From ai-dev
Process issues sequentially: /dev per issue in isolated sub-agent → CI wait → merge → next
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-dev:dev-all [issue numbers, e.g. #42 #43 #44, or empty for all open issues][issue numbers, e.g. #42 #43 #44, or empty for all open issues]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Process multiple GitHub Issues sequentially. Each issue runs `/dev` in an isolated sub-agent, then waits for CI and merges before proceeding to the next.
Process multiple GitHub Issues sequentially. Each issue runs /dev in an isolated sub-agent, then waits for CI and merges before proceeding to the next.
Arguments: $ARGUMENTS
Each issue gets its own branch, PR, and merge cycle:
CLAUDE.md and look for ## Core Values sectionIf $ARGUMENTS is provided: Extract issue numbers.
If empty: Fetch all open issues:
gh issue list --state open --json number,title,labels,body --limit 100
won't — these are explicitly decided not to implement## Won't Do — cross-reference issue titlesLaunch parallel Explore agents (one per issue) to quickly understand scope:
Each agent:
gh issue view {NUMBER} --json title,body,labels,commentsCheck issue bodies for: blocked by #N, depends on #N, after #N
Topological sort:
Present:
won't label and Won't Do matches)Ask user to confirm before proceeding.
Create a master task tracker:
TaskCreate for each issue: "#{number}: {title}"
git checkout main && git pull origin main
Agent(
prompt: "/goal 'Issue #{issue_number} is resolved: tests pass, review has no Critical findings, and PR is created' /dev #{issue_number}",
model: "opus",
isolation: "worktree"
)
The sub-agent:
After the sub-agent completes, validate the result before proceeding to merge:
workspace/{issue}/review.json to get the structured review outputDecision logic:
| Review Status | Action |
|---|---|
critical (critical_count > 0) | Skip this issue. Report to user: "#{issue} has {N} critical findings — skipping." Mark task as failed. Proceed to next issue. |
warnings (warning_count > 0) | Report to user. AskUserQuestion: "#{issue} PR has {N} unresolved warnings. Merge anyway?" If yes → proceed. If no → skip. |
clean | Proceed to auto-merge. |
Sub-agent failed (status: "failed") | Skip this issue. Report failure reason. Proceed to next issue. |
gh pr merge {PR_URL} --auto --merge --delete-branch
Poll until merged (check every 30 seconds, timeout 15 minutes):
STATE=$(gh pr view {PR_URL} --json state -q '.state')
If CI fails:
## Batch Development Summary
| # | Issue | PR | Status |
|---|-------|----|--------|
| 1 | #{42} Title | PR_URL | Merged |
| 2 | #{43} Title | PR_URL | Merged |
| 3 | #{44} Title | — | Skipped (CI failed) |
Completed: N / M issues
Mark all tasks completed.
When the user invokes /dev-all with /goal, the entire batch runs autonomously:
/goal "All issues in $ARGUMENTS are resolved: each has a merged PR or a documented skip reason"
In autonomous mode:
AskUserQuestion confirmations — proceed with best judgment| Situation | Action |
|---|---|
| Issue not found | Skip, warn in report |
| Circular dependency | Skip affected issues, report |
| Sub-agent /dev fails | Ask user: skip or stop |
| CI fails | Ask user: skip or stop |
| Merge conflict | Ask user: skip or stop |
| 3 consecutive failures | Stop, report to user |
| Auto-merge timeout (15min) | Report, ask user |
npx claudepluginhub riox432/ai-dev-templates --plugin ai-devGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.