Review Fetch Phase

OrganizationPopular

prisma

review-fetch-phase

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.

Overview

Publisher	prisma
Repository	`orm`
Skill name	`review-fetch-phase`
Stars	47.6K
Forks	2.5K
Bundled files	10
License	Apache-2.0
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
10 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by prisma on GitHub. Read the source before you install it.

Installation

Install the Review Fetch Phase AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/prisma/orm.git /tmp/orm
mkdir -p .claude/skills
cp -r /tmp/orm/skills-contrib/review-fetch-phase .claude/skills/review-fetch-phase

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Review Fetch Phase in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Review Fetch Phase on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Review Fetch Phase is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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 (the artifacts must stay untracked). In a git checkout the guard asks git directly; in a Jujutsu workspace with no git directory it accepts a directory under the workspace root's ignored wip/ tree:

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

Run fetch script to produce canonical JSON:

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

Validate canonical JSON before deriving additional files:

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

Render markdown from canonical JSON:

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

Generate text summary from canonical JSON:

bash
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:

bash
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]

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Review Fetch Phase AI skill do?

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.

Why use Review Fetch Phase on TypingMind?

Because you install it once and use it with any model. Review Fetch Phase is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Review Fetch Phase in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/prisma/orm/tree/main/skills-contrib/review-fetch-phase. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Review Fetch Phase?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Review Fetch Phase?

As many as you like. As long as a model supports skills, you can use Review Fetch Phase with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Review Fetch Phase AI skill free?

Yes. It is published on GitHub by prisma under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Receiving Code Review

obra

CommunityPopular

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

Requesting Code Review

obra

CommunityPopular

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

Systematic Debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Test Driven Development

obra

CommunityPopular

Use when implementing any feature or bugfix, before writing implementation code

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Review Fetch Phase

Inputs

Behavior

Schema contract

Error handling

Output to user

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now