Draft a migration plan for one table
Devin handles this as a draft: Columns and the backfill question. Do not run SQL.
- Steps
- 4
- Cost
- medium
- Time
- An hour
Unverified · docs.devin.ai · 16 Oct 2026
Loading the catalog…
Loading the catalog…
Best for
Agents that can move a ticket, bug, or upgrade toward a diff. Ranking follows how many shipping-code playbooks each agent has in this catalog.
Ranked by how many matching playbooks are in this catalog, then by how many of those are marked easy, then by lower cost buckets. This is coverage inside AI Playbook Gems, not a benchmark and not a vote.
7 playbooks · 2 marked easy
5 playbooks · 2 marked easy
4 playbooks · 2 marked easy
3 playbooks · 0 marked easy
2 playbooks · 2 marked easy
1 playbook · 1 marked easy
Devin handles this as a draft: Columns and the backfill question. Do not run SQL.
Unverified · docs.devin.ai · 16 Oct 2026
Cursor handles this as a draft: Replace emails with placeholders. Do not use production data.
Unverified · cursor.com · 16 Oct 2026
Claude Code handles this as a draft: Scripts, main files, and the test command in the README. Do not push.
Unverified · code.claude.com · 16 Oct 2026
Codex CLI handles this as a draft: Old, new, and who reads it in the snippets I paste. Do not ship the API.
Unverified · learn.chatgpt.com · 15 Oct 2026
Cursor handles this as a draft: The smallest change that could explain the failure I paste. Do not commit.
Unverified · cursor.com · 15 Oct 2026
Claude Code reads a single module, writes characterization tests, then changes structure only where those tests pass.
Unverified · code.claude.com · 15 Oct 2026
Cursor's agent searches the repo, edits the files for one ticket, and runs the checks you name. The ticket's out-of-scope list is part of the prompt.
Unverified · cursor.com · 15 Oct 2026
Devin handles this as a draft: One message per hunk group I describe. Do not commit.
Unverified · docs.devin.ai · 14 Oct 2026
Codex CLI investigates a single red check, patches it, and shows the command output. It does not rewrite the suite to go green.
Unverified · learn.chatgpt.com · 14 Oct 2026
Cursor handles this as a draft: From the tests I paste. Do not change runtime behavior.
Unverified · cursor.com · 13 Oct 2026
Claude Code summarizes breaking changes for a single dependency, applies the upgrade, and runs the existing tests. Major bumps stay behind a question.
Unverified · code.claude.com · 12 Oct 2026
Perplexity handles this as a draft: What the message says and the line I paste. Do not rewrite the whole project.
Unverified · docs.perplexity.ai · 11 Oct 2026
Devin picks up one issue and opens a PR. The playbook tells it which repo, which commands, and what not to touch.
Unverified · docs.devin.ai · 9 Oct 2026
Cursor Agent adds a failing test for a known bug, then the fix, and stops if the test never failed.
Unverified · cursor.com · 9 Oct 2026
Devin handles this as a draft: The command in the runbook I paste and the signal that means stop. Do not execute it.
Unverified · docs.devin.ai · 8 Oct 2026
Claude Code handles this as a draft: Breaking changes that mention the version I am on. Do not run the upgrade.
Unverified · code.claude.com · 8 Oct 2026
Copilot lists cases for a change you describe. You run them. The plan is not permission to skip the ones that are slow.
Unverified · docs.github.com · 2 Oct 2026
Claude Code writes a one-page map of how to run, test, and change the system. It does not edit application code.
Unverified · code.claude.com · 2 Oct 2026
GitHub Copilot handles this as a draft: Frames in our code, not the library, first. Do not push a fix.
Unverified · docs.github.com · 30 Sep 2026
Cursor handles this as a draft: Acceptance checks from the ticket text. Do not start coding until I say so.
Unverified · cursor.com · 30 Sep 2026
Cursor Agent walks one screen for missing names, keyboard traps, and contrast notes, then patches the clear code issues.
Unverified · cursor.com · 26 Sep 2026
Codex CLI builds a feature described as observable behavior, runs the tests you name, and leaves unrelated files alone.
Unverified · learn.chatgpt.com · 18 Sep 2026
Cursor leads this page because it has 7 matching playbooks in AI Playbook Gems. Ranked by how many matching playbooks are in this catalog, then by how many of those are marked easy, then by lower cost buckets. This is coverage inside AI Playbook Gems, not a benchmark and not a vote.
Ranked by how many matching playbooks are in this catalog, then by how many of those are marked easy, then by lower cost buckets. This is coverage inside AI Playbook Gems, not a benchmark and not a vote.
The seed catalog is unverified. A higher rank means more playbooks on file, not a measured win.