jon-the-dev/claude-code-plugin-marketplace-v0/next-issue
Claude Code and agent skill by jon-the-dev/claude-code-plugin-marketplace-v0
- community
- ext:[{"type":"hook","description":"Pre/post lifecycle hooks"}]
Checking that the SKILL.md file is still in the repository.
Get the next GitHub issue to work on, implement it in an isolated worktree, create a PR, and auto-merge when CI passes. Use this skill whenever the user wants to pick up the next issue, work on GitHub issues, or asks "what should I work on next?" — even if they don't say "next-issue" explicitly.
Install
npx vskill@latest install jon-the-dev/claude-code-plugin-marketplace-v0/next-issueSemi-extensibleMentions customization, but needs skill-specific knowledge. Read the extensible skills standard
SKILL.md
Next Issue
This is a single-issue shortcut. It delegates to the mini-sprint skill with these overrides:
- NUM_ISSUES = 1 — select only the top priority issue
- Skip Phase 2 (Planning) — no sprint plan needed for one issue; go straight to worktree setup
- No sprint report — just log the result to the journal and AUTOBOT.log
- No user confirmation on issue selection — the priority rules are encoded in the script; announce which issue you're picking up and why, then proceed immediately
Read and follow the mini-sprint skill (${CLAUDE_PLUGIN_ROOT}/skills/mini-sprint/SKILL.md) with the overrides above.
Implementation Agents
When implementing the issue, use the same subagent strategy as /implement:
- `frontend-developer` — React and Frontend work
- `backend-developer` — FastAPI and backend logic
- `cloud-architect` — AWS, Terraform, or DevOps activities
- `test-writer` — Write new or updated tests for changed code (runs on sonnet to save tokens)
- `test-runner` — Python, JS, TS, TF, or other test execution
- `code-auditor` — Post-implementation audit for issues
After each code-change agent finishes:
- Launch a
test-writeragent to write any new or updated tests needed for the changed code - Launch a
test-runnerto validate all tests pass - Launch a
/codex:reviewagent to see if we missed anything (ensure it knows the task/issue details). Requires the externalcodexplugin (/plugin install codex@openai-codex); if it isn't installed, skip this step and note it in the result. - Follow up with the appropriate developer agent to address any failures
Run code-auditor and pre-commit checks before committing.
Use the shared fetch script:
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingplugins/ai-developer/skills/next-issue/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Extension points
hookPre/post lifecycle hooks
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/jon-the-dev/claude-code-plugin-marketplace-v0/next-issue)