Backlog Creation
Create and structure the initial product backlog for "$ARGUMENTS". Break roadmap themes into epics and user stories, prioritize using MoSCoW or WSJF, identify MVP scope, and tag stories with labels.
Arguments. $ARGUMENTS may contain the project name and optional flags. Take the first token as <project> and treat --skip-checks as a flag; never include flags in file paths. All paths below use <project>. If --skip-checks is present, skip the prerequisite check and, before writing any artifact, append one line to .singularskills/log.jsonl: {"ts":"<ISO timestamp>","skill":"project-management-backlog-creation","workflow":"project-management","phase":1,"project":"<project>","event":"skipped","artifact":"01-plan.md","note":"<reason or \"none given\">"}.
Prerequisites
Part of a workflow. This skill is phase 1 (Plan) of the Scrum workflow (project-management); cross-domain workflows run it too. First check .singularskills/log.jsonl for an open run for this project: a run-started line with "project":"<project>" and no later run-finished line for the same workflow and project. If one exists, the conductor is running you: continue here. Otherwise, if the user asked to start, run, continue or resume a process or workflow rather than this one step, do not continue here: invoke the workflow skill with the workflow the user asked for, or project-management when they named none, followed by <project>; it runs this phase in order, asks before it writes and records the run. Otherwise continue here: a later phase runs on its own, behind its gate.
Run this skill's gate before writing: sh <this skill's folder>/scripts/gate.sh <project> <project root>, where <project root> is the folder that contains .singularskills/ (use . when you are already there). If it exits non-zero, stop and tell the user what it printed, unless --skip-checks was given (see Arguments). On a refusal, before you stop, append this line to .singularskills/log.jsonl (create the folder and file if missing): {"ts":"<ISO timestamp>","skill":"project-management-backlog-creation","workflow":"project-management","phase":1,"project":"<project>","event":"refused","artifact":"01-plan.md","note":"<what the gate printed>"}. Once the gate has passed, or under --skip-checks once you have appended the skipped line, append this line before you start work: {"ts":"<ISO timestamp>","skill":"project-management-backlog-creation","workflow":"project-management","phase":1,"project":"<project>","event":"started","artifact":"01-plan.md","note":""}.
Check that .singularskills/project-management/<project>/00-initiate.md exists. If it does not, tell the user to run an Initiate skill first (e.g., project-charter) and stop.
Process
Read existing context:
- Read
.singularskills/project-management/<project>/00-initiate.mdfor charter and scope context - Read
.singularskills/project-management/<project>/01-plan.mdif it exists (for vision, goals, and roadmap) - Read
references/user-story-template.mdfor story format - Read
references/scrum-guide.mdfor Scrum alignment
- Read
Break roadmap themes into epics:
- For each theme from the roadmap, identify constituent epics
- For each epic: name, description, acceptance criteria, estimated size (S/M/L/XL)
- Ensure epics are large enough to be meaningful but small enough to complete in 1-3 sprints
- If no roadmap exists yet, derive epics directly from charter scope and objectives
Break epics into user stories:
- Write each story in "As a [persona], I want [action], so that [benefit]" format
- Aim for 3-8 stories per epic (split epics that generate more than 10 stories)
- Ensure each story delivers value independently where possible
- Add brief acceptance criteria to each story (detailed criteria come in the user-stories skill)
Prioritize the backlog:
- Select a prioritization method:
- MoSCoW: Must have, Should have, Could have, Won't have (this time)
- WSJF (Weighted Shortest Job First): (Business Value + Time Criticality + Risk Reduction) / Job Size
- Apply the method consistently across all stories
- Document the rationale for high-priority and deprioritized items
- Resolve priority conflicts by referencing product goals and North Star metric
- Select a prioritization method:
Structure the backlog by priority:
- Order stories from highest to lowest priority
- Group by epic for readability, but maintain priority order within each epic
- Number stories for easy reference (e.g., EPIC-001, EPIC-002)
- Include a priority summary showing the distribution (how many Must/Should/Could/Won't)
Identify MVP scope:
- MVP = all Must-have stories (or highest-WSJF stories that fit within first milestone)
- Validate that MVP delivers a coherent, usable product — not just a random subset
- Check that MVP aligns with the first release milestone from the roadmap
- Flag any Must-have stories that feel too large or risky for MVP
Tag stories with labels:
- Type: feature, bug, tech-debt, spike (research), infrastructure
- Component: frontend, backend, API, database, DevOps, design
- Risk level: high, medium, low
- Ensure labels are consistent and will be useful for filtering and reporting
Write the artifact — append to
.singularskills/project-management/<project>/01-plan.mdunder a## Product Backlogsection. Create the file with a# Plan — <project>heading if it does not exist; if a## Product Backlogsection already exists, replace only that section. The section contains:- Epics Summary — list of epics with size, theme, and story count
- Prioritized Backlog — ordered list of stories with priority, epic, labels
- MVP Scope — stories included in MVP with rationale
- Priority Distribution — counts by MoSCoW category or WSJF bands
- Label Summary — counts by type and component labels
Output
Product backlog appended to .singularskills/project-management/<project>/01-plan.md. Present a summary highlighting:
- Total number of epics and stories created
- MVP scope: number of stories and estimated effort
- Priority distribution across MoSCoW categories
- Any gaps or risks identified during backlog creation
Record the run. After you have written your section, append this line to .singularskills/log.jsonl (the started line of Prerequisites, with "event":"finished"): {"ts":"<ISO timestamp>","skill":"project-management-backlog-creation","workflow":"project-management","phase":1,"project":"<project>","event":"finished","artifact":"01-plan.md","note":""}.
This artifact is shared by every skill of phase 1 (Plan). The frontmatter is written once, by whoever creates the file: if you create it, open it with the block below (skill is the phase title, started the time of that first write; gate is passed when the gate ran clean and skipped under --skip-checks); if it already exists, leave the block alone except to update finished and to set gate to the worst value among the sections (skipped over passed).
---
skill: Plan
workflow: project-management
phase: 1
project: <project>
started: <ISO timestamp>
finished: <ISO timestamp>
agent: <the agent you run in, or "unknown">
gate: <passed|skipped>
---
Open your ## Product Backlog section with one italic line, *<skill name> · <ISO timestamp> · gate: <passed|skipped>* (your skill name is project-management-backlog-creation).
End your section with ### Decisions and ### Open questions (one level under your ## Product Backlog heading, so the section stays one block), in this shape:
### Decisions
- <what was chosen> — <why> — <what was rejected>
### Open questions
- <what the next phase or a reviewer must settle>