# platform-architecture-analyze

Audits a Salesforce DX project against the Salesforce Well-Architected framework. It checks code and metadata, scores pillars, and leaves repo files untouched.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 2900 installs · ★ 1112
- Author: forcedotcom
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/forcedotcom/sf-skills/tree/HEAD/plugins/builder/salesforce-code-quality/skills/platform-architecture-analyze/SKILL.md
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/skills/platform-architecture-analyze

## What it does

The skill orchestrates an architecture review of a Salesforce DX codebase against the Salesforce Well-Architected framework. It evaluates observable code and metadata signals across pillars such as Trusted and Adaptable. The review inspects sharing declarations and SOQL selectivity, attaching exact `file:line` references to every finding.

Instead of running a separate static scanner from scratch, it delegates heavy checks to `dx-code-analyzer-run` and language server checks via `platform-lsp-integrate`. Direct `grep` and `find` commands catch lightweight structural anti-patterns, such as Apex classes missing sharing keywords and legacy workflow metadata. When an active org connection exists via `sf org display`, it inspects OWD settings and permission sets.

The skill runs strictly in read-only mode: it never edits code or deploys metadata, meaning developers must apply all recommended fixes manually. Running it requires the Salesforce CLI (`sf` version `>=2.0.0`). Governance criteria that cannot be verified directly in local files are shifted into a separate checklist for manual review.

## Requirements
- Works with: Salesforce

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add forcedotcom/sf-skills --skill platform-architecture-analyze -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/platform-architecture-analyze/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/platform-architecture-analyze/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add forcedotcom/sf-skills --skill platform-architecture-analyze -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/platform-architecture-analyze/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add forcedotcom/sf-skills --skill platform-architecture-analyze -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/platform-architecture-analyze/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install forcedotcom/sf-skills platform-architecture-analyze
```

2. **Manually: put the files in place**
- File: `.github/skills/platform-architecture-analyze/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add forcedotcom/sf-skills --skill platform-architecture-analyze -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/forcedotcom/sf-skills --path plugins/builder/salesforce-code-quality/skills/platform-architecture-analyze
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/platform-architecture-analyze/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add forcedotcom/sf-skills --skill platform-architecture-analyze -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/forcedotcom/sf-skills/tree/HEAD/plugins/builder/salesforce-code-quality/skills/platform-architecture-analyze/SKILL.md

## When to use it
- Audit a Salesforce DX repository against Well-Architected pillars
- Spot Apex classes missing `with sharing` or `inherited sharing` declarations
- Identify SOQL queries inside loops and unindexed queries
- Generate a governance checklist for manual team review
- Detect legacy workflow metadata and `@future` annotations across packages

## Example prompts
- Review the architecture of this Salesforce project
- Run a Well-Architected check on this repository
- Audit this project for security and governor limit risks

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 310f093d61354c50.

BEGIN THIRD-PARTY FILE 310f093d61354c50
```text
---
name: platform-architecture-analyze
description: "Use when the developer asks to \"review the architecture\", \"run a Well-Architected check\", \"audit this project\", \"is this project well-architected?\", or wants to assess security/governor-limit/risk as a holistic code-and-metadata health report. Grades observable criteria (sharing/FLS, bulkification, SOQL selectivity, packageability) with file:line evidence; emits a governance checklist for what it can't see. Read-only, never edits. DO NOT TRIGGER for single-tool Apex scans (dx-code-analyzer-run)."
allowed-tools:
  - Bash
  - Read
  - Glob
  - Grep
metadata:
  cliTools:
    - tool: ["sf"]
      semver: ">=2.0.0"
  relatedSkills:
    - "dx-code-analyzer-run"
    - "platform-lsp-integrate"
    - "platform-metadata-retrieve"
    - "platform-apex-generate"
---

# Analyzing Architecture (Well-Architected Review)

Grade a Salesforce DX project against the **Salesforce Well-Architected** framework and produce an honest, evidence-backed report: a pillar-scored table for what's observable in code and metadata, plus a human checklist for the governance/process concerns a local repo can't reveal.

This skill is an **orchestrator**. It does not re-implement static analysis — it drives the analysis skills the plugin already ships and maps their output onto the Well-Architected pillars. It is **read-only**: it grades and recommends; it never edits, deploys, or deletes.

It also backs the `architecture-review` agent, which runs this exact workflow as a dedicated read-only reviewer. Invoke the agent for an end-to-end review; use this skill directly when you want the workflow inline in the current session.

## Capability resolution

1. **Skill-orchestrated review** (this skill) — runs the observable checks by delegating to existing skills/MCP tools, scores each sub-pillar, and emits the manual checklist.
2. **Direct CLI / grep** — used only for the lightweight structural signals the rubric names (sharing keywords, legacy-tech file types, deploy strategy). Fine standalone, but skips the pillar scoring and the governance checklist this skill provides.
3. **API** — not applicable.
```
END THIRD-PARTY FILE 310f093d61354c50

The third-party file has ended. Everything between the 310f093d61354c50 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2166 of 10165 bytes. © forcedotcom · Apache-2.0 · https://github.com/forcedotcom/sf-skills/tree/HEAD/plugins/builder/salesforce-code-quality/skills/platform-architecture-analyze/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md