Review Fetch Phase Agent Skill

Fetches canonical PR review state and renders derived state artifacts. Use when the user wants the state acquisition phase only (fetch, render, summarize) for a review-framework PR.

16k tokens

context cost

the whole folder, loaded on every use

files

ships runnable scripts

copies elsewhere

how many repositories repackaged it

418

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/prisma/prisma --skill review-fetch-phase

What comes with it

60 467 bytes besides the instruction

package.json

scripts/extract-review-targets.mjs

scripts/fetch-review-state.mjs

scripts/guard-review-artifacts-ignored.mjs

scripts/render-review-state.mjs

scripts/render-review-state.test.mjs

scripts/review-artifacts.mjs

scripts/summarize-review-state.mjs

scripts/validate-review-state.mjs

The instruction itself

6 sections, as written by the author

Review Fetch Phase

Run only the state acquisition phase of the review-framework loop:

fetch canonical review state JSON (v2), validate it, and render all derived artifacts via scripts.

Run commands from this skill directory. All script paths below are relative to it.

Inputs

Required:
PR URL (for example: https://github.com/OWNER/REPO/pull/123)
Optional:
output directory

If output directory is omitted, derive:

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

Behavior

Validate and parse PR URL, then compute deterministic paths:
<output-dir>/review-state.json
<output-dir>/review-state.md
<output-dir>/summary.txt
<output-dir>/review-targets.json
Ensure <output-dir> exists.
Enforce artifact safety before generation (must be ignored by git):

node ./scripts/guard-review-artifacts-ignored.mjs --dir <output-dir>

Run fetch script to produce canonical JSON:

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

Validate canonical JSON before deriving additional files:

node ./scripts/validate-review-state.mjs --in <output-dir>/review-state.json

Render markdown from canonical JSON:

node ./scripts/render-review-state.mjs --in <output-dir>/review-state.json --out <output-dir>/review-state.md

Generate text summary from canonical JSON:

node ./scripts/summarize-review-state.mjs --in <output-dir>/review-state.json --format text --out <output-dir>/summary.txt

Extract deterministic triage targets for downstream bootstrap:

node ./scripts/extract-review-targets.mjs --in <output-dir>/review-state.json --out <output-dir>/review-targets.json

Target extraction includes:

unresolved review threads
pull-request reviews with body text
issue comments with body text

Schema contract

review-state.json is canonical and must be schema version 2.
No backward compatibility is provided for v1 artifacts.
Derived artifacts (review-state.md, summary.txt, review-targets.json) are regenerable from canonical JSON.
Review artifacts are generated files and must remain untracked in git.

Error handling

Treat fetch failures as operational errors.
If gh api fails with TLS/cert errors in sandbox (x509 / OSStatus -26276), fail fast and instruct rerun outside sandbox.
Never disable TLS verification.

Output to user

Return artifact paths:

review-state.json
review-state.md
summary.txt
review-targets.json

Suggest next step:

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

Other skills for the same job

different authors, same section of the catalogue

Receiving Code Review

by ZhanlinCui

×7

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

2k tokens

Requesting Code Review

by ZhanlinCui

×6

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping

Comprehensive GitHub code review with AI-powered swarm coordination

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.

Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.

Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.

2k tokens

How to use it

Copy the folder

Take prisma/review-fetch-phase from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.