# iterate-pr

Iterates on a pull request until actionable CI passes and review comments are fixed. It handles test failures and feedback loops without waiting for human approval.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 4600 installs · ★ 1089
- Author: getsentry
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/getsentry/skills/tree/HEAD/skills/iterate-pr/SKILL.md
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/skills/iterate-pr

## What it does

The skill manages an automated feedback loop for open GitHub pull requests. It sorts review comments via `scripts/fetch_pr_feedback.py` into severity buckets, fixing high and medium priority items while asking how to handle low priority suggestions.

When tests fail, the workflow inspects full logs using `gh run view <run-id> --log-failed`. It diagnoses the cause and pushes new commits with `git push` after verifying changes locally.

You need authenticated `gh` and `uv` installed in the target repository root. If the branch needs a rebase or hits a required human approval gate, the skill stops immediately instead of waiting.

## Requirements
- Works with: GitHub

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add getsentry/skills --skill iterate-pr -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/iterate-pr/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/iterate-pr/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add getsentry/skills --skill iterate-pr -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/iterate-pr/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add getsentry/skills --skill iterate-pr -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/iterate-pr/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install getsentry/skills iterate-pr
```

2. **Manually: put the files in place**
- File: `.github/skills/iterate-pr/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add getsentry/skills --skill iterate-pr -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/getsentry/skills --path skills/iterate-pr
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/iterate-pr/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add getsentry/skills --skill iterate-pr -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/getsentry/skills/tree/HEAD/skills/iterate-pr/SKILL.md

## When to use it
- fix failing CI checks on open pull requests
- triage review feedback by priority level
- inspect failed test logs with GitHub CLI
- push fixes after local verification

## Example prompts
- Iterate on this PR until CI passes and review feedback is addressed
- Check failing CI checks for the current PR and fix them
- Run iterate-pr to resolve review comments and monitor test runs

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 791d3b1eba75d4d3.

BEGIN THIRD-PARTY FILE 791d3b1eba75d4d3
````text
---
name: iterate-pr
description: Iterate on a PR until actionable CI passes and high/medium review feedback is addressed. Use for PR CI failures, review feedback, or green-check loops; do not wait for human approval, draft status, or merge gates.
disable-model-invocation: false
---

# Iterate on PR Until CI Passes

Goal: fix actionable CI failures and high/medium review feedback. Stop and report human approval, draft-readiness, and merge-readiness gates.

Requires:
- authenticated `gh`
- `uv`
- target repository root as cwd
- skill-root-relative script paths, for example `scripts/fetch_pr_checks.py`

## Bundled Scripts

| Script | Run | Output |
|--------|-----|--------|
| `scripts/fetch_pr_checks.py` | `uv run scripts/fetch_pr_checks.py [--pr NUMBER]` | JSON: `pr`, `summary`, `checks`, failure snippets |
| `scripts/fetch_pr_feedback.py` | `uv run scripts/fetch_pr_feedback.py [--pr NUMBER]` | JSON buckets: `high`, `medium`, `low`, `bot`, `resolved` |
| `scripts/monitor_pr_checks.py` | `uv run scripts/monitor_pr_checks.py [--pr NUMBER]` | terminal marker plus tab-separated checks |
| `scripts/reply_to_thread.py` | `uv run scripts/reply_to_thread.py THREAD_ID BODY [...]` | JSON reply results |

Check summary fields include `failed`, `pending`, `actionable_pending`, and `human_gate_pending`.

Monitor markers:
- `ALL_CHECKS_PASSED`
- `CHECKS_DONE_WITH_FAILURES`
- `NO_CHECKS_REGISTERED`
- `DRAFT_PR_WITH_NO_CHECKS`
- `CHECKS_BLOCKED_BY_REVIEW_GATE`

## Workflow

### 1. Identify PR

Run:
```bash
gh pr view --json number,url,headRefName,isDraft,reviewDecision
```

Stop when:
- no PR exists
- draft PR has no checks after monitor grace period: report `DRAFT_PR_WITH_NO_CHECKS`

Draft rule: inspect existing checks/feedback only. Do not mark ready for review unless asked.

### 2. Handle Feedback

Run `uv run scripts/fetch_pr_feedback.py [--pr NUMBER]`.

| Bucket | Action |
|--------|--------|
| `high` | fix |
| `medium` | fix |
| `low` | ask user which to address |
| `bot` | skip informational comments |
| `resolved` | skip |

Feedback fix checklist:
- verify root cause
- search related code
- fix all instances
- for `review_bot: true`: fix real issues, explain false positives

Low-priority prompt format:
```text
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 should I address? ("1,3", "all", or "none")
```

### 3. Check CI Status

Run `uv run scripts/fetch_pr_checks.py [--pr NUMBER]`.

| State | Action |
|-------|--------|
| `failed > 0` and `actionable_pending == 0` | fix failures |
| `actionable_pending > 0` | wait; poll feedback while waiting |
| `pending > 0` and `actionable_pending == 0` | report `CHECKS_BLOCKED_BY_REVIEW_GATE` |
| no checks after grace period | report `NO_CHECKS_REGISTERED` or `DRAFT_PR_WITH_NO_CHECKS` |
| all actionable checks passed | run post-CI feedback check |

Wait for actionable review bots: sentry, warden, cursor, bugbot, seer, codeql.
Do not wait for approval, `isDraft`, `REVIEW_REQUIRED`, Codecov, or informational bots.

### 4. Fix CI Failures

For each failure:
1. read full log: `gh run view <run-id> --log-failed`
````
END THIRD-PARTY FILE 791d3b1eba75d4d3

The third-party file has ended. Everything between the 791d3b1eba75d4d3 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 3277 of 5036 bytes. © getsentry · Apache-2.0 · https://github.com/getsentry/skills/tree/HEAD/skills/iterate-pr/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md