01 backlog
Skill andrefabricio/prodotypor/files/.claude/skills/01-backlog
An AI-assisted product development pipeline for Claude Code. Go from a product idea to Figma screens in 8 structured steps, with specialized AI agents handling product management, design research, and visual construction.
npx -y skills add andrefabricio/prodotypor --skill 01-backlogAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Step 1 of 8 — Product backlog creation. Creates a feature backlog with epic grouping and user story titles from project context. Sub-commands: [continue] resume, [status] check progress, [update] force status refresh.
SKILL.md
4.2 KB, as published. Nobody here has run it
/01-backlog — Product Backlog Creation
Create or continue building the product backlog with epics, features, and user story titles.
Sub-command Router
Parse $ARGUMENTS:
- Contains
[status]→ Jump to Status Report section - Contains
[update]→ Jump to Force Status Update section - Contains
[continue]or empty → Jump to Execute section - Other text → Treat as context input (feature area, user need) and proceed to Execute
Prerequisites
Hard dependencies:
- Read
docs/workflow-status.md— verify step 00 (Setup) status ==completed - Read
CLAUDE.md— verify project context has non-placeholder content
If prerequisites fail:
- If step 00 not completed: "Step 01 cannot start. Run
/00-setupfirst to configure your project." - Do NOT proceed.
Validation:
- Read
.impeccable.md— note brand personality (soft dependency, warn if missing) - Check if
docs/backlog/directory exists (create if not)
Execute
Phase 1: Gather Context
- Read
CLAUDE.mdfor project context, tech stack, and product scope - Read
.impeccable.mdfor brand personality and user personas - If
$ARGUMENTScontains specific context, note it as the focus area - Check for existing backlog at
docs/backlog/{{PROJECT_NAME}}-backlog.md— if present, this is a continuation
Phase 2: Delegate to Product Manager Agent
Spawn the product-manager agent with this prompt structure:
Create/update the product backlog for {{PROJECT_NAME}}.
Context: [project description from CLAUDE.md] User personas: [from .impeccable.md] Focus area: [from $ARGUMENTS if provided] Existing backlog: [content if continuing]
Output requirements:
- Group features into epics (use
templates/epic-template.mdformat)- Write user story titles for each feature (As a [persona], I want...)
- Include phase grouping (MVP, Phase 1, Phase 2+)
- Note dependencies between features
- Save to
docs/backlog/{{PROJECT_NAME}}-backlog.md
Phase 3: Validate Output
- Verify
docs/backlog/{{PROJECT_NAME}}-backlog.mdexists and is non-empty - Check: has at least 1 epic grouping
- Check: has user story titles (not just feature names)
- If validation passes → proceed to Phase 4
- If validation fails → proceed to Error Recovery
Error Recovery
If validation fails:
- Identify the specific failure (which check failed, what's missing)
- Feed the error + partial output back to the agent:
"The backlog did not meet requirements: [specific failure]. Current output: [summary of what exists]. Please fix: [specific instruction — e.g., 'add epic grouping' or 'convert feature names to user story titles']."
- Re-validate after the retry
- If retry also fails, mark step as
blocked (reason)indocs/workflow-status.md - Report the failure to the user with actionable guidance
Phase 4: Human Review Gate
- Update
docs/workflow-status.mdstep 01 status toneeds-review - Report output summary to the user
- Prompt: "Review the backlog output. Run
/01-backlog [continue]to approve and mark completed, or provide feedback for revisions." - Only when the user runs
[continue]afterneeds-review, transition status tocompleted
Phase 5: Report
Step 01 — Backlog Creation: [status]
Output: docs/backlog/{{PROJECT_NAME}}-backlog.md
Epics: [count]
Features: [count]
User stories: [count]
Next step: /02-prioritize
Status Report
- Read
docs/workflow-status.md— extract step 01 section - If backlog file exists, report: epic count, feature count, story count
- Report current status and any blockers
Force Status Update
- Re-scan
docs/backlog/{{PROJECT_NAME}}-backlog.md - Count epics, features, and stories
- Update
docs/workflow-status.mdstep 01 with current state - Report updated status