Skip to content

xpepper/pr-review-agent-skill / pr-review-grill

pr-review-grill

Verified

Use when addressing open pull-request review comments and the user wants to discuss, challenge, and decide each comment one at a time, applying the decisions in one batch at the end or as each one is made. Trigger for requests to grill review feedback, walk through comments individually, debate whether comments are valid, or work through PR feedback collaboratively. Do not use this skill for fast batch triage; use pr-review-loop instead.

FileKindSize
README.mdmarkdown1.6 KB
SKILL.mdskill md16.4 KB
references/triage-guide.mdmarkdown2.8 KB
references/triage-state.mdmarkdown1.7 KB

references/triage-state.md

View on GitHub
# Triage State

The state file is `.pr-review/triage.json` at the repository root. Keep it
gitignored and local to the review session.

Example:

```json
{
  "version": 1,
  "phase": "discussion",
  "mode": "batch",
  "pr": {
    "owner": "org",
    "repo": "repository",
    "number": 42,
    "base": "master",
    "head": "feature/example"
  },
  "current_item": 1,
  "final_approval": false,
  "items": [
    {
      "key": "review-thread:PRRT_example",
      "type": "review-thread",
      "thread_id": "PRRT_example",
      "comment_ids": [123456],
      "author": "reviewer",
      "path": "src/example.rs",
      "line": 42,
      "body": "Review feedback",
      "group_key": null,
      "status": "decided",
      "classification": "PARK",
      "decision": "defer for team API discussion",
      "rationale": "The concern is valid, but changing the public scalar requires a team decision.",
      "implementation_notes": "Do not change code in this PR.",
      "remote_action": "leave-open"
    }
  ]
}
```

## Allowed values

`mode`:

- `batch`
- `apply-as-decided`

`phase`:

- `preflight`
- `collection`
- `discussion`
- `approval`
- `processing`
- `summary`
- `complete`

Item `status`:

- `pending`
- `discussing`
- `decided`
- `processing`
- `processed`
- `parked`
- `awaiting-clarification`

`remote_action` should describe intent, not claim success. Examples:

- `reply-and-resolve`
- `reply-and-leave-open`
- `leave-open`
- `none`

After a remote action, add verification fields such as:

```json
{
  "reply_id": 987654,
  "reply_verified": true,
  "thread_resolved": true,
  "commit": "abc1234",
  "pushed": true
}
```

Never store tokens, credentials, or secrets in this file.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall