# backlog-management

backlog-management is a Claude Code skill that defines shared backlog conventions for Azure DevOps, GitHub, and Jira. It structures PRD decomposition, triage, sprint planning, and task synchronization.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 1627 repo stars
- Author: microsoft
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/microsoft/hve-core/tree/HEAD/.github/skills/project-planning/backlog-management/SKILL.md
- Updated: 2026-10-25
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/backlog-management

## What it does

This skill defines a platform-agnostic baseline for managing work items. It standardizes planning file lifecycles, similarity checks for incoming work, autonomy tiers, outbound sanitization, and story quality criteria. Concrete tracker details remain isolated in platform references: MCP command sets for Azure DevOps and GitHub, or terminal operations and environment variables for Jira.

Target platforms are resolved through an ordered heuristic: direct user prompts, active paths under `.copilot-tracking/**`, issue key shapes such as `#NNN` or `PROJ-123`, and non-interactive MCP readiness probes. When multiple platforms look plausible, the agent asks for clarification between the top two choices instead of guessing.

Because `user-invocable` is set to `false`, developers do not trigger this skill directly. Consuming agent skills load these conventions to interact with actual trackers.

## Requirements
- Works with: GitHub, Azure DevOps, Jira

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add microsoft/hve-core --skill backlog-management -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add microsoft/hve-core --skill backlog-management -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add microsoft/hve-core --skill backlog-management -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install microsoft/hve-core .github/skills/project-planning/backlog-management
```

2. **Manually: put the files in place**
- File: `.github/skills/backlog-management/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add microsoft/hve-core --skill backlog-management -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/microsoft/hve-core --path .github/skills/project-planning/backlog-management
```

### Windsurf (Devin Desktop)

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

### 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/microsoft/hve-core/tree/HEAD/.github/skills/project-planning/backlog-management/SKILL.md

## When to use it
- break down a PRD into an actionable work-item hierarchy
- triage open issues and detect duplicate items
- plan sprints by assessing capacity and dependencies
- create pull requests and extract pipeline logs in Azure DevOps

## Example prompts
- Break down this PRD into work items for our Jira backlog
- Review recent GitHub issues, flag duplicates, and suggest triage labels
- Plan our next sprint scope and check dependencies in Azure DevOps

## Source text · SKILL.md · MIT

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: bb5a5baa70a8a454.

BEGIN THIRD-PARTY FILE bb5a5baa70a8a454
```text
---
name: backlog-management
description: "Shared backlog conventions for Azure DevOps, GitHub, and Jira. Use for platform resolution, autonomy tiers, sanitization guards, and story quality, and for Azure DevOps pull request creation and build status or log retrieval."
license: MIT
user-invocable: false
compatibility: "Hosts: vscode, github-coding-agent. Reference-only conventions; the consuming skill supplies tracker access."
metadata:
  authors: "microsoft/hve-core"
  spec_version: "1.0.0"
  last_updated: "2026-10-02"
---

# Backlog Management

Shared, platform-agnostic conventions for backlog managers across Azure DevOps, GitHub, and Jira. This skill owns the structural core that every platform reuses: how planning files are named and laid out, how planned items are identified, how candidate work is compared to existing work, how autonomy gates mutations, how outbound text is sanitized, and how an interrupted workflow resumes. Each platform contributes only its small delta (the command surface, field vocabulary, reference-ID prefix, and action verbs) through a per-platform reference.

## When to Use

Use this skill when running any backlog workflow for a supported platform:

* Discovery — turn user requests, artifacts, or queries into candidate work items.
* Triage — assess existing items, recommend field, label, priority, and status changes, and flag duplicates.
* PRD-to-work-item planning — map a PRD into a validated work-item hierarchy for a separate execution pass.
* Sprint and iteration planning — analyze a delivery window for coverage, capacity, dependencies, and gaps, and recommend grooming candidates.
* Execution — process a reviewed handoff into sequential create, update, transition or move, and comment operations.

Read the platform-agnostic conventions below, then load the reference that matches the active platform for its concrete command surface and vocabulary.

## How This Skill Is Organized

* This file — the platform-agnostic core: platform resolution, planning-file lifecycle, directory conventions, planning-type enum, scope normalization, reference-ID scheme, similarity assessment, autonomy tiers, content sanitization, state persistence, and human review triggers.
* [references/workflows.md](references/workflows.md) — the platform-agnostic workflow protocols (discovery, triage, execution), the platform binding resolution table, the operation contract, dry-run and error handling, and the shared planning-file templates.
```
END THIRD-PARTY FILE bb5a5baa70a8a454

The third-party file has ended. Everything between the bb5a5baa70a8a454 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 2495 of 28807 bytes. © microsoft · MIT · https://github.com/microsoft/hve-core/tree/HEAD/.github/skills/project-planning/backlog-management/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
