PUT SKILLS TO WORK
Start with the task at hand.
Match your situation to a workflow, then give your agent a concrete request. These example prompts are starting points: adapt the task and constraints to your own repository.
01 / Recommended skill: Understanding Codebases
Understanding an unfamiliar repository
You have inherited a repository and need to understand how requests reach storage before making changes.
Use understanding-codebases. Trace one main request from its entry point through business logic to persistence. Cite the relevant files and symbols, identify tests and conventions, and separate facts from assumptions. Do not edit code.Expected output: A focused repository map, request flow, key files, and a list of unresolved questions.
02 / Recommended skill: Implementing Features
Implementing a feature
A catalog needs search and category filtering without changing its existing layout or data contracts.
Use implementing-features. Add search by name and description plus category filtering to this catalog. Reuse existing components and data types, handle empty results, preserve unrelated behavior, and verify the requested interactions. Report the checks actually run.Expected output: Working filtering behavior, appropriate coverage, and a focused implementation report.
03 / Recommended skill: Debugging Code
Investigating a failing test
A test that previously passed now fails, and the cause is not established.
Use debugging-code. Investigate the failing test provided in this task. Reproduce it before editing, trace the failing execution path, and test focused hypotheses. Fix the root cause without weakening assertions, add regression coverage if needed, and rerun the original failure.Expected output: Reproduction evidence, a justified root cause, a minimal fix, and verification results.
04 / Recommended skill: Designing Frontend
Improving an interface
An existing form has unclear hierarchy and inconsistent feedback on narrow screens.
Use designing-frontend. Improve this form using the existing components and tokens. Clarify field grouping and action hierarchy, preserve behavior, and handle validation, loading, and success states. Inspect mobile and desktop rendering and verify keyboard access.Expected output: A coherent responsive form with accessible controls and verified interaction states.
05 / Recommended skill: Setting Up Agentic Projects
Preparing a project for AI-assisted development
A repository has working code and documentation but needs clear coding-agent instructions.
Use setting-up-agentic-projects in setup mode. Read existing instructions, skills, and approved project documentation. Create the smallest useful AGENTS.md and only essential adapters for tools already in use. Preserve configuration and application code. Verify paths and commands and report actual checks.Expected output: Concise project instructions, justified adapters, and a setup report with verification limits.