# Backlog

> Maintain Linear backlog at ~50 items by generating context-aware feature ideas based on the platform's current capabilities.

- **Type:** Skill
- **Install:** `agentstack add skill-imtaegan-claude-saas-flow-backlog`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ImTaegan](https://agentstack.voostack.com/s/imtaegan)
- **Installs:** 0
- **Category:** [Developer Tools](https://agentstack.voostack.com/c/developer-tools)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ImTaegan](https://github.com/ImTaegan)
- **Source:** https://github.com/ImTaegan/claude-saas-flow/tree/main/skills/backlog

## Install

```sh
agentstack add skill-imtaegan-claude-saas-flow-backlog
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Linear Backlog Management

Keeps your Linear backlog healthy (~50 items) by analyzing the codebase and generating contextually relevant enhancement ideas.

## Project Configuration

Read project configuration from `.claude/project.json`:
- `linear.teamId`, `linear.teamName`, `linear.projectId`

If `.claude/project.json` doesn't exist, suggest running `/setup-project` first.

**Target Count**: 50 items in Backlog (configurable — adjust as needed).

## Instructions for Claude

### Step 0: Load Configuration

```bash
PROJECT_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
```

Read `$PROJECT_ROOT/.claude/project.json`.

### Step 1: Analyze Current Platform

Understand the platform's current capabilities by:
1. Reading key files in the codebase (top-level entry points, route files, schema files)
2. Checking for a `REFERENCES/` directory in the project root
3. Understanding the domain from package.json, README, and code structure

### Step 2: Query Current Backlog

```
Use mcp__linear__list_issues:
- team: [from config.linear.teamName]
- project: [from config.linear.projectId]
- state: "Backlog"
- includeArchived: false
- limit: 250
```

Calculate: `itemsToCreate = 50 - currentBacklogCount`

If backlog already has 50+ items:
```
Backlog is already at target size (X items)
No new items needed!
```

### Step 3: Generate New Feature Ideas

Generate `itemsToCreate` features that:

**Quality Criteria:**
- Are contextually relevant to the project's domain
- Build on existing features found in the codebase
- Address real pain points for the target users
- Are not duplicates of existing backlog items
- Range from quick wins to strategic initiatives

**Feature Categories:**
- Workflow automation and efficiency
- Analytics and reporting
- Communication and collaboration
- Integration with relevant tools
- Mobile and accessibility improvements
- Security and compliance enhancements
- User experience polish
- Growth and engagement features

**Each Feature Must Include:**
- **Name**: Clear, concise title (50 chars max)
- **Description**: 2-3 sentences explaining what it does and why it's valuable
- **Priority**: 0=None, 1=Urgent, 2=High, 3=Normal, 4=Low
- **Labels**: "Feature" + additional relevant labels

### Step 4: Add Features to Linear

For each generated feature:

```
Use mcp__linear__create_issue:
- team: [from config.linear.teamName]
- project: [from config.linear.projectId]
- title: [feature name]
- description: [feature description]
- state: "Backlog"
- labels: ["Feature", and others]
- priority: [0-4]
```

Add a small delay between calls to be respectful of rate limits.

### Step 5: Report Results

```
=== Backlog Maintenance Complete ===

Before: X items in backlog
Created: Y new features
After: Z items in backlog (target: 50)

New Features Added:
1. **ABC-XX**: Feature Name (Priority: High)
   Description...

2. **ABC-XX**: Feature Name (Priority: Medium)
   Description...

Use /feature-from-backlog to refine and start working on any of these!
```

## Example Feature Ideas

**Good Examples:**
- "Bulk Status Updates" — Update status for multiple records at once with reason tracking. Saves time when processing batches.
- "Network Visualization Map" — Visual graph showing relationships and patterns. Helps identify top connections.
- "Automated Onboarding Email Series" — 5-email sequence triggered on signup with personalization tokens.

**Bad Examples (Too Generic):**
- "Make UI Better" — Not specific enough
- "Add API Endpoints" — Not user-facing value
- "Fix Bugs" — Not a feature

## Feature Distribution Guidelines

Aim for a balanced backlog:
- **High Priority (20%)**: Major features, competitive necessities
- **Medium Priority (50%)**: Standard improvements
- **Low Priority (30%)**: Polish, edge cases, experiments

## Error Handling

**If Linear API fails:**
```
Failed to connect to Linear
Check MCP server configuration
```

## Success Criteria

- Backlog has ~50 items
- All new items have valid priorities
- No duplicate feature names
- All features are contextually relevant

## Integration with Other Skills

- **Start backlog item**: `/feature-from-backlog`
- **View all issues**: `/project-status`

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ImTaegan](https://github.com/ImTaegan)
- **Source:** [ImTaegan/claude-saas-flow](https://github.com/ImTaegan/claude-saas-flow)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-imtaegan-claude-saas-flow-backlog
- Seller: https://agentstack.voostack.com/s/imtaegan
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.