start-issue▌
vkehfdl1/marshroom · updated Apr 8, 2026
MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.
Automate Marshroom cart issue setup with branch creation, status tracking, and context injection.
- ›Reads the Marshroom state file, filters cart issues matching the current repository, and creates a feature or hotfix branch with standardized naming ( Feature/#N or HotFix/#N )
- ›Mandatory state.json update: sets issue status to running via marsh start command or atomic jq write, with verification to ensure the update succeeds
- ›Injects issue body as context so the agent understands the full
Start working on a Marshroom cart issue in the current repository.
Critical Requirements
- state.json update is MANDATORY. After creating the branch, you MUST update the issue status to
runningin${MARSHROOM_STATE:-~/.config/marshroom/state.json}. If this fails, stop and report the error — do NOT silently continue. - Use
marsh startif available; otherwise fall back to directjqatomic write (see step 10).
Steps
- Read
${MARSHROOM_STATE:-~/.config/marshroom/state.json}and parse the JSON - Extract the
cartarray. If the cart is empty, tell the user to add issues in the Marshroom app - Run
git remote get-url originto get the current repo's remote URL - Extract
owner/repofrom the remote URL (handle both HTTPS and SSH formats) - Filter cart entries where
repoCloneURL(HTTPS) orrepoSSHURL(SSH) matches the current remote. Compare by extractingowner/repofrom each - If no matching cart entries, tell the user this repo has no cart issues
- If
$ARGUMENTScontains an issue number, find that entry; otherwise if multiple matches, list them and ask the user to pick one - Run
git checkout main && git pull origin mainto ensure main is up to date - Create and checkout the branch:
git checkout -b {branchName}The branch name should beFeature/#NorHotFix/#N.Nis issue number. - Update issue status (MANDATORY):
- First try:
marsh start #{issueNumber} - If
marshis not found in PATH, fall back to direct atomic update:STATE_FILE="${MARSHROOM_STATE:-~/.config/marshroom/state.json}" TMP="$(mktemp "${STATE_FILE}.XXXXXX")" jq --argjson n ISSUE_NUMBER '.cart |= map(if .issueNumber == $n then .status = "running" else . end)' \ "$STATE_FILE" > "$TMP" && mv -f "$TMP" "$STATE_FILE" - Verify the update succeeded by reading state.json and confirming status is
running
- First try:
- Inject issue context:
- Read the
issueBodyfield from the matched cart entry - If non-null, display it under a "## Issue Details" header
- This gives the agent full context about what needs to be done
- Read the
- Confirm the branch was created and display:
- Issue: #{issueNumber} {issueTitle}
- Branch: {branchName}
- Repository: {repoFullName}
- Status: running
- Ask the user permission to start planning to resolve issue. If the user allows it, starts planning using /plan mode.
How to use start-issue on Cursor
AI-first code editor with Composer
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
- ›Cursor installed and configured on your development machine
- ›Node.js version 16.0+ with npm package manager (verify with
node --version) - ›Active project directory or workspace where you want to add start-issue
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
The skills CLI fetches start-issue from GitHub repository vkehfdl1/marshroom and configures it for Cursor.
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
Verify installation
Confirm successful installation by checking the skill directory location:
Reload or restart Cursor to activate start-issue. Access the skill through slash commands (e.g., /start-issue) or your agent's skill management interface.
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
List & Monetize Your Skill
Submit your Claude Code skill and start earning
Use Cases▌
User Story & Requirements Generation
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Competitive Analysis
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Roadmap Prioritization
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
Make data-driven prioritization decisions faster
Stakeholder Communication
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Implementation Guide▌
Prerequisites
- ›Claude Desktop or compatible AI client
- ›Access to product documentation and roadmap tools (Jira, Notion, etc.)
- ›Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
- ›Stakeholder contact information and communication channels
Time Estimate
30-60 minutes to see productivity improvements
Installation Steps
- 1.Install product management skill
- 2.Start with user story generation for known feature
- 3.Progress to competitive analysis: research 2-3 competitors
- 4.Use for roadmap prioritization: apply RICE/ICE scoring
- 5.Draft stakeholder communications and refine based on feedback
- 6.Build template library for recurring PM tasks
- 7.Share effective prompts with product team
Common Pitfalls
- ⚠Not validating competitive research—verify facts before sharing
- ⚠Accepting user stories without involving engineering team
- ⚠Over-relying on frameworks without qualitative judgment
- ⚠Not customizing outputs to company culture and communication style
- ⚠Skipping stakeholder validation of generated requirements
Best Practices▌
✓ Do
- +Validate research and competitive analysis with real data
- +Collaborate with engineering when generating technical requirements
- +Customize frameworks and templates to your company context
- +Use skill for first drafts, refine with stakeholder input
- +Document successful prompt patterns for PM tasks
- +Combine AI efficiency with human judgment and intuition
✗ Don't
- −Don't publish competitive analysis without fact-checking
- −Don't finalize user stories without engineering review
- −Don't make prioritization decisions solely on AI scoring
- −Don't skip customer validation of generated requirements
- −Don't ignore company-specific context and culture
💡 Pro Tips
- ★Provide context: company goals, constraints, customer feedback
- ★Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
- ★Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
- ★Use skill for 70% generation + 30% customization to company needs
When to Use This▌
✓ Use When
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid When
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
Learning Path▌
- 1Basic: user stories, feature specs, status updates
- 2Intermediate: competitive analysis, prioritization frameworks, PRDs
- 3Advanced: product strategy, go-to-market planning, OKR setting
- 4Expert: product vision, market positioning, business model innovation
Discussion
Product Hunt–style comments (not star reviews)- No comments yet — start the thread.
Ratings
4.4★★★★★70 reviews- ★★★★★Benjamin Abebe· Dec 24, 2024
I recommend start-issue for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
- ★★★★★Harper Iyer· Dec 20, 2024
Useful defaults in start-issue — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
- ★★★★★Harper Patel· Dec 20, 2024
start-issue reduced setup friction for our internal harness; good balance of opinion and flexibility.
- ★★★★★Kofi Park· Dec 16, 2024
start-issue has been reliable in day-to-day use. Documentation quality is above average for community skills.
- ★★★★★Ganesh Mohane· Dec 8, 2024
Registry listing for start-issue matched our evaluation — installs cleanly and behaves as described in the markdown.
- ★★★★★Isabella Iyer· Dec 4, 2024
start-issue is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
- ★★★★★Mei Park· Nov 27, 2024
Keeps context tight: start-issue is the kind of skill you can hand to a new teammate without a long onboarding doc.
- ★★★★★Chen Anderson· Nov 23, 2024
Solid pick for teams standardizing on skills: start-issue is focused, and the summary matches what you get after install.
- ★★★★★Harper Rao· Nov 15, 2024
Useful defaults in start-issue — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
- ★★★★★Harper Menon· Nov 11, 2024
I recommend start-issue for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
showing 1-10 of 70