Resolve issues on all your open PRs in parallel. Use when user says "fix all my open PRs", "resolve issues on all my PRs", "address comments on all my pull requests", "batch fix my PRs", or "make all my PRs merge-ready".
Automatically resolves issues across multiple open pull requests in parallel, making them merge-ready.
npx claudepluginhub uniswap/ai-toolkitThis skill is limited to using the following tools:
Batch resolve issues across all your open pull requests in the current repository. Spawns parallel agents to address review comments and CI failures on each PR, automatically committing and pushing fixes.
| Argument | Type | Default | Description |
|---|---|---|---|
max | number | 5 | Maximum number of PRs to process |
gh api usermax PRs (default: 5)1. Get GitHub username
↓
2. List open PRs (author:me, newest first)
↓
3. Cap at max PRs
↓
4. For each PR (in parallel):
└─→ Spawn Task agent with review-executor-agent
└─→ Fix CI issues
└─→ Address review comments
└─→ Auto-commit and push each fix
↓
5. Collect results from all agents
↓
6. Output summary report
# Get current GitHub user
gh api user --jq '.login'
# Get current repo info
gh repo view --json owner,name --jq '"\(.owner.login)/\(.name)"'
Use the GitHub MCP or gh CLI to list PRs:
# List open PRs authored by current user, newest first
gh pr list --author @me --state open --json number,title,url,createdAt --limit {max}
For each PR, spawn a Task agent with the review-executor-agent subagent type:
Task(
subagent_type: "development-pr-workflow:review-executor-agent",
prompt: "Resolve all issues on PR #{pr_number} in {owner}/{repo}.
IMPORTANT: This is an AUTOMATED batch run. You MUST:
1. Fix all CI failures first
2. Address all review comments
3. AUTO-COMMIT each fix with a descriptive message
4. AUTO-PUSH after each commit
5. Do NOT ask for confirmation - commit and push immediately
PR URL: {pr_url}
PR Title: {pr_title}
After completing all fixes, report:
- Number of commits made
- Summary of changes
- Any issues that could not be resolved",
run_in_background: true
)
After spawning all agents, wait for them to complete by reading their output files. Track:
Provide a structured summary:
## Batch PR Resolution Summary
### Processed PRs: {count}/{total}
| PR | Status | Commits | Notes |
| ---- | ---------- | ------- | ------------------- |
| #123 | ✅ Success | 3 | All issues resolved |
| #456 | ✅ Success | 1 | CI fixed |
| #789 | ❌ Failed | 0 | Error: {reason} |
### Failed PRs (require manual attention)
- **PR #789**: {error_details}
### Total Changes
- **Commits made**: {total_commits}
- **PRs resolved**: {success_count}
- **PRs failed**: {fail_count}
This skill AUTO-COMMITS and AUTO-PUSHES changes. Unlike the single-PR resolver, this batch mode operates autonomously to maximize throughput. Each fix is committed granularly with a descriptive message.
# Resolve issues on up to 5 PRs (default)
/resolve-all-prs
# Resolve issues on up to 10 PRs
/resolve-all-prs max=10
# Resolve issues on up to 3 PRs
/resolve-all-prs max=3
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.