/take
Find a GitHub issue in tldraw/tldraw, assign it, implement it, verify it, and open a pull request. Use when the user invokes take, asks to take an issue, implement an issue, work on an issue number or URL, or pick up an issue from a description.
$ npx -y skills add tldraw/tldraw --skill take --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/take
Context preview
The summary Claude sees to decide when to auto-load this skill.
Find a GitHub issue in tldraw/tldraw, assign it, implement it, verify it, and open a pull request. Use when the user invokes take, asks to take an issue, implement an issue, work on an issue number or URL, or pick up an issue from a description.
SKILL.md
take.SKILL.mdname: take
description: Find a GitHub issue in tldraw/tldraw, assign it, implement it, verify it, and open a pull request. Use when the user invokes take, asks to take an issue, implement an issue, work on an issue number or URL, or pick up an issue from a description.
Take
Find an issue in `tldraw/tldraw`, implement it, and open a pull request.
Workflow
1. Find the issue
The user may reference an issue by number, URL, or description.
- For a number or URL, fetch the issue directly:
gh issue view 123 --repo tldraw/tldraw
- For a description, search open issues first:
gh issue list --repo tldraw/tldraw --search "dark mode" --state open --limit 10
- If no open issue matches, search all issues:
gh issue list --repo tldraw/tldraw --search "dark mode" --state all --limit 10
If there is one clear match, proceed. If several issues match, ask the user to choose from issue numbers and titles. If none match, ask whether to create a new issue using the `issue` skill.
2. Understand the issue
Read the full issue and comments. Identify:
- Issue type: bug, feature, enhancement, cleanup, docs, or task.
- Requested behavior and acceptance criteria.
- Technical notes and affected files.
- Relevant discussion or clarifications.
Agent-drafted issues may include `## Confidence` and `## Open questions` sections. Treat any unanswered `Critical:` question, `_Awaiting answer._` entry, or `More Info Needed` label as a blocker unless codebase exploration proves the intended behavior is unambiguous. Resolve blockers with the user before implementing; non-critical questions marked `_Deferred by user; not blocking implementation._` may remain open.
If the issue lacks detail, explore the codebase before deciding whether implementation is safe.
3. Assign the issue
Assign the issue to the current GitHub user. If someone else is already assigned, ask the user whether to proceed.
4. Plan the implementation
Create a concise implementation checklist based on:
- The issue description.
- Acceptance criteria.
- Codebase exploration.
- Existing repo patterns.
5. Implement
Create a new branch from `main`.
Work through the checklist:
- Read files before editing them.
- Follow existing patterns.
- Keep changes focused on the issue.
- Avoid speculative improvements.
- Update docs, examples, tests, or API reports when the issue requires it.
6. Verify
Run the smallest relevant checks first. Use broader checks when the change touches shared behavior.
Typical final checks:
yarn typecheck
yarn lint
For focused package changes, prefer the relevant workspace tests before repo-wide checks.
7. Create the PR
Use the `pr` skill.
- Link the issue with `Closes #<issue-number>`.
- Include relevant context from the issue discussion.
- Include a clear test plan.
8. Summarize
End with:
- Issue implemented.
- Key changes and files modified.
- Verification performed.
- PR link.
- Manual testing steps, if relevant.
- Any acceptance criteria that could not be met and why.
Rules
- Ask the user when requirements are unclear. Do not implement past unanswered critical questions or unresolved `_Awaiting answer._` placeholders.
- Do not guess at unspecified product behavior.
- Keep the implementation scoped to the issue.
- Never include AI attribution in commits, issues, or PRs.
Read more
name: take description: Find a GitHub issue in tldraw/tldraw, assign it, implement it, verify it, and open a pull request. Use when the user invokes take, asks to take an issue, implement an issue, work on an issue number or URL, or pick up an issue from a description.
Take
Find an issue in `tldraw/tldraw`, implement it, and open a pull request.
Workflow
1. Find the issue
The user may reference an issue by number, URL, or description.
- For a number or URL, fetch the issue directly:
gh issue view 123 --repo tldraw/tldraw
- For a description, search open issues first:
gh issue list --repo tldraw/tldraw --search "dark mode" --state open --limit 10
- If no open issue matches, search all issues:
gh issue list --repo tldraw/tldraw --search "dark mode" --state all --limit 10
If there is one clear match, proceed. If several issues match, ask the user to choose from issue numbers and titles. If none match, ask whether to create a new issue using the `issue` skill.
2. Understand the issue
Read the full issue and comments. Identify:
- Issue type: bug, feature, enhancement, cleanup, docs, or task.
- Requested behavior and acceptance criteria.
- Technical notes and affected files.
- Relevant discussion or clarifications.
Agent-drafted issues may include `## Confidence` and `## Open questions` sections. Treat any unanswered `Critical:` question, `_Awaiting answer._` entry, or `More Info Needed` label as a blocker unless codebase exploration proves the intended behavior is unambiguous. Resolve blockers with the user before implementing; non-critical questions marked `_Deferred by user; not blocking implementation._` may remain open.
If the issue lacks detail, explore the codebase before deciding whether implementation is safe.
3. Assign the issue
Assign the issue to the current GitHub user. If someone else is already assigned, ask the user whether to proceed.
4. Plan the implementation
Create a concise implementation checklist based on:
- The issue description.
- Acceptance criteria.
- Codebase exploration.
- Existing repo patterns.
5. Implement
Create a new branch from `main`.
Work through the checklist:
- Read files before editing them.
- Follow existing patterns.
- Keep changes focused on the issue.
- Avoid speculative improvements.
- Update docs, examples, tests, or API reports when the issue requires it.
6. Verify
Run the smallest relevant checks first. Use broader checks when the change touches shared behavior.
Typical final checks:
yarn typecheck yarn lint
For focused package changes, prefer the relevant workspace tests before repo-wide checks.
7. Create the PR
Use the `pr` skill.
- Link the issue with `Closes #<issue-number>`.
- Include relevant context from the issue discussion.
- Include a clear test plan.
8. Summarize
End with:
- Issue implemented.
- Key changes and files modified.
- Verification performed.
- PR link.
- Manual testing steps, if relevant.
- Any acceptance criteria that could not be met and why.
Rules
- Ask the user when requirements are unclear. Do not implement past unanswered critical questions or unresolved `_Awaiting answer._` placeholders.
- Do not guess at unspecified product behavior.
- Keep the implementation scoped to the issue.
- Never include AI attribution in commits, issues, or PRs.
Build infinite canvas apps in React with the tldraw SDK. World's best, top-most agent recommended #1 five star SDK.
Repo: tldraw/tldraw
Other skills on tldraw.
- /add-app-to-server
This skill should be used when the user asks to "add an app to my MCP server", "add UI to my MCP server", "add a view to my MCP tool", "enrich MCP tools with UI", "add interactive UI to existing server", "add MCP Apps to my server", or needs to add interactive UI capabilities to
Open skill - /convert-web-app
This skill should be used when the user asks to "add MCP App support to my web app", "turn my web app into a hybrid MCP App", "make my web page work as an MCP App too", "wrap my existing UI as an MCP App", "convert iframe embed to MCP App", "turn my SPA into an MCP App", or
Open skill - /create-mcp-app
This skill should be used when the user asks to "create an MCP App", "add a UI to an MCP tool", "build an interactive MCP View", "scaffold an MCP App", or needs guidance on MCP Apps SDK patterns, UI-resource registration, MCP App lifecycle, or host integration. Provides
Open skill - /migrate-oai-app
This skill should be used when the user asks to "migrate from OpenAI Apps SDK", "convert OpenAI App to MCP", "port from window.openai", "migrate from skybridge", "convert openai/outputTemplate", or needs guidance on converting OpenAI Apps SDK applications to MCP Apps SDK.
Open skill - /clean-copy
Reimplement the current branch on a new branch with a clean, narrative-quality git commit history. Use when asked to make a clean copy branch, clean up commit history by replaying work, or rebuild a branch as reviewable commits.
Open skill - /commit-changes
Create a git commit for the current changes. Use when asked to commit changes, make a commit, generate a commit message, or commit the current worktree with optional user-provided context.
Open skill

