Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Guides refactoring and assessment of diff size, abstractions, layers, and signal threading. Favors removing code and making the smallest change that solves the problem.
Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.
Applies to commands, lifecycle steps, and processing loops that encounter crashes, restarts, or retries. Designs them to converge on the same end state regardless of earlier partial runs.
Guides replacement of internal APIs while existing callers still use the old version. Migrates callers and deletes the old API together rather than retaining compatibility layers.
Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibility layers.
Reviews code for layers that obscure answers and hidden state that readers must remember. Encourages collapsing wrappers with one caller and reducing the scope of mutable state.
Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.
Applies to stateful logic, excessive branching, and repeated assumptions about data shape. Encodes the domain in a structure rather than scattering conditionals across files.
Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.
Guides agents to complete reversible work and present the result for human correction. Reserves requests for confirmation for irreversible actions.
Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.
Guides planned rewrites and migrations with explicit phase boundaries. Prioritizes reaching the target architecture rather than maintaining smooth intermediate states through disposable compatibility code.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name