full-stop — Claude Code skill for PR handoff
This Claude Code skill triggers when a request says “full stop,” including as a closing emphasis. It prepares a pull request for review and handoff, then leaves it unmerged.
MIT 1,300 installs ★ 4,278 updated 2026-11-11
npx skills add t3dotgg/tstack --skill full-stop -a claude-codeWhat full-stop does
full-stop follows the full-send workflow but stops before merging and hands the ready pull request back to the user. The phrase “full stop” authorizes its testing and verification steps; a separate “full send” request is not needed.
The skill can commit, push to the task branch, rebase, and resolve conflicts. It disables auto-merge and removes the PR from a merge queue before work, then checks both again before each push. Work cannot proceed if automatic merging cannot be prevented.
Before handoff, it checks the live PR’s status, checks, reviews, and mergeability, and confirms that the PR is open and will not merge without the user. In T3 Code, it calls unwatch_pull_request. The full-send skill is required for its workflow, proof rules, review, and change checks.
What it helps with
- prepare a pull request for manual merging
- check the final diff after changes or conflict fixes
- stop auto-merge before handing off a PR
- report checks, review status, and remaining risks
Example prompts for the agent
- Prepare the pull request for merge, but leave it unmerged. Full stop.
- Resolve the conflicts and check the final diff. Full stop.
- Finish the PR and hand it back open, with auto-merge disabled. Full stop.
How to install full-stop
1Skills CLI (Vercel)
npx skills add t3dotgg/tstack --skill full-stop -a claude-code2Manually: put the files in place
~/.claude/skills/full-stop/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/full-stop/
1Skills CLI (Vercel)
npx skills add t3dotgg/tstack --skill full-stop -a codex2Manually: put the files in place
.agents/skills/full-stop/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add t3dotgg/tstack --skill full-stop -a cursor2Manually: put the files in place
.cursor/skills/full-stop/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install t3dotgg/tstack skills/full-stop2Manually: put the files in place
.github/skills/full-stop/SKILL.md1Skills CLI (Vercel)
npx skills add t3dotgg/tstack --skill full-stop -a gemini-cli2Platform CLI
gemini skills install https://github.com/t3dotgg/tstack --path skills/full-stopManually: put the files in place
.devin/skills/full-stop/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add t3dotgg/tstack --skill full-stop -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about full-stop
How do I install full-stop in Claude Code?
Run npx skills add t3dotgg/tstack --skill full-stop -a claude-code. The skill file is installed at ~/.claude/skills/full-stop/SKILL.md.
What does full-stop do?
It uses the full-send workflow to check a pull request’s readiness, then hands it off without merging. It also disables auto-merge and removes the PR from any merge queue before work.
What does full-stop need to work?
The full-send skill supplies the workflow, proof rules, review, and change checks that full-stop follows. The skill also checks the live pull request and its merge settings.
Source text
SKILL.md · MIT
--- name: full-stop description: Trigger this if the user says 'full stop', even as a closing "Full stop." that reads like emphasis. --- # Full Stop Do the same work as `full-send`, but stop with the PR ready for the user to merge. Never merge it. Read [full-send](../full-send/SKILL.md) and follow its workflow, proof rules, review, and babysitting steps. An explicit "full stop" request authorizes that work without a separate "full send" request. That includes full-send's testing permission. A "full stop" request is the permission for the test methods Proof needs, even when a project file says to ask first, for example before computer use. Use those methods directly. Its merge permission does not apply. The overrides below take precedence. ## No merging You may commit, push, rebase, fix conflicts, and use `--force-with-lease` on this task's branch. Never merge, enable auto-merge, enter a merge queue, push to the default branch, bypass branch protection, or delegate those actions. Disable existing auto-merge and remove the PR from any merge queue before work begins; check again before each push. Report these changes. If you cannot prevent automatic merging, report the blocker before proceeding. ## Stop at the gate Use full-send's merge gate as the readiness check. Replace its merge and final report steps with a handoff. Proof and review must cover the final diff; recheck behavior changes and meaningful conflict fixes before handoff. Fetch the target branch and check the live PR's head, base, checks, reviews, and mergeability. Confirm it is open, not a draft, and not set to merge without the user. If someone else merged it, report that instead. - **Ready to merge:** the merge gate passes. Leave the PR open and unmerged. - **Waiting for required approval:** only human approval remains. Confirm that this is the actual blocker. - **Blocked:** explain what prevents readiness, what you tried, and what is needed. Follow full-send's rules for asking the user. In T3 Code, call `unwatch_pull_request` before the handoff or a question. Report the PR link, final head, verdict, proof, reviewer outcome, and remaining risks. State whether the PR is still open and unmerged.
© t3dotgg · MIT · t3dotgg/tstack