Agent Native

github-review-iteration

Orchestrates an iterative GitHub PR review loop by delegating triage and implementation to sub-agents, then repeating until all actionable review items are…

by PrismaOfficial publisherNot reviewed

Identity proven by GitHub's verified organisation badge (prisma)

Agents
Claude Code
License
Apache-2.0 (permissive)
Pin
55458c4pinned Oct 9, 2026
Context cost
about 1,900 tokenswhen the skill loads
GitHub stars
415on prisma/prisma-next
Scripts
1 script

What it does

“Orchestrates a GitHub PR review loop by delegating triage and implementation to dedicated sub-agents, then repeating until actionable review items are cleared. Use when the user says “address PR review”, “triage review comments”, or “iterate until review is clean”.”
The author's description, from SKILL.md

Generated summary from the skill's own text

Orchestrates an iterative GitHub PR review loop by delegating triage and implementation to sub-agents, then repeating until all actionable review items are resolved. The skill fetches PR state, triages comments into actions, executes fixes with explicit commits, and re-fetches until the review is clean.

When to use it

  • User asks to address PR review comments or triage review items
  • Need to iterate through multiple review rounds automatically
  • PR has mixed or bundled comments requiring structured action planning

When not to

  • Single manual review comment reply needed without iteration
  • Review comments are out-of-scope or informational only
  • Sub-agents for triage or implementation are not available

Install

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add prisma/prisma-next --skill github-review-iteration

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install prisma/prisma-next github-review-iteration@55458c441d2cf452028c22eed21370447720840a

Installs the commit we checked (55458c4).

Copy by hand

Download the folder at 55458c4 and put it in .claude/skills/github-review-iteration for Claude Code and in .agents/skills/github-review-iteration for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at 55458c4

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "github-review-iteration" by Prisma.

Source, pinned to commit 55458c441d2cf452028c22eed21370447720840a:
https://github.com/prisma/prisma-next/tree/55458c441d2cf452028c22eed21370447720840a/skills-contrib/github-review-iteration

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/github-review-iteration/ for Claude Code and .agents/skills/github-review-iteration/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Listing and checks: https://www.agentnative.dev/skills/prisma/github-review-iteration

SKILL.md at the pin

---
name: github-review-iteration
description: Orchestrates a GitHub PR review loop by delegating triage and implementation to dedicated sub-agents, then repeating until actionable review items are cleared. Use when the user says “address PR review”, “triage review comments”, or “iterate until review is clean”.
argument-hint: "[triage|implement|iterate] [pr-url] [output-dir]"
---

# GitHub Review Iteration

Run an iterative PR review loop: **fetch state → render/summarize → triage actions → implement (code + Done + resolve) → re-fetch** until the PR has no remaining actionable items.

This skill is an **orchestrator**. It delegates:

- triage to `../review-triage-phase/agents/review-triager.md`
- implementation to `../review-implement-phase/agents/review-implementer.md`

The orchestrator owns sequencing, handoff, and loop control. It does not perform triage or implementation directly when delegation is available.

## Locating sibling skills and scripts

This skill depends on three sibling skills that live **in the same parent directory**:

- `../review-fetch-phase/` — fetches and renders PR review state
- `../review-triage-phase/` — triages review threads into an action plan
- `../review-implement-phase/` — implements triaged actions and resolves threads

All script paths in this document are **relative to this skill's directory**. Use `../` to reach sibling skills. Do **not** search the workspace/repo for these files — they are part of the skills installation, not the project being reviewed.

## Usage

This skill supports subcommands:
- `triage`: fetch + triage into structured actions
- `implement`: execute the triaged actions and update status
- `iterate`: loop `triage` → `implement` until clear (default)

```text
/github-review-iteration iterate <PR_URL> [output-dir]
```

When `output-dir` is omitted, use the standard layout: `wip/reviews/<owner>_<repo>_pr-<number>/` (derived from PR URL).

Example:

```text
/github-review-iteration iterate https://github.com/OWNER/REPO/pull/123
```

## Files written (deterministic layout)

Store artifacts under:

`wip/reviews/<owner>_<repo>_pr-<number>/`

Canonical artifacts:

- `review-state.json` (canonical v2)
- `review-actions.json` (canonical v2)

Derived artifacts:

- `review-state.md`
- `summary.txt` (or JSON summary)
- `review-actions.md`
- `apply-log.json` (optional)

When you need a thin wrapper for path setup + standard script calls, run:

```bash
node ./scripts/review-iterate.mjs --pr <PR_URL>
```

For phase-specific execution without full orchestration, use:

- `/review-fetch-phase <PR_URL> [output-dir]`
- `/review-triage-phase <PR_URL> [output-dir]`
- `/review-implement-phase <PR_URL> [output-dir]`

## Behavioral rules

- **WILL ADDRESS** items:
  - reply + 👍
  - leave unresolved until fixed
- **Not addressed in this PR** items:
  - reply with rationale + 👎
  - resolve the thread
- **Implementation**:
  - granular, intent-driven commits
  - explicit staging only (never `git add -A` / `git add .`)
  - reply “Done” and resolve when complete

## Operational reliability notes (Cursor)

### `gh api` TLS / cert failures in sandboxed shells

If GitHub administration fails with an error like:

- `x509: OSStatus -26276` (or similar TLS/certificate verification failures)

Treat it as an **environment/sandbox cert-store mismatch**, not a script bug.

Recovery:

- Re-run the affected `gh` calls **outside** the sandbox (use a shell mode that uses the system cert store).
- Do **not** disable TLS verification (no `GH_NO_VERIFY_SSL`, no custom curl flags).
- After re-running, continue the loop normally (fetch → triage → implement → resolve → repeat).

### JSON-first deterministic commands

All script paths below are relative to this skill's directory.

1. Fetch canonical JSON:

```bash
node ../review-fetch-phase/scripts/fetch-review-state.mjs --pr <PR_URL> --out-json <review-dir>/review-state.json
```

2. Render and summarize from JSON (pure scripts):

```bash
node ../review-fetch-phase/scripts/render-review-state.mjs --in <review-dir>/review-state.json --out <review-dir>/review-state.md
node ../review-fetch-phase/scripts/summarize-review-state.mjs --in <review-dir>/review-state.json --format text --out <review-dir>/summary.txt
```

3. Render triage plan from canonical actions JSON:

```bash
node ../review-triage-phase/scripts/render-review-actions.mjs --in <review-dir>/review-actions.json --out <review-dir>/review-actions.md
```

## Data exchange format (triager → implementer)

`review-actions.json` is the contract between the triager and implementer.

Minimum v2 shape:

```json
{
  "version": 2,
  "pr": { "url": "https://github.com/OWNER/REPO/pull/123", "nodeId": "PR_kw..." },
  "reviewState": { "path": "review-state.json", "fetchedAt": "...", "version": 2 },
  "actions": [
    {
      "actionId": "A-001",
      "target": { "kind": "review_thread", "nodeId": "PRRT_xxx", "url": "..." },
      "decision": "will_address",
      "summary": "One-line description of what will be done",
      "rationale": null,
      "targetFiles": ["path/to/file.ts"],
      "acceptance": "How to tell it's done",
      "status": "pending",
      "done": null
    }
  ]
}
```

Rules:

- Use **node ids only** for targets (`target.nodeId`).
- Preserve `actions[]` order intentionally (do not reorder).
- Implementer updates `status` (`pending|in_progress|done`) and `done` records in place.
- **Compound targets**: A single `pull_request_review` body may contain multiple findings (especially from automated reviewers like CodeRabbit which bundle "outside diff range" comments into the review body). The triager must decompose these into sub-actions (e.g., `A02a`, `A02b`). Never blanket-dismiss review bodies without reading their content.

## Procedure

### `triage`

1. **Delegate to triage sub-agent**

Invoke the review triager agent at `../review-triage-phase/agents/review-triager.md` and pass:

- PR URL
- output paths:
  - `<output-dir>/review-state.md`
  - `<output-dir>/review-state.json`
  - `<output-dir>/review-actions.md`
  - `<output-dir>/review-actions.json`
- optional scope constraints

2. **Require triage outputs**

The triager must:

- fetch review state (via `../review-fetch-phase/scripts/fetch-review-state.mjs`)
- triage review threads into `review-actions.json` decisions/status
- write/update `review-actions.md` and `review-actions.json`

3. **Validate handoff contract**

Before returning from `triage`, verify that `<output-dir>/review-actions.json` exists and is valid for implementer consumption (`version`, PR metadata, and `actions[]` with `target.kind` + `target.nodeId`).

### `implement`

1. **Delegate to implementation sub-agent**

Invoke the review implementer agent at `../review-implement-phase/agents/review-implementer.md` and pass:

- PR URL
- `<output-dir>/review-actions.md`
- `<output-dir>/review-actions.json`
- optional scope constraints

2. **Require implementation outputs**

The implementer must:

- work through pending `will_address` actions
- make focused, explicit-staging commits
- run smallest relevant checks per action
- reply "On it" when starting, then "Done" and resolve the thread when complete
- update `review-actions.json` in-place (`status`, `done`)
- re-fetch review state at the end to verify remaining actionable items

Responsibility note:
- Posting "Done" and resolving completed threads belongs to the implementer phase and is part of marking actions done.

### `iterate`

Repeat delegated `triage` → delegated `implement` until there are no remaining actionable review items.

Loop contract:

1. Run `triage` delegation and read resulting `review-actions.json`.
2. Inspect `review-actions.json`; if no `will_address` actions remain with `pending` or `in_progress` status, stop and report completion.
3. Run `implement` delegation.
4. Re-run `triage` delegation to refresh state and determine next iteration.
5. Continue until clear.

## Optional shortcuts (repo-specific)

If this repo provides dedicated slash commands or subagents for triage/implementation, prefer them to reduce manual steps.

From prisma/prisma-next at 55458c4, shown as plain text under its license: Apache-2.0 (permissive). The license text is in LICENSE.

View SKILL.md on GitHub at 55458c4

Files

4 files, 15 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at 55458c4
All 44 skills from Prisma

More from Prisma

  • prisma-8

    This skill helps agents work with Prisma 8, a contract-first data layer for TypeScript projects.

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 3.5K tokens · pinned 6 days ago

  • adr-review

    This skill reviews Architecture Decision Records (ADRs) from a fresh perspective, identifying clarity and structural issues, then rewrites them for future…

    Claude Code, Codex, Cursor +4 · about 590 tokens · pinned 6 days ago

  • ast-visitor-pattern

    This skill teaches agents to use the visitor pattern with frozen subclasses for discriminated unions that need multiple dispatch sites.

    Claude Code, Codex, Cursor +4 · about 710 tokens · pinned 6 days ago

  • bumping-biome

    Updates the biome code formatter package to a specified version using pnpm, renames configuration files to biome.jsonc format, updates schema references, and…

    Claude Code, Codex, Cursor +4 · about 290 tokens · pinned 6 days ago

  • contrib-pr

    This skill guides external contributors through opening a pull request against prisma-next by following the project's contribution guidelines.

    Claude Code, Codex, Cursor +4 · about 2.2K tokens · pinned 6 days ago

  • create-pr

    This skill creates a GitHub pull request with a Linear-ticket-prefixed title and a decision-led narrative description for the prisma-next repository.

    Claude Code, Codex, Cursor +4 · about 4.3K tokens · pinned 6 days ago

All Coding workflow skills
  • maintainer-review

    This skill helps maintainers assess GitHub issues and PRs by evaluating whether claimed problems are real, whether existing features already solve them, and…

    by OpenAIOfficial publisher

    Claude Code, Codex, Cursor +4 · about 8.9K tokens · pinned 6 days ago

  • maintainer-review

    Evaluates GitHub issues and PRs through a systematic desk review to assess demonstrated need, existing workarounds, design correctness, and maintainer impact.

    by OpenAIOfficial publisher

    Claude Code, Codex, Cursor +4 · about 8.3K tokens · pinned 6 days ago

  • dd-file-issue

    This skill helps file GitHub issues to the DataDog/pup repository for bugs, feature requests, and documentation problems related to the pup CLI, agents, and…

    by DatadogOfficial publisher

    Claude Code, Codex, Cursor +3 · about 2.2K tokens · pinned 6 days ago

  • prisma-next-feedback

    Routes bug reports, feature requests, and team Q&A to the appropriate Prisma Next channel.

    by PrismaOfficial publisher

    Claude Code, Codex, Cursor +4 · about 4.2K tokens · pinned 6 days ago

  • github-code

    This skill enables agents to interact with GitHub repositories using git and gh commands for implementation, code investigation, branching, pull request…

    by SentryOfficial publisher

    Claude Code, Codex, Cursor +4 · about 580 tokens · pinned 6 days ago

  • github-headless-pr-fixture

    This skill provides a local Git repository fixture for working on GitHub pull request getsentry/junior#691.

    by SentryOfficial publisher

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 140 tokens · pinned 6 days ago

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use