Validates code quality and test counts before creating a pull request for review.

Install

mkdir -p .claude/skills/pr-stevegjones && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15394" && unzip -o skill.zip -d .claude/skills/pr-stevegjones && rm skill.zip

Installs to .claude/skills/pr-stevegjones

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Create a pull request with full validation. Use when ready to submit work for review.
85 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • Run pre-push validation suites
  • Update test counts in PR body with fresh results
  • Verify existence of required artifacts like feature proposals
  • Push local branch to remote with tracking
  • Create a new pull request on GitHub
  • Report the created PR URL to the user

How it works

The skill first runs pre-push validation, then updates test counts in the PR body, verifies artifacts, pushes the branch, and finally creates or updates a GitHub pull request.

Inputs & outputs

You give it
Local code changes, a base branch, and potentially an existing draft PR
You get back
A validated GitHub pull request with updated test statistics or a report of validation failures

When to use pr

  • Create a validated pull request
  • Run pre-push test suites
  • Update PR body with fresh test results
  • Ensure PRs are ready for review

About this skill

Create Pull Request

Run full validation, then create a PR if clean.

Steps

  1. Run pre-push validation
/sdlc-core:validate --pre-push
  1. If validation fails, report the issues and stop. Do NOT push or create PR.

  2. Re-verify any test counts cited in the PR body.

    --pre-push runs the pytest suite only. If the draft PR body cites results from integration smokes, E2E suites, soak tests, container tests, or any other harness outside local-validation.py, re-run those exact suites in this session and update the counts in the body to match the fresh run.

    Example: a PR body saying "266 unit tests, 20/20 container smoke, 8/8 sequential E2E, 18/18 fresh-user-flow" requires pytest tests/ -q, bash tests/integration/workforce-smoke/run-containers.sh, bash tests/integration/workforce-smoke/run-e2e.sh, and bash tests/integration/workforce-smoke/run-fresh-user-flow.sh to all run this session before the PR is opened.

    Session memory of test counts goes stale fast — fixtures grow, assertions drift, environments change. Only numbers you have just observed this session belong in the body. If a suite cannot run in this environment (missing binary, no Docker, etc.), delete the number from the body and say so explicitly rather than leaving a stale figure that cites another machine's result.

    If the PR already exists and counts have drifted post-creation, update the body in place rather than closing and recreating:

    gh pr edit <number> --body-file <updated-body.md>
    
  3. Verify required artifacts exist:

    • Feature proposal in docs/feature-proposals/
    • Retrospective in retrospectives/
    • If either is missing, warn the user and ask whether to proceed.
  4. If validation passes, proceed:

    • Check if the branch tracks a remote: git branch -vv
    • Push to remote with tracking: git push -u origin <branch>
    • Base branch defaults to main unless $ARGUMENTS specifies otherwise
  5. Create the PR using gh pr create:

gh pr create --title "<short title under 70 chars>" --body "$(cat <<'EOF'
## Summary
<1-3 bullet points summarizing the changes>

## Changes
<List of files modified/created>

## Test plan
- [ ] `/sdlc-core:validate --pre-push` passes
- [ ] CI pipeline passes
<additional test steps as needed>

🤖 Generated with [Claude Code](https://claude.com/claude-code)
EOF
)"
  1. Report the PR URL to the user.

When not to use it

  • When validation fails and issues need to be reported
  • When the user does not want to create a pull request

Limitations

  • It stops if pre-push validation fails
  • It requires specific test suites to be runnable in the current environment for accurate counts
  • It does not automatically fix missing artifacts

How it compares

This skill automates the pre-submission validation and PR creation process, ensuring test results are current and artifacts are present, unlike manual PR creation.

Compared to similar skills

pr side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
pr (this skill)03moReviewIntermediate
dependency-upgrade265moReviewIntermediate
finishing-a-development-branch43moReviewBeginner
positron-pr-helper13moReviewBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry