map
Generate a visual architecture overview of the codebase with Mermaid diagrams. Produces ARCHITECTURE.md at repo root. Use when the user says "map", "architecture", "overview", or wants to understand the codebase structure.
What this skill does
# Map Codebase
Generate a visual architecture overview and write `ARCHITECTURE.md` at the repo root.
## Process
Work with the `code_context` MCP tool to explore the codebase structure, key types, and call graphs. Use Mermaid syntax for diagrams that render on GitHub.
### 1. Check index status
```json
{"op": "get status"}
```
If TS or LSP indexing < 90%, wait and re-check — map quality depends on a fully indexed codebase.
### 2. Gather structural data
**File inventory** + scale (use `get status` counts):
```json
{"op": "grep code", "pattern": ".", "max_results": 1}
```
**Key symbols** — major types, traits, entry points:
```json
{"op": "search symbol", "kind": "struct", "query": "", "max_results": 50}
{"op": "search symbol", "kind": "function", "query": "main", "max_results": 10}
{"op": "search symbol", "kind": "trait", "query": "", "max_results": 30}
{"op": "search symbol", "kind": "class", "query": "", "max_results": 30}
{"op": "search symbol", "kind": "interface", "query": "", "max_results": 30}
```
**Module structure**:
```json
{"op": "list symbols", "file_path": "<entry-point>"}
```
**Call graph** from entry points:
```json
{"op": "get callgraph", "symbol": "<entry-point>", "direction": "outbound", "max_depth": 2}
```
**Dependencies**:
```json
{"op": "get blastradius", "file_path": "<key-file>", "max_hops": 2}
```
### 3. Read project config
`Cargo.toml` / `package.json` / `go.mod` / `pyproject.toml`, and entry points (`main.rs`, `lib.rs`, `index.ts`, `main.go`, etc.).
### 4. Write `ARCHITECTURE.md`
Sections (each must include at least one Mermaid diagram where applicable):
**Header**:
```markdown
# Architecture
> Auto-generated by SwissArmyHammer `/map` — [timestamp]
## Overview
[2-3 sentences: what this is, what it does, language/framework]
```
**Module/Package Dependencies** (`graph TD`) — group by layer when there are clear layers (CLI → core → data):
````markdown
```mermaid
graph TD
A[module-a] --> B[module-b]
A --> C[module-c]
B --> D[shared-lib]
C --> D
```
````
**Key Types and Relationships** (`classDiagram`) — focus on 10–20 most important types:
````markdown
```mermaid
classDiagram
class Server {
+start()
+handle_request()
}
class Handler {
<<trait>>
+execute()
}
Server --> Handler
```
````
**Key Flows** (`sequenceDiagram`) — 1–3 critical paths (request handling, data pipeline, build):
````markdown
```mermaid
sequenceDiagram
participant Client
participant Server
participant Handler
participant DB
Client->>Server: request
Server->>Handler: dispatch
Handler->>DB: query
DB-->>Handler: result
Handler-->>Server: response
Server-->>Client: reply
```
````
**Codebase Composition** (`pie`):
````markdown
```mermaid
pie title Codebase by Module
"Core" : 45
"CLI" : 20
"Tests" : 25
"Config" : 10
```
````
**Directory Structure** — annotated tree of top-level dirs.
**Symbol Index** — table of major public types/functions grouped by module:
```markdown
| Module | Symbol | Kind | Description |
|--------|--------|------|-------------|
| server | Server | struct | Main server instance |
| server | start | fn | Entry point |
| handler | Handler | trait | Request handler interface |
```
### 5. Summary
```
Wrote ARCHITECTURE.md
- [N] modules/packages mapped
- [N] key types documented
- [N] flows diagrammed
- [N] Mermaid diagrams generated
Diagrams render on GitHub, VS Code, Obsidian.
```
## Rules
- Always write to repo root; overwrite if exists.
- Every section gets at least one Mermaid diagram.
- Diagrams must be valid Mermaid that renders on GitHub.
- Architecture, not implementation — show the forest.
- Back every claim with a query result, not a guess.
- Monorepo/workspace: workspace view first, then drill into key packages.
{% if arguments %}- **Scoped mapping**: the user requested `{{ arguments }}`. Scope queries and output to that subdirectory or module.
{% endif %}- Path/module argument → scope the map.
- Keep under 500 lines. Be selective.
Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.