syntax); rename the node.
  • In sequenceDiagram, participant names with spaces or punctuation need an alias: participant AS as Auth Service.
  • Never use a Mermaid reserved word as a participant name, alias, or node id: note, end, loop, alt, opt, par, and, else, activate, deactivate, class, state, click, link. For example a notification participant must be Notifier, not Note (which collides with the note keyword).
  • In erDiagram, entity and attribute names must be single identifier-like tokens; put human phrasing in the relationship label.
  • Keep labels short. Move explanation into the surrounding prose or the caption, not the diagram.

Update runs

  • A wrong diagram is a stale claim, not existing structure to preserve. If a source change makes a diagram inaccurate, update the diagram in the same edit as the surrounding prose.
  • Do not rewrite a diagram that is still accurate. Regenerating unchanged diagrams creates diff noise.
  • If a page contains a text fence preceded by an HTML comment starting with "openwiki: mermaid parse failed", that is a diagram a previous run degraded. Fix the syntax using the parser error in the comment, restore the ```mermaid fence, and delete the comment.

Lebih banyak skill dari langchain-ai

deepagents-thread-inspector
langchain-ai
Periksa dan jelaskan percakapan di penyimpanan sesi SQLite Deep Agents Code lokal. Gunakan sebagai cadangan saat alat pelacakan LangSmith tidak tersedia, untuk…
deepagents-python-quickstart
langchain-ai
Buat kerangka minimal Deep Agent lokal dalam Python dengan mengikuti panduan memulai resmi, menggunakan pencarian web bawaan penyedia alih-alih Tavily. Gunakan saat pengguna ingin…
deepagents-typescript-quickstart
langchain-ai
Buat kerangka Deep Agent lokal minimal dalam TypeScript dengan mengikuti quickstart resmi, menggunakan pencarian web native penyedia alih-alih Tavily. Gunakan saat pengguna…
eval-engineering
langchain-ai
Periksa repositori agen dan trace opsional dari pengguna secara iteratif, wawancarai pengguna, lalu buat, jalankan, dan audit eval Harbor satu per satu. Gunakan untuk…
LangChain RAG Pipeline
langchain-ai
GUNAKAN KETERAMPILAN INI saat membangun sistem retrieval-augmented generation (RAG) apa pun. Mencakup pemuat dokumen, RecursiveCharacterTextSplitter, embeddings (OpenAI),…
LangChain Structured Output & HITL
langchain-ai
langchain-structured-output-&-hitl — sebuah skill yang dapat diinstal untuk agen AI, diterbitkan oleh langchain-ai/langchain-skills.
LangSmith Datasets
langchain-ai
PANGGIL KETERAMPILAN INI saat membuat dataset evaluasi dari jejak ATAU mengunggah dataset ke LangSmith ATAU menanyakan dataset. Mencakup tipe dataset (final_response,…
langsmith-evaluator
langchain-ai
GUNAKAN KETERAMPILAN INI saat membangun pipeline evaluasi untuk LangSmith. Mencakup tiga komponen inti: (1) Membuat Evaluator - LLM-as-Judge, kode kustom; (2)…