principle-outcome-oriented-execution
Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.
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.Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.
Requires direct checks such as running the feature, reading the actual value, or inspecting the diff. Treats compilation, proxies, and self-reports as insufficient evidence of completion.
Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'
Revisits an existing design as though a new requirement had been present from the start. Favors a foundational redesign over attaching the requirement as an add-on.
Apply when integrating a new requirement into an existing design. Redesign as if the requirement had been a foundational assumption from day one, instead of bolting it on.
Addresses concurrent actors writing to the same file, branch, key, or state object. Prioritizes separating state and uses structural serialization only when a single shared writer is a genuine invariant.
Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.
Structures sweeps, migrations, repeated edits, commits, and pull requests into independently verifiable units. Checks each unit before the next and orders delivery so reviewers can assess the sequence.
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.
Guides the sequencing of additions, refactors, and rewrites. Removes dead code, redundant validators, and stub references first so new work builds on a simpler foundation.
Apply when sequencing an addition, refactor, or rewrite. Remove dead weight, redundant validators, and stub references first, then build on the simpler base.
Guides type and function-signature design in statically typed languages. Promotes branded semantic primitives, parsing external data at boundaries, exhaustive variants, and types derived from authoritative schemas without misleading the compiler.
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