Shepherd Pr logo

Shepherd Pr

OrganizationPopular
tldraw
shepherd-pr

Keep an eye on this PR. Review and resolve pull request comments and fix build failures autonomously. Use when asked to review PR feedback, address reviewer comments, fix CI failures, resolve PR threads, or handle PR maintenance tasks like "review PR comments", "fix the build", "address PR feedback", "clean up PR", or "resolve comments". Handles comment triage (resolve false positives, fix trivial issues, flag complex ones), build/lint/type errors, and e2e snapshot updates.

Overview

Publishertldraw
Repositorytldraw
Skill nameshepherd-pr
Stars
50.4K
Forks
3.5K
Bundled files
Instructions only
Links
  • 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 tldraw on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. 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.
2

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/tldraw/tldraw.git /tmp/tldraw
mkdir -p .claude/skills
cp -r /tmp/tldraw/skills/shepherd-pr .claude/skills/shepherd-pr
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Shepherd Pr 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 Shepherd Pr 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 Shepherd Pr 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 PR

Autonomously review PR comments and build status, resolving what can be done with high confidence (>=80%) and flagging the rest for human review.

Workflow

Note: this repository requires that you be using node 24. Use nvm to switch to node 24 before running any commands:

bash
nvm use 24

1. Gather context

bash
# Get PR number for current branch
gh pr view --json number,headRefName,url

# Get review threads with resolution status
gh api graphql -f query='
  query($owner: String!, $repo: String!, $number: Int!) {
    repository(owner: $owner, name: $repo) {
      pullRequest(number: $number) {
        reviewThreads(first: 100) {
          nodes {
            id
            isResolved
            comments(first: 50) {
              nodes {
                body
                path
                line
                author { login }
                createdAt
                databaseId
              }
            }
          }
        }
      }
    }
  }
'

Filter to unresolved threads only.

2. Triage each unresolved comment

Read the referenced code and investigate. Classify into:

A. False positive / already resolved — The issue no longer exists in current code.

  • Reply explaining why, citing specific code or commit.
  • Resolve the thread.

B. Trivial fix (>=80% confidence) — Obvious, mechanical fix. No design decisions or matters of opinion. Examples: typos, missing null checks, wrong variable names, off-by-one, missing imports.

  • Make the fix.
  • Reply describing what was changed.
  • Resolve the thread.

C. Needs human input (<80% confidence) — Design question, significant refactor, or ambiguous fix.

  • Do NOT resolve.
  • Add to end-of-session summary.

3. Reply and resolve threads

Reply to a comment:

bash
gh api repos/{owner}/{repo}/pulls/{number}/comments/{comment_id}/replies \
  -f body="<your reply>"

Resolve a thread:

bash
gh api graphql -f query='
  mutation($threadId: ID!) {
    resolveReviewThread(input: {threadId: $threadId}) {
      thread { isResolved }
    }
  }
' -f threadId="$THREAD_ID"

Always push fixes, then reply, then resolve related threads (in that order).

4. Check build status

bash
gh pr checks --json name,status,conclusion

Investigate failures by category:

Lint errors — Run yarn lint-current. Fix if mechanical (formatting, import order, unused vars). Flag if the lint rule itself is questionable.

Type errors — Run yarn typecheck from repo root. Fix straightforward type mismatches. Flag if fix requires architectural decisions.

Unit test failures — Run yarn test run in relevant workspace. Fix if test expectation is clearly outdated due to intentional code changes. Flag if failure reveals actual bug or design concern.

E2E snapshot failures — Determine whether the PR's code changes should cause visual differences:

  • If yes (UI changes, style updates): add the update-snapshots label to trigger the automated update workflow:
    bash
    gh pr edit --add-label "update-snapshots"
  • If no: flag as unintended regression for human review.

Mysterious/unexpected failures — Do not attempt to fix. Flag for human review with error output.

5. Commit and push fixes

bash
git add <specific files>
git commit -m "Address PR review feedback

- <summary of changes>"
git push

Stage specific files only. Never force push. Never use git add -A.

6. End-of-session summary

Always end with:

## PR review summary

### Resolved
- <thread>: <what was done>

### Fixed
- <description of fix>

### Needs your input
- <thread>: <why it needs human judgment>

### Build status
- <status of each check, any actions taken>

Omit empty sections.

Guidelines

  • Conservative threshold: only act when >=80% confident the fix is correct and uncontroversial.
  • Never resolve comments raising design questions or matters of opinion.
  • Never resolve without replying first.
  • Read actual code before concluding a comment is a false positive.
  • Verify fixes don't break types (yarn typecheck) or lint (yarn lint-current).
  • Do not modify test expectations unless change is clearly intentional.

Frequently asked questions

What does the Shepherd Pr AI skill do?

Keep an eye on this PR. Review and resolve pull request comments and fix build failures autonomously. Use when asked to review PR feedback, address reviewer comments, fix CI failures, resolve PR threads, or handle PR maintenance tasks like "review PR comments", "fix the build", "address PR feedback", "clean up PR", or "resolve comments". Handles comment triage (resolve false positives, fix trivial issues, flag complex ones), build/lint/type errors, and e2e snapshot updates.

Why use Shepherd Pr on TypingMind?

Because you install it once and use it with any model. Shepherd Pr 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 Shepherd Pr in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tldraw/tldraw/tree/main/skills/shepherd-pr. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Shepherd Pr?

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 Shepherd Pr?

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

Is the Shepherd Pr AI skill free?

It is published on GitHub by tldraw. Check the repository for licensing terms. 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇