Total 39,896 skills
Showing 12 of 39896 skills
Use when writing or reviewing Go code to ensure idiomatic style, up-to-date language features, and best practices.
Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.
Build and operate Turborepo monorepos with deterministic task graphs, cache correctness, and CI scalability. Use for `turbo.json` design, task dependency modeling, outputs/inputs hashing, environment variable handling, remote cache rollout, and pipeline troubleshooting.
Skill for Playwright-driven web UI testing, exploration, test generation, execution, and debugging (TypeScript or Python). Triggers for tasks involving application testing, validation, test generation, or UI automation in web applications.
Traditional development workflow skill for product requirement intake, engineering research, technical planning, task breakdown, implementation, testing, bugfix loop, and engineering review. Use when a user wants to run or continue a structured software delivery workflow that mirrors real product-development collaboration.
Provides up-to-date documentation and version guidance for external libraries. Use when working with any third-party library (JS, Python, Ruby, Go, .NET, etc.), when the user asks about a library-specific API or best practice, when debugging a dependency issue, or when installing or upgrading a dependency. Prefer this over guessing or relying on stale knowledge.
Build, tune, and operate Ruff for Python linting, formatting, and editor/CI integration. Use when adding or updating Ruff configuration, migrating from Black/Flake8/isort, selecting rule families, enforcing fix safety, or debugging lint/format behavior in local development, pre-commit, and CI.
Create or update a reusable product marketing context document with positioning, audience, ICP, use cases, and messaging. Use at the start of a project to avoid repeating core marketing context across tasks.
Use this skill when crafting, iterating, or optimizing prompts for LLMs including zero-shot, few-shot, chain-of-thought, role prompting, structured output, and prompt chaining. Not for fine-tuning or training models. Not for evaluating model quality across benchmarks.
Write, review, or fix Swift concurrency code using actors, async/await, and structured concurrency. Use when implementing concurrent features, resolving data race warnings, migrating from GCD, enabling Swift 6 strict concurrency mode, or adopting Swift 6.2 approachable concurrency (@concurrent, main-actor-by-default, isolated conformances).
Review a PR linked to a kspec task, post findings as inline comments, and merge only when all quality gates pass. You NEVER fix code — you review and comment. If issues found, kick back to worker.
Task management CLI for tracking and managing feature subtasks with status, dependencies, and validation