Turn your team's standard operating procedure for shipping code into an executable AI skill. Automate running tests, fixing lint, pushing to the repo, and monitoring CI, saving significant engineering time and reducing friction.
with Claire Vo
Identify and list the entire manual checklist your team follows before merging a pull request. This includes tasks like running lint, running tests, building, pushing to git, and monitoring the CI pipeline.
Convert the documented SOP into a custom, executable skill for your code assistant. The blog post suggests creating a /ship skill that encapsulates the entire process.
The skill should first run all necessary local checks on the code (e.g., using Bazel for linting/building). Once local checks pass, it should push the code to the Git repository.
Program the skill to monitor the CI/CD pipeline (e.g., BuildKite) by checking the pull request status. Add logic for the AI to automatically fix minor issues, such as lint errors, and retry the build.
Include important constraints in the skill's instructions to prevent destructive actions. For example, explicitly instruct the AI not to force push to avoid overwriting Git history.
When your code change is ready, simply invoke your custom skill (e.g., by typing /ship in your code assistant) and let the AI handle the entire monotonous process of getting your code merged.
Create a simple app to manage your expensive purchases. This workflow uses AI to automatically scan receipts and product photos, extract key information, and save product manuals, all in one place.
Build and iterate on high-fidelity prototypes directly in your browser. This workflow uses a custom web UI to generate designs from prompts, visually annotate feedback, and automatically implement revisions with AI.
Overcome generic AI-generated designs by building a custom prototyping environment. This workflow connects your company's design system to an AI code editor, ensuring all prototypes are on-brand and high-fidelity.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.