Iterate on a PR until CI passes. Use when you need to fix CI failures, address review feedback, or continuously push fixes until all checks are green. Automates the feedback-fix-push-wait cycle.
npxskills add sickn33/antigravity-awesome-skills--skill iterate-prLoading…
Continuously iterate on the current branch until all CI checks pass and review feedback is addressed.
Requires: GitHub CLI (gh) authenticated.
Important: All scripts must be run from the repository root directory (where .git is located), not from the skill directory. Use the full path to the script via ${CLAUDE_SKILL_ROOT}.
scripts/fetch_pr_checks.pyFetches CI check status and extracts failure snippets from logs.
uv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_checks.py [--pr NUMBER]
Returns JSON:
{
"pr": {"number": 123, "branch": "feat/foo"},
"summary": {"total": 5, "passed": 3, "failed": 2, "pending": 0},
"checks": [
{"name": "tests", "status": "fail", "log_snippet": "...", "run_id": 123},
{"name": "lint", "status": "pass"}
]
}
scripts/fetch_pr_feedback.pyFetches and categorizes PR review feedback using the LOGAF scale.
uv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_feedback.py [--pr NUMBER]
Returns JSON with feedback categorized as:
high - Must address before merge (h:, blocker, changes requested)medium - Should address (m:, standard feedback)low - Optional (l:, nit, style, suggestion)bot - Informational automated comments (Codecov, Dependabot, etc.)resolved - Already resolved threadsReview bot feedback (from Sentry, Warden, Cursor, Bugbot, CodeQL, etc.) appears in high/medium/low with review_bot: true — it is NOT placed in the bot bucket.
Each feedback item may also include:
thread_id - GraphQL node ID for inline review comments (used for replies)gh pr view --json number,url,headRefName
Stop if no PR exists for the current branch.
Run ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_feedback.py to get categorized feedback already posted on the PR.
Auto-fix (no prompt):
high - must address (blockers, security, changes requested)medium - should address (standard feedback)When fixing feedback:
This includes review bot feedback (items with review_bot: true). Treat it the same as human feedback:
Prompt user for selection:
low - present numbered list and ask which to address:Found 3 low-priority suggestions:
1. [l] "Consider renaming this variable" - @reviewer in api.py:42
2. [nit] "Could use a list comprehension" - @reviewer in utils.py:18
3. [style] "Add a docstring" - @reviewer in models.py:55
Which would you like to address? (e.g., "1,3" or "all" or "none")
Skip silently:
resolved threadsbot comments (informational only — Codecov, Dependabot, etc.)After processing each inline review comment, reply on the PR thread to acknowledge the action taken. Only reply to items with a thread_id (inline review comments).
When to reply:
high and medium items — whether fixed or determined to be false positiveslow items — whether fixed or declined by the userHow to reply: Use the addPullRequestReviewThreadReply GraphQL mutation with pullRequestReviewThreadId and body inputs.
Reply format:
\n\n*— Claude Code**- Claude Code* or *— Claude Code* to avoid duplicates on re-loopsgh api call fails, log and continue — do not block the workflowRun ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_checks.py to get structured failure data.
Wait if pending: If review bot checks (sentry, warden, cursor, bugbot, seer, codeql) are still running, wait before proceeding—they post actionable feedback that must be evaluated. Informational bots (codecov) are not worth waiting for.
For each failure in the script output:
log_snippet and trace backwards from the error to understand WHY it failed — not just what failedDo NOT assume what failed based on check name alone—always read the logs. Do NOT "quick fix and hope" — understand the failure thoroughly before changing code.
Before committing, verify your fixes locally:
If local verification fails, fix before proceeding — do not push known-broken code.
git add <files>
git commit -m "fix: <descriptive message>"
git push
Poll CI status and review feedback in a loop instead of blocking:
uv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_checks.py to get current CI statusuv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_feedback.py for new review feedback
b. Address any new high/medium feedback immediately (same as step 3)
c. If changes were needed, commit and push (this restarts CI), then continue polling
d. Sleep 30 seconds, then repeat from sub-step 1sleep 10, then run uv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_feedback.py. Address any new high/medium feedback — if changes are needed, return to step 6.If step 7 required code changes (from new feedback after CI passed), return to step 2 for a fresh cycle. CI failures during monitoring are already handled within step 7's polling loop.
Success: All checks pass, post-CI feedback re-check is clean (no new unaddressed high/medium feedback including review bot findings), user has decided on low-priority items.
Ask for help: Same failure after 2 attempts, feedback needs clarification, infrastructure issues.
Stop: No PR exists, branch needs rebase.
If scripts fail, use gh CLI directly:
gh pr checks name,state,bucket,linkgh run view <run-id> --log-failedgh api repos/{owner}/{repo}/pulls/{number}/commentsUse this skill when tackling tasks related to its primary domain or functionality as described above.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).