# Prime Backend

Primes the agent with focused understanding of the backend portion of the codebase, ...

- Repository: https://github.com/coleam00/skills (726 stars)
- Category: Design
- License: MIT
- Last updated: 2026-10-30
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add coleam00/skills --skill prime-backend -g -a claude-code -y`
Codex: `npx skills add coleam00/skills --skill prime-backend -g -a codex -y`
Cursor: `npx skills add coleam00/skills --skill prime-backend -g -a cursor -y`
Gemini CLI: `npx skills add coleam00/skills --skill prime-backend -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add coleam00/skills`

## Description

Primes the agent with focused understanding of the backend portion of the codebase, API routes, services, data models, and database layer, without loading unrelated frontend code. Use at the start of a session when the work is scoped to API endpoints, business logic, or data access. Optionally pulls external task context from Jira issues and Confluence pages first.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Prime Backend: Load Backend Context

## Objective

Build targeted understanding of the backend codebase by analyzing its structure, routes, services, and data layer. Loading only backend context keeps the context window light on complex full-stack codebases. If external task references are provided, load them first so the analysis is anchored to the actual work.

## Process

### Step 0: Load External Context

**Run this step BEFORE the codebase analysis.** It accepts optional arguments: `[jira-issue-keys] [confluence-page-ids]`.

- Jira keys may be a single key (`ACC-2`) or comma-separated (`ACC-2,ACC-3`).
- Confluence page ids are numeric page ids.

**If Jira issue keys are provided:**

1. Call `mcp__atlassian__getAccessibleAtlassianResources` to obtain the `cloudId`.
2. For each Jira key, call `mcp__atlassian__getJiraIssue` with that `cloudId`, the issue key, and `responseContentFormat: "markdown"`.
3. Treat the returned issue summary, description, and acceptance criteria as the task context for everything that follows.

**If Confluence page ids are provided:**

1. Call `mcp__atlassian__getConfluencePage` for each page id with `contentFormat: "markdown"` (use the `cloudId` from above, fetching it via `mcp__atlassian__getAccessibleAtlassianResources` if it was not already retrieved).
2. Treat the returned page content as supporting context (specs, design docs, requirements).

**If no arguments are provided:** Skip this step entirely and proceed to Step 1.

Briefly summarize any external context loaded before continuing, this frames the rest of the priming.

### 1. Locate the Backend

List all tracked files to find the backend root:

!`git ls-files`

Common backend roots: `backend/`, `server/`, `api/`, `app/` (FastAPI/Django), `src/` (when project is backend-only). Identify the correct root before proceeding.

### 2. Read Backend Documentation

The rest: https://github.com/coleam00/skills/blob/HEAD/.claude/skills/prime-backend/SKILL.md