Excalidraw Canvas Toolkit
lingzhi227/agent-research-skills
Draws and refines Excalidraw diagrams on a live canvas through MCP tools or a REST API, with screenshots, file import and export, snapshots and Mermaid conversion.
Guide for reading a codebase and building a high-quality, persistent architecture knowledge graph via the Excalidraw Architect MCP kg tools.
Install Architecture Knowledge Graph
$ npx skills add BV-Venky/excalidraw-architect-mcp --skill architecture-knowledge-graph -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install BV-Venky/excalidraw-architect-mcp architecture-knowledge-graph --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/BV-Venky/excalidraw-architect-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.skills/architecture-knowledge-graph .claude/skills/architecture-knowledge-graph && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "architecture-knowledge-graph" agent skill from https://github.com/BV-Venky/excalidraw-architect-mcp/tree/main/.skills/architecture-knowledge-graph into .claude/skills/architecture-knowledge-graph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-knowledge-graph", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/BV-Venky/excalidraw-architect-mcp/tree/main/.skills/architecture-knowledge-graphType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add BV-Venky/excalidraw-architect-mcp --skill architecture-knowledge-graph -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install BV-Venky/excalidraw-architect-mcp architecture-knowledge-graph --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BV-Venky/excalidraw-architect-mcp.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.skills/architecture-knowledge-graph .agents/skills/architecture-knowledge-graph && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "architecture-knowledge-graph" agent skill from https://github.com/BV-Venky/excalidraw-architect-mcp/tree/main/.skills/architecture-knowledge-graph into .agents/skills/architecture-knowledge-graph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-knowledge-graph", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add BV-Venky/excalidraw-architect-mcp --skill architecture-knowledge-graph -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install BV-Venky/excalidraw-architect-mcp architecture-knowledge-graph --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BV-Venky/excalidraw-architect-mcp.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.skills/architecture-knowledge-graph .cursor/skills/architecture-knowledge-graph && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "architecture-knowledge-graph" agent skill from https://github.com/BV-Venky/excalidraw-architect-mcp/tree/main/.skills/architecture-knowledge-graph into .cursor/skills/architecture-knowledge-graph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-knowledge-graph", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/BV-Venky/excalidraw-architect-mcp.git --path .skills/architecture-knowledge-graph--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add BV-Venky/excalidraw-architect-mcp --skill architecture-knowledge-graph -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install BV-Venky/excalidraw-architect-mcp architecture-knowledge-graph --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BV-Venky/excalidraw-architect-mcp.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.skills/architecture-knowledge-graph .gemini/skills/architecture-knowledge-graph && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "architecture-knowledge-graph" agent skill from https://github.com/BV-Venky/excalidraw-architect-mcp/tree/main/.skills/architecture-knowledge-graph into .gemini/skills/architecture-knowledge-graph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-knowledge-graph", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install BV-Venky/excalidraw-architect-mcp architecture-knowledge-graphInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add BV-Venky/excalidraw-architect-mcp --skill architecture-knowledge-graph -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/BV-Venky/excalidraw-architect-mcp.git skills-src && mkdir -p .github/skills && cp -r skills-src/.skills/architecture-knowledge-graph .github/skills/architecture-knowledge-graph && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "architecture-knowledge-graph" agent skill from https://github.com/BV-Venky/excalidraw-architect-mcp/tree/main/.skills/architecture-knowledge-graph into .github/skills/architecture-knowledge-graph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-knowledge-graph", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add BV-Venky/excalidraw-architect-mcp --skill architecture-knowledge-graph -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install BV-Venky/excalidraw-architect-mcp architecture-knowledge-graph --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BV-Venky/excalidraw-architect-mcp.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.skills/architecture-knowledge-graph .opencode/skills/architecture-knowledge-graph && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "architecture-knowledge-graph" agent skill from https://github.com/BV-Venky/excalidraw-architect-mcp/tree/main/.skills/architecture-knowledge-graph into .opencode/skills/architecture-knowledge-graph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-knowledge-graph", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
architecture-knowledge-graph- GitHub stars
- 158
- Token cost
- ~1.1k tokens
- SKILL.md length
- 557 words
- Files
- 1
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- MIT
At a glance
Guide for reading a codebase and building a high-quality, persistent architecture knowledge graph via the Excalidraw Architect MCP kg tools.
- Works in 5 steps: kg_init once (or kg_import to bootstrap… → Discovery pass — identify every service… → Linking pass — only after all services… → …
- Updating the knowledge graph (.claude/architecture.md)
- SKILL.md covers Core Principle, Workflow (do the passes in…, How to find the edges (where… and Conventions (keep the graph…, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Architecture Knowledge Graph is an agent skill from BV-Venky/excalidraw-architect-mcp. Guide for reading a codebase and building a high-quality, persistent architecture knowledge graph via the Excalidraw Architect MCP kg tools. Use when creating or updating the knowledge graph (.claude/architecture.md), mapping services and their dependencies, or analyzing one or more repos to capture how services communicate.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Knowledge Management, covering Knowledge graphs, Diagrams and MCP servers. It works with Model Context Protocol, Excalidraw and Apache Kafka. The repository describes itself as: Turn your architecture into a living, queryable knowledge graph - and render it as beautiful auto-laid-out Excalidraw diagrams. An MCP server for Cursor, Claude Code & Windsurf… The licence is MIT.
When your agent uses it
- Updating the knowledge graph (.claude/architecture.md)
- Mapping services and their dependencies
- More repos to capture how services communicate
Example prompts
- “/architecture-knowledge-graph”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- kg_init once (or kg_import to bootstrap from an existing .excalidraw).
- Discovery pass — identify every service first. Add each with
- Linking pass — only after all services exist, add edges with kg_link.
- kg_lint — catch dangling references, cycles, and single points of
- kg_render (whole graph) or **kg_render_view / kg_render_around /
What it can do on your machine
Read from SKILL.md and the folder at commit 6280bb3. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Architecture Knowledge Graph loads about 1.1k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 557 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from BV-Venky/excalidraw-architect-mcp at commit 6280bb3, republished under its MIT licence (© BV-Venky). 557 words, ~1,148 tokens.
Download SKILL.mdSave it as
.claude/skills/architecture-knowledge-graph/SKILL.md (or your agent's skills folder).- name
- architecture-knowledge-graph
- description
- Guide for reading a codebase and building a high-quality, persistent architecture knowledge graph via the Excalidraw Architect MCP kg_* tools. Use when creating or updating the knowledge graph (.claude/architecture.md), mapping services and their dependencies, or analyzing one or more repos to capture how services communicate.
Architecture Knowledge Graph Guide
This skill teaches you how to turn a codebase into a clean, durable knowledge
graph using the kg_* MCP tools. The graph (default .claude/architecture.md)
is the single source of truth; diagrams are rendered views of it.
Graph quality depends almost entirely on how well you read the code. The MCP preserves, validates, and renders whatever you put in — it does not analyze the codebase. That analysis is your job.
Core Principle
Model services/components and how they communicate, not classes, functions,
or every import. A "service" is a deployable unit / bounded context — one
repo, one container, one logical responsibility.
Workflow (do the passes in order — don't interleave)
kg_initonce (orkg_importto bootstrap from an existing.excalidraw).- Discovery pass — identify every service first. Add each with
kg_add_service, settingcomponent_type,domain, andownerwhile the info is in front of you (Dockerfiles,CODEOWNERS, READMEs, manifests). - Linking pass — only after all services exist, add edges with
kg_link. Linking before a target exists fails; that's why discovery comes first. kg_lint— catch dangling references, cycles, and single points of failure. Fix them before rendering.kg_render(whole graph) orkg_render_view/kg_render_around/kg_render_domainfor focused diagrams.
How to find the edges (where services talk)
Look for these signals and translate each into a labelled kg_link:
| Signal in code | Link | Label / style |
|---|---|---|
| HTTP client, base URL, OpenAPI/Swagger spec | sync call | "REST /orders", style: solid |
| gRPC stub / proto service | sync call | "gRPC GetOrder", style: solid |
| Kafka/SQS/RabbitMQ producer | async event | "Kafka order.created", style: dashed |
| Kafka/SQS/RabbitMQ consumer | async event (incoming) | label with the same topic |
| DB connection string / ORM config | datastore | "reads/writes", style: solid |
Service-discovery / env var (PAYMENTS_URL) | dependency | name the protocol |
Cross-repo detection (multiple repos)
To connect services across repos, match a producer in repo A to a consumer in repo B using the shared join key:
- Async: topic / queue name (A publishes
order.created, B subscribesorder.created→kg_link order-svc -> fulfilment-svc "Kafka order.created" style=dashed). - Sync: the called service's route/host (A calls
https://payments/charge→ link A → payments).
Do a producer/consumer inventory across all repos before linking, so you don't miss an edge whose two ends live in different codebases.
Show full SKILL.md (202 more words)Show less
Conventions (keep the graph consistent across sessions)
- Stable kebab-case ids, reused everywhere:
order-service— neverOrderServiceone session andordersthe next. Id drift silently corrupts a cumulative graph. - Every edge is labelled with the mechanism. No bare arrows between services.
- Style encodes transport:
solid= sync (REST/gRPC/DB),dashed= async (events/queues). Consistency makes diagrams instantly readable. - Set
domainto group services (team / bounded context / tier) so you can render one domain at a time.
Granularity
The full graph may be large, but any single rendered view should stay readable
(~6–15 services). If a domain has 20 services, render it per sub-domain with
kg_render_domain / kg_render_view rather than one giant picture. Resist
decomposing a service into its internal classes — that's a different diagram.
Known limitation: parallel edges
A dependency is keyed on (from_id, to_id), so a second kg_link between the
same pair replaces the first. If A talks to B two ways (REST and Kafka),
combine them into one label — "REST /orders · Kafka order.created" — or link
the primary transport. Don't issue two kg_link calls expecting two arrows.
Verify
Unlike diagrams, the graph is deterministically checkable. After building, run
whats_connected_to <service> and kg_lint to sanity-check the topology
matches your understanding of the system before sharing rendered views.
© BV-Venky, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .skills/architecture-knowledge-graph of BV-Venky/excalidraw-architect-mcp.
Open the folder on GitHubat commit 6280bb3
Compare with similar skills
Architecture Knowledge Graph next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Architecture Knowledge Graph this skillBV-Venky/excalidraw-architect-mcp | 158 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Excalidraw Canvas Toolkitlingzhi227/agent-research-skills | 386 | — | ~3.8k | Automated safety check: Pass | None | |
| MemPalace MemoryMemPalace/mempalace | 59k | — | ~2.7k | Automated safety check: Pass | MIT | |
| Docsmint Document ManagerHiAi-gg/docsmint | 118 | — | ~584 | Automated safety check: Pass | Apache-2.0 | |
| Memoryyonatangross/orchestkit | 290 | — | ~1.8k | Automated safety check: Notes | MIT | |
| Sage Wikixoai/sage-wiki | 622 | — | ~2.4k | Automated safety check: Pass | MIT |
Similar skills
MemPalace Memory
MemPalace/mempalace
Gives an agent a local memory palace over MCP: verbatim conversation memory, semantic search and a temporal knowledge graph, with a per-session recall protocol.
Docsmint Document Manager
HiAi-gg/docsmint
Manage and research DocsMint documents through its scoped MCP tools, including categories, folders, hybrid search, GraphRAG, rerank, and index refresh.
Memory
yonatangross/orchestkit
Read-side memory operations on the knowledge graph: search past decisions and patterns, load session context, view decision timelines, render Mermaid graph visualizations.
Sage Wiki
xoai/sage-wiki
Reference skill for sage-wiki — local-first knowledge graph with MCP server, REST API, compiled wiki, and Obsidian-compatible output.
Ogham Maintain
ogham-mcp/ogham-mcp
Admin and maintenance workflows for Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.
More from BV-Venky/excalidraw-architect-mcp
Excalidraw Architect
BV-Venky/excalidraw-architect-mcp
Choose and compose the right Excalidraw diagram - architecture, flowchart, sequence, state, ER, swimlane, process, timeline, quadrant, pyramid, venn, loop, gantt, bar, line, scatter, and more -…
Excalidraw Diagram Design
BV-Venky/excalidraw-architect-mcp
Guide for structuring graph input (nodes and edges) for the Excalidraw Architect MCP tool to produce clean, readable diagrams.
Related
Categories
Questions about Architecture Knowledge Graph
What does Architecture Knowledge Graph do?
Guide for reading a codebase and building a high-quality, persistent architecture knowledge graph via the Excalidraw Architect MCP kg tools. Architecture Knowledge Graph is an agent skill from BV-Venky/excalidraw-architect-mcp. Guide for reading a codebase and building a high-quality, persistent architecture knowledge graph via the Excalidraw Architect MCP kg tools.
When should I use Architecture Knowledge Graph?
Architecture Knowledge Graph fits situations like: updating the knowledge graph (.claude/architecture.md); mapping services and their dependencies; more repos to capture how services communicate.
How do I install Architecture Knowledge Graph in Claude Code?
Run `npx skills add BV-Venky/excalidraw-architect-mcp --skill architecture-knowledge-graph -a claude-code`. Or copy the skill folder (.skills/architecture-knowledge-graph in BV-Venky/excalidraw-architect-mcp) into .claude/skills/architecture-knowledge-graph in your project. Claude Code loads it when a task matches its description.
How do I install Architecture Knowledge Graph in Codex?
Run `npx skills add BV-Venky/excalidraw-architect-mcp --skill architecture-knowledge-graph -a codex`. Or copy the skill folder (.skills/architecture-knowledge-graph in BV-Venky/excalidraw-architect-mcp) into .agents/skills/architecture-knowledge-graph in your project. Codex loads it when a task matches its description.
Can I use Architecture Knowledge Graph in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add BV-Venky/excalidraw-architect-mcp --skill architecture-knowledge-graph -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/architecture-knowledge-graph, .gemini/skills/architecture-knowledge-graph, .github/skills/architecture-knowledge-graph and .opencode/skills/architecture-knowledge-graph in your project.
What does Architecture Knowledge Graph need to run?
SKILL.md names no scripts, command-line tools or credentials: Architecture Knowledge Graph is instructions for the agent only.
Does Architecture Knowledge Graph access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Architecture Knowledge Graph safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Architecture Knowledge Graph use?
Architecture Knowledge Graph is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Architecture Knowledge Graph use?
About 1.1k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Architecture Knowledge Graph?
Skills that share tags, products or a category with Architecture Knowledge Graph: Excalidraw Canvas Toolkit (lingzhi227/agent-research-skills, 386 stars), MemPalace Memory (MemPalace/mempalace, 59k stars), Docsmint Document Manager (HiAi-gg/docsmint, 118 stars) and Memory (yonatangross/orchestkit, 290 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Architecture Knowledge Graph?
BV-Venky (a GitHub user) maintains it in BV-Venky/excalidraw-architect-mcp, which has 158 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on August 25, 2026.
Source: BV-Venky/excalidraw-architect-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.