Browser Sandbox Environment
⚡️ Ready to unleash?
Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.
pr-automation
Install pr-automation, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.
PR Automation
Orchestrate the full PR automation lifecycle using a label-based state machine. Each invocation performs at most one "heavy" action (review or fix), then exits. Pure skips continue within the same session to find the next eligible PR.
Announce at start: "I'm using pr-automation skill to process PRs."
Usage
/pr-automation
No arguments required. The daemon script scripts/pr-automation.sh manages the automation loop.
Configuration
TRUSTED_CONTRIBUTORS_TEAM: detected from REPO org (e.g. iOfficeAI/trusted-contributors)
CRITICAL_PATH_PATTERN: env var, default in scripts/pr-automation.conf
LARGE_PR_FILE_THRESHOLD: env var (default: 50), also in scripts/pr-automation.conf
PR_DAYS_LOOKBACK: env var (default: 7), also in scripts/pr-automation.conf
REPO is detected automatically at runtime — do not hardcode it:
bash1REPO=$(gh repo view --json nameWithOwner --jq '.nameWithOwner') 2ORG=$(echo "$REPO" | cut -d'/' -f1)
Label State Machine
| Label | Meaning | Terminal? |
|---|---|---|
bot:reviewing | Review in progress (mutex) | No |
bot:ready-to-fix | CONDITIONAL review done, waiting for bot to fix next session | No |
bot:fixing | Fix in progress (mutex) | No |
bot:ci-waiting | CI failed and author notified — snoozed until author pushes new commits | No |
bot:needs-rebase | Merge conflict that bot cannot auto-resolve — author must rebase | No |
bot:needs-human-review | Blocking issues — human must intervene | Yes |
bot:ready-to-merge | Bot done, code is clean — human just needs to confirm and merge | Yes |
Exit Rules
- Any substantive action (approve workflow, post comment, run review, run fix) → EXIT after completing
- Pure skip (WIP, draft, terminal label, CI running, mergeability unknown,
bot:ci-waiting) → continue to find next PR in same session
Steps
Step 1 — Fetch Candidate PRs
Read the lookback window from the environment (default 7 days):
bash1DAYS=${PR_DAYS_LOOKBACK:-7} 2gh pr list \ 3 --state open \ 4 --search "created:>=$(date -v-${DAYS}d '+%Y-%m-%d' 2>/dev/null || date -d "${DAYS} days ago" '+%Y-%m-%d') -is:draft" \ 5 --json number,title,labels,createdAt,author \ 6 --limit 50
Save the result as candidate_prs.
If candidate_prs is empty: log [pr-automation] No open PRs found. Exiting. then log [pr-automation:exit] action=no_prs reason="no open PRs" and EXIT.
Step 2 — Get Trusted Contributors
bash1gh api orgs/${ORG}/teams/trusted-contributors/members --jq '[.[].login]'
Save as trusted_logins. If API call fails, treat as empty array.
Step 3 — Select Target PR
Sort candidate_prs using this three-key order:
- Primary: has label
bot:ready-to-fix→ these PRs first - Secondary: author.login in
trusted_logins→ trusted PRs next - Tertiary: createdAt ascending (oldest first / FIFO)
Iterate through sorted list to find the first eligible PR.
Skip conditions (skip this PR, try next — stay in session):
| Condition | Check |
|---|---|
Title contains WIP (case-insensitive) | title.toLowerCase().includes('wip') |
Has label bot:needs-rebase | check labels array |
Has label bot:needs-human-review | check labels array |
Has label bot:ready-to-merge | check labels array |
Has label bot:done | check labels array |
Has label bot:reviewing | check labels array |
Has label bot:fixing | check labels array |
Has label bot:ci-waiting | check labels array — wake-up check runs as fallback if no eligible PR found |
When eligible PR found:
For fresh PRs (no bot: label): add bot:reviewing to claim it:
bash1gh pr edit <PR_NUMBER> --add-label "bot:reviewing"
For bot:ready-to-fix PRs: swap label atomically:
bash1gh pr edit <PR_NUMBER> --remove-label "bot:ready-to-fix" --add-label "bot:fixing"
Save this PR as target_pr (number, title, author.login, is_ready_to_fix).
If no eligible PR found after full iteration: run the snoozed PR wake-up checks as a fallback before giving up.
Fallback: Wake Up Snoozed PRs
Check both bot:ci-waiting and bot:needs-rebase PRs for new commits.
1. Wake up bot:ci-waiting PRs:
Fetch all open PRs with bot:ci-waiting and check if the author has pushed new commits since the last CI failure comment:
bash1WAITING_PRS=$(gh pr list --state open --label "bot:ci-waiting" \ 2 --json number,createdAt,author --limit 50)
For each PR in WAITING_PRS (sorted by createdAt ascending, oldest first):
bash1PR_NUMBER=<number> 2 3LAST_CI_COMMENT_TIME=$(gh pr view $PR_NUMBER --json comments \ 4 --jq '[.comments[] | select(.body | test("<!-- pr-review-bot -->") and test("CI 检查未通过"))] | last | .createdAt // ""') 5 6LATEST_COMMIT_TIME=$(gh pr view $PR_NUMBER --json commits \ 7 --jq '.commits | last | .committedDate')
If LATEST_COMMIT_TIME > LAST_CI_COMMENT_TIME (author pushed new commits since the CI failure comment):
bash1gh pr edit $PR_NUMBER --remove-label "bot:ci-waiting" --add-label "bot:reviewing"
Log: [pr-automation] PR #<PR_NUMBER> woke up from ci-waiting: new commits detected. Claiming as target.
Save this PR as target_pr and continue to Step 4 (treat it as a freshly claimed PR).
2. Wake up bot:needs-rebase PRs:
If no bot:ci-waiting PR was woken up, check bot:needs-rebase PRs:
bash1REBASE_PRS=$(gh pr list --state open --label "bot:needs-rebase" \ 2 --json number,createdAt,author --limit 50)
For each PR in REBASE_PRS (sorted by createdAt ascending, oldest first):
bash1PR_NUMBER=<number> 2 3LAST_CONFLICT_COMMENT_TIME=$(gh pr view $PR_NUMBER --json comments \ 4 --jq '[.comments[] | select(.body | test("<!-- pr-review-bot -->") and test("合并冲突"))] | last | .createdAt // ""') 5 6LATEST_COMMIT_TIME=$(gh pr view $PR_NUMBER --json commits \ 7 --jq '.commits | last | .committedDate')
If LATEST_COMMIT_TIME > LAST_CONFLICT_COMMENT_TIME (author pushed new commits since the conflict comment):
bash1gh pr edit $PR_NUMBER --remove-label "bot:needs-rebase" --add-label "bot:reviewing"
Log: [pr-automation] PR #<PR_NUMBER> woke up from needs-rebase: new commits detected. Claiming as target.
Save this PR as target_pr and continue to Step 4 (treat it as a freshly claimed PR).
If no PRs were woken up: log [pr-automation] No eligible PR found this round. then log [pr-automation:exit] action=no_eligible_pr reason="all PRs skipped, no snoozed PRs woken up" and EXIT.
Step 3b — Handle bot:ready-to-fix PR
Taken when selected PR had bot:ready-to-fix (CONDITIONAL review already done in a previous session).
First: check for new commits since the review (author may have pushed fixes):
bash1LAST_REVIEW_TIME=$(gh pr view <PR_NUMBER> --json comments \ 2 --jq '[.comments[] | select(.body | startswith("<!-- pr-review-bot -->"))] | last | .createdAt // ""') 3 4LATEST_COMMIT_TIME=$(gh pr view <PR_NUMBER> --json commits \ 5 --jq '.commits | last | .committedDate')
If LATEST_COMMIT_TIME > LAST_REVIEW_TIME (author pushed new commits since review):
bash1gh pr edit <PR_NUMBER> --remove-label "bot:fixing"
Log: [pr-automation] PR #<PR_NUMBER> has new commits since review — re-queuing for fresh review.
Log: [pr-automation:exit] action=requeue pr=#<PR_NUMBER> reason="new commits since review"
EXIT. (PR re-enters normal queue with no bot: label → will be fully re-reviewed next round)
If no new commits, continue below.
Re-check CI (new commits may have been pushed since review):
bash1gh pr view <PR_NUMBER> --json statusCheckRollup \ 2 --jq '.statusCheckRollup[] | {name: .name, status: .status, conclusion: .conclusion}'
Required jobs: Code Quality, Unit Tests (ubuntu-latest), Unit Tests (macos-14), Unit Tests (windows-2022), Coverage Test, i18n-check
| Condition | Action |
|---|---|
| All required jobs SUCCESS | Continue to pr-fix below |
| Any job QUEUED or IN_PROGRESS | Remove bot:fixing → log "CI still running for PR #N" → EXIT |
| Any non-informational job FAILURE or CANCELLED (excl. codecov) | Remove bot:fixing → log "CI failed for PR #N, re-queueing" → EXIT |
Load the existing review report into the current session (pr-fix requires it to be present):
bash1gh pr view <PR_NUMBER> --json comments \ 2 --jq '.comments[] | select(.body | startswith("<!-- pr-review-bot -->")) | .body' \ 3 | tail -1
Output the fetched review report in the conversation so pr-fix can find it. If no review comment is found, abort:
bash1gh pr edit <PR_NUMBER> --remove-label "bot:fixing" --add-label "bot:needs-human-review"
Log: [pr-automation] PR #<PR_NUMBER> no review report found — cannot fix. Transferred to human review.
Log: [pr-automation:exit] action=needs_human pr=#<PR_NUMBER> reason="no review report found"
EXIT.
Run pr-fix:
/pr-fix <PR_NUMBER> --automation
After pr-fix completes, check if pr-fix already handled everything (fork fallback path):
bash1PR_STATE=$(gh pr view <PR_NUMBER> --json state --jq '.state')
If PR_STATE is CLOSED (pr-fix used fork fallback — closed the original PR and created a replacement):
Log: [pr-automation] PR #<PR_NUMBER> fork fallback handled by pr-fix — original closed, replacement PR created.
Log: [pr-automation:exit] action=fork_fallback pr=#<PR_NUMBER> reason="pr-fix closed original and created replacement PR"
EXIT.
Otherwise, post comment and mark ready to merge:
bash1gh pr edit <PR_NUMBER> --remove-label "bot:fixing" --add-label "bot:ready-to-merge" 2gh pr comment <PR_NUMBER> --body "<!-- pr-automation-bot --> 3✅ 已自动修复,代码无阻塞性问题,请人工确认后合并。"
Log: [pr-automation] PR #<PR_NUMBER> fix complete — marked bot:ready-to-merge.
Log: [pr-automation:exit] action=ready_to_merge pr=#<PR_NUMBER> reason="fix complete, needs human confirmation to merge"
EXIT.
Step 4 — Check CI Status
bash1gh pr view <PR_NUMBER> --json statusCheckRollup \ 2 --jq '.statusCheckRollup[] | {name: .name, status: .status, conclusion: .conclusion}'
Required jobs: Code Quality, Unit Tests (ubuntu-latest), Unit Tests (macos-14), Unit Tests (windows-2022), Coverage Test, i18n-check
| Condition | Action |
|---|---|
| All required jobs SUCCESS and no non-informational jobs FAILURE/CANCELLED | Continue to Step 4.5 |
| Any required job QUEUED or IN_PROGRESS | Remove bot:reviewing → log [pr-automation:skip] action=ci_running pr=#<PR_NUMBER> reason="CI still running" → find next PR |
statusCheckRollup empty (CI never triggered) | Approve workflow (see below) → remove bot:reviewing → EXIT |
Any non-informational job (required or not) FAILURE or CANCELLED (excl. codecov/*) | Check dedup (see below) → find next PR or post comment → EXIT |
Workflow approval (CI never triggered):
Use the PR's head commit SHA to precisely find action_required runs for this PR
(avoids missing fork PRs that gh run list may not return in default pagination):
bash1HEAD_SHA=$(gh pr view <PR_NUMBER> --json headRefOid --jq '.headRefOid') 2RUN_IDS=$(gh api "repos/$REPO/actions/runs?head_sha=$HEAD_SHA&status=action_required" \ 3 --jq '.workflow_runs[].id') 4for RUN_ID in $RUN_IDS; do 5 gh run approve "$RUN_ID" --repo "$REPO" 6done
Log: [pr-automation] Approved workflow runs for PR #<PR_NUMBER>.
Log: [pr-automation:exit] action=workflow_approved pr=#<PR_NUMBER> reason="CI not triggered, approved workflow runs"
Remove bot:reviewing:
bash1gh pr edit <PR_NUMBER> --remove-label "bot:reviewing"
EXIT.
CI failure dedup check:
bash1# Last CI failure bot comment time 2LAST_CI_COMMENT_TIME=$(gh pr view <PR_NUMBER> --json comments \ 3 --jq '[.comments[] | select(.body | test("<!-- pr-review-bot -->") and test("CI 检查未通过"))] | last | .createdAt // ""') 4 5# Latest commit time 6LATEST_COMMIT_TIME=$(gh pr view <PR_NUMBER> --json commits \ 7 --jq '.commits | last | .committedDate')
-
If
LAST_CI_COMMENT_TIMEis non-empty ANDLATEST_COMMIT_TIME <= LAST_CI_COMMENT_TIME: No new commits since last CI failure comment — swap labels and find next PR:bash1gh pr edit <PR_NUMBER> --remove-label "bot:reviewing" --add-label "bot:ci-waiting"Log
[pr-automation:skip] action=ci_failure_dedup pr=#<PR_NUMBER> reason="CI failed, no new commits since last comment"→ find next PR -
Otherwise: post CI failure comment below → log
[pr-automation:exit] action=ci_failed pr=#<PR_NUMBER> reason="CI failure, commented"→ removebot:reviewing→ EXIT
CI failure comment:
bash1gh pr comment <PR_NUMBER> --body "<!-- pr-review-bot --> 2 3## CI 检查未通过 4 5以下 job 在本次自动化 review 时未通过,请修复: 6 7| Job | 结论 | 8|-----|------| 9| <失败的 job 名称> | ❌ <FAILURE 或 CANCELLED> | 10 11本次自动化 review 暂缓,待 CI 全部通过后将重新处理。"
Step 4.5 — Resolve Merge Conflicts
bash1gh pr view <PR_NUMBER> --json mergeable,mergeStateStatus,headRefName,baseRefName \ 2 --jq '{mergeable, mergeStateStatus, head: .headRefName, base: .baseRefName}'
mergeable | mergeStateStatus | Action |
|---|---|---|
MERGEABLE | any | Continue to Step 5 |
UNKNOWN | any | Remove bot:reviewing → log [pr-automation:skip] action=merge_unknown pr=#<PR_NUMBER> reason="mergeability unknown, will retry" → find next PR |
CONFLICTING | any | Run conflict dedup check (see below) |
Merge conflict dedup check:
bash1# Last conflict bot comment time 2LAST_CONFLICT_COMMENT_TIME=$(gh pr view <PR_NUMBER> --json comments \ 3 --jq '[.comments[] | select(.body | test("<!-- pr-review-bot -->") and test("合并冲突"))] | last | .createdAt // ""') 4 5LATEST_COMMIT_TIME=$(gh pr view <PR_NUMBER> --json commits \ 6 --jq '.commits | last | .committedDate')
-
If
LAST_CONFLICT_COMMENT_TIMEis non-empty ANDLATEST_COMMIT_TIME <= LAST_CONFLICT_COMMENT_TIME: No new commits — removebot:reviewing→ log[pr-automation:skip] action=conflict_dedup pr=#<PR_NUMBER> reason="conflict already notified, no new commits"→ find next PR (no new action) -
Otherwise: attempt auto-rebase below.
Auto-rebase attempt (in worktree):
bash1REPO_ROOT=$(git rev-parse --show-toplevel) 2WORKTREE_DIR="/tmp/aionui-pr-${PR_NUMBER}" 3 4# Clean up any stale worktree 5git worktree remove "$WORKTREE_DIR" --force 2>/dev/null || true 6 7# Create worktree in detached HEAD mode (no local branch created) 8git fetch origin <head_branch> 9git fetch origin <base_branch> 10git worktree add "$WORKTREE_DIR" origin/<head_branch> --detach 11 12# Symlink node_modules so tsc/lint can run in the worktree 13ln -s "$REPO_ROOT/node_modules" "$WORKTREE_DIR/node_modules" 14 15cd "$WORKTREE_DIR" 16git rebase origin/<base_branch>
If rebase succeeds, run quality check:
bash1cd "$WORKTREE_DIR" 2bunx tsc --noEmit 3bun run lint:fix
If quality check passes:
bash1cd "$WORKTREE_DIR" 2git push --force-with-lease origin HEAD:<head_branch> 3cd "$REPO_ROOT" 4git worktree remove "$WORKTREE_DIR" --force 2>/dev/null || true 5gh pr edit <PR_NUMBER> --remove-label "bot:reviewing"
Log: [pr-automation] Resolved merge conflicts for PR #<PR_NUMBER>, pushed rebase.
EXIT (CI re-triggers automatically).
Fallback — if rebase fails OR quality check fails:
bash1cd "$REPO_ROOT" 2git worktree remove "$WORKTREE_DIR" --force 2>/dev/null || true
Post comment:
bash1gh pr comment <PR_NUMBER> --body "<!-- pr-review-bot --> 2 3## 合并冲突(无法自动解决) 4 5本 PR 与目标分支存在冲突,自动 rebase 未能干净解决。请手动 rebase 后重新 push: 6 7\`\`\`bash 8git fetch origin 9git rebase origin/<base_branch> 10# 解决冲突后 11git push --force-with-lease 12\`\`\`"
bash1gh pr edit <PR_NUMBER> --remove-label "bot:reviewing" --add-label "bot:needs-rebase"
Log: [pr-automation:exit] action=conflict_unresolved pr=#<PR_NUMBER> reason="merge conflict, needs human rebase"
EXIT.
Step 5 — Assess PR Scale and Critical Path
No checkout needed — use remote refs to check the diff:
bash1git fetch origin pull/${PR_NUMBER}/head 2BASE_REF=$(gh pr view <PR_NUMBER> --json baseRefName --jq '.baseRefName') 3git fetch origin "$BASE_REF" 4 5FILES_CHANGED=$(git diff origin/${BASE_REF}...FETCH_HEAD --name-only | wc -l | tr -d ' ') 6 7# CRITICAL_PATH_PATTERN: defined in Configuration section above 8CRITICAL_FILES="" 9if [ -n "$CRITICAL_PATH_PATTERN" ]; then 10 CRITICAL_FILES=$(git diff origin/${BASE_REF}...FETCH_HEAD --name-only \ 11 | grep -E "$CRITICAL_PATH_PATTERN") 12 [ -n "$CRITICAL_FILES" ] && HAS_CRITICAL=true || HAS_CRITICAL=false 13else 14 HAS_CRITICAL=false 15fi
Save FILES_CHANGED, HAS_CRITICAL, and CRITICAL_FILES for later steps.
Step 6 — Run pr-review (automation mode)
Before running a new review, check if a valid cached review already exists:
bash1LAST_REVIEW_TIME=$(gh pr view <PR_NUMBER> --json comments \ 2 --jq '[.comments[] | select(.body | startswith("<!-- pr-review-bot -->"))] | last | .createdAt // ""') 3 4# Exclude update-branch merge commits — these are automatically generated by GitHub 5# when the PR branch is synced with base (e.g. via the update-branch API), and do 6# not represent new author code changes that would invalidate the cached review. 7# Such commits always have a messageHeadline of the form: 8# "Merge branch '<base>' into <head>" 9BASE_REF=$(gh pr view <PR_NUMBER> --json baseRefName --jq '.baseRefName') 10LATEST_COMMIT_TIME=$(gh pr view <PR_NUMBER> --json commits | \ 11 jq --arg base "$BASE_REF" \ 12 '.commits | map(select(.messageHeadline | test("^Merge branch '\''" + $base + "'\'' into ") | not)) | last | .committedDate // (.commits | last | .committedDate)')
If LAST_REVIEW_TIME is non-empty AND LATEST_COMMIT_TIME <= LAST_REVIEW_TIME:
The existing review is still valid (no new commits since it was posted). Load the cached conclusion from the existing comment:
bash1gh pr view <PR_NUMBER> --json comments \ 2 --jq '[.comments[] | select(.body | startswith("<!-- pr-review-bot -->"))] | last | .body'
Parse the <!-- automation-result --> block from the cached comment. Set CONCLUSION, IS_CRITICAL_PATH, and CRITICAL_PATH_FILES from it, then skip to Step 7 (do not run pr-review again).
Log: [pr-automation] PR #<PR_NUMBER> has valid cached review (no new commits since review) — skipping re-review.
Otherwise (no existing review, or new commits have been pushed since the last review): run a fresh review:
/pr-review <PR_NUMBER> --automation
After pr-review completes, parse the <!-- automation-result --> block:
<!-- automation-result -->
CONCLUSION: APPROVED | CONDITIONAL | REJECTED | CI_FAILED | CI_NOT_READY
IS_CRITICAL_PATH: true | false
CRITICAL_PATH_FILES:
- file1
- file2
PR_NUMBER: <number>
<!-- /automation-result -->
When IS_CRITICAL_PATH is false, CRITICAL_PATH_FILES is (none).
Save CONCLUSION, IS_CRITICAL_PATH, and CRITICAL_PATH_FILES (override Step 5 values if different).
If block is missing: set CONCLUSION=REJECTED, log the error, continue to Step 7.
Step 7 — Execute Decision Matrix
CONCLUSION = APPROVED
-
Post comment:
When
IS_CRITICAL_PATH=true, include the matched files in the comment:bash1# Build critical path file list for the comment 2if [ -n "$CRITICAL_FILES" ]; then 3 CRITICAL_LIST=$(echo "$CRITICAL_FILES" | sed 's/^/ - `/' | sed 's/$/`/') 4 CRITICAL_SECTION=" 5> 📂 **命中核心路径的文件:** 6${CRITICAL_LIST}" 7else 8 CRITICAL_SECTION="" 9fi 10 11gh pr comment <PR_NUMBER> --body "<!-- pr-automation-bot --> 12✅ 已自动 review,代码无阻塞性问题,请人工确认后合并。${CRITICAL_SECTION}" -
Update labels:
bash1gh pr edit <PR_NUMBER> --remove-label "bot:reviewing" --add-label "bot:ready-to-merge" -
Log:
[pr-automation] PR #<PR_NUMBER> approved, marked bot:ready-to-merge. -
Log:
[pr-automation:exit] action=ready_to_merge pr=#<PR_NUMBER> reason="review passed, needs human confirmation to merge" -
EXIT.
CONCLUSION = CONDITIONAL
- Update labels (defer pr-fix to next session):
bash
1gh pr edit <PR_NUMBER> --remove-label "bot:reviewing" --add-label "bot:ready-to-fix" - Log:
[pr-automation] PR #<PR_NUMBER> CONDITIONAL — marked bot:ready-to-fix for next session. - Log:
[pr-automation:exit] action=conditional pr=#<PR_NUMBER> reason="review conditional, deferred fix to next session" - EXIT.
CONCLUSION = REJECTED
- Post comment:
bash
1gh pr comment <PR_NUMBER> --body "<!-- pr-automation-bot --> 2❌ 本 PR 存在阻塞性问题,无法自动处理,已转交人工 review。详见上方 review 报告。" - Update labels:
bash
1gh pr edit <PR_NUMBER> --remove-label "bot:reviewing" --add-label "bot:needs-human-review" - Log:
[pr-automation] PR #<PR_NUMBER> rejected, transferred to human review. - Log:
[pr-automation:exit] action=rejected pr=#<PR_NUMBER> reason="blocking issues, transferred to human review" - EXIT.
CONCLUSION = CI_FAILED or CI_NOT_READY
Safety fallback (Step 4 should have caught these):
- Remove
bot:reviewing:bash1gh pr edit <PR_NUMBER> --remove-label "bot:reviewing" - Log:
[pr-automation] PR #<PR_NUMBER> CI not ready at pr-review stage. Skipping. - Log:
[pr-automation:exit] action=ci_not_ready pr=#<PR_NUMBER> reason="CI not ready at review stage" - EXIT.
Mandatory Rules
- Single heavy action per session — review OR fix, then EXIT
- bot:reviewing / bot:fixing are mutexes — always set immediately when claiming a PR
- Clean up on skip — whenever skipping a PR mid-flow, always remove
bot:reviewingfirst - No AI signature — no
Co-Authored-By, noGenerated within any comment or commit - Label atomicity — when swapping labels, do both in a single
gh pr editcall - Comment dedup — always check for existing bot comment before posting CI failure or conflict comments
FAQ & Installation Steps
These questions and steps mirror the structured data on this page for better search understanding.
? Frequently Asked Questions
What is pr-automation?
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
How do I install pr-automation?
Run the command: npx killer-skills add iOfficeAI/AionUi/pr-automation. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.
Which IDEs are compatible with pr-automation?
This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.
↓ How To Install
-
1. Open your terminal
Open the terminal or command line in your project directory.
-
2. Run the install command
Run: npx killer-skills add iOfficeAI/AionUi/pr-automation. The CLI will automatically detect your IDE or AI agent and configure the skill.
-
3. Start using the skill
The skill is now active. Your AI agent can use pr-automation immediately in the current project.