Collect Review Findings

Community

paulinevos

collect-review-findings

Present a reviewer agent's planned review comments for approval, then post the approved ones to the pull request as inline comments. Use when a dispatched reviewer has finished, when asked to show or post planned review comments, or to submit a drafted review.

Overview

Publisher	paulinevos
Repository	`claude-stuff`
Skill name	`collect-review-findings`
Stars	64
Forks	0
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

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.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by paulinevos on GitHub. Read the source before you install it.

Installation

Install the Collect Review Findings 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.
https://github.com/paulinevos/claude-stuff/tree/main/plugins/pr-reviewer/skills/collect-review-findings
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/paulinevos/claude-stuff/tree/main/plugins/pr-reviewer/skills/collect-review-findings

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

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/paulinevos/claude-stuff.git /tmp/claude-stuff
mkdir -p .claude/skills
cp -r /tmp/claude-stuff/plugins/pr-reviewer/skills/collect-review-findings .claude/skills/collect-review-findings

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

Use it in TypingMind

Enable Collect Review Findings 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 Collect Review Findings 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 Collect Review Findings 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.

collect-review-findings

Findings arrive planned, never posted. You present them, the user decides, and only then does anything reach GitHub. Posting a review is public and visible to the PR author — you MUST have explicit approval for this PR, in this run. Approval of an earlier PR's findings does not carry over.

Read the reviewer's scratchpad (review-<repo-name>-<number>). When several reviewers finished, handle one PR at a time — approval is per PR.
Present every finding in full: file, line, severity, what it rests on, and the comment body as it would be posted. Do not summarise the bodies away — the user is approving the words that get posted. Lead with the blocking findings. Say plainly when there are none.
Let the user drop, keep, or edit each finding, and say what they want the review to be: a plain comment, approval, or changes requested. Ask when they have not said — do not infer it from the severities.

Post only what survived. Inline comments need the file path and a line in the diff:

sh
gh api repos/<owner>/<name>/pulls/<n>/comments \
  -f body='<comment>' -f commit_id='<head sha>' -f path='<file>' \
  -F line=<line> -f side=RIGHT

For one review carrying every comment at once, POST repos/<owner>/<name>/pulls/<n>/reviews takes a comments array plus event (COMMENT, APPROVE, REQUEST_CHANGES). Get the head sha from gh pr view <n> --json headRefOid. A comment whose line is not in the diff is rejected — post it as a PR-level comment instead of moving it to a line it does not belong on.

Report what was posted and what was dropped, with the PR URL. Stop there: you MUST NOT re-review, reply to the author's responses, or post again without a fresh approval.

When the user wants nothing posted, say so and leave the scratchpad intact — the plan keeps its value as notes for a review they write themselves.

Frequently asked questions

What does the Collect Review Findings AI skill do?

Why use Collect Review Findings on TypingMind?

Because you install it once and use it with any model. Collect Review Findings 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 Collect Review Findings in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/paulinevos/claude-stuff/tree/main/plugins/pr-reviewer/skills/collect-review-findings. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Collect Review Findings?

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 Collect Review Findings?

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

Is the Collect Review Findings AI skill free?

Yes. It is published on GitHub by paulinevos under the MIT 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

Discrawl

openclaw

OrganizationPopular

Discord archive: search, sync freshness, DMs, summaries, TUI, repo/release work.

Gitcrawl

GitHub archive: issue/PR search, sync freshness, duplicate clusters, current GitHub handoff, and Gitcrawl repo work.

Graincrawl

Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work.

Openclaw Changelog Update

openclaw

OrganizationPopular

Regenerate OpenClaw release changelog sections from git history before beta, stable, or extended-stable releases.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

collect-review-findings

Frequently asked questions

Related AI Skills

Set up your own AI workspace now