Skills15
Skills
Procedures loaded on invocation. They carry the reasoning and the examples the rules point at.
api-verification Prove a search, filter or API answer is real before relying on it, and budget web search across a fan-out. architecture-viewer Open or update an architecture diagram with the selected builtin or custom viewer, preserving a neutral session handoff. code-quality-instruments Measure whether a test suite is any good, not only that it passes: branch coverage, mutation score, complexity-times-coverage risk, duplication. delegation-tiering Decide whether to spawn a subagent, and on which model tier and reasoning effort. design-loop Raise the visual quality of something that already renders: build, screenshot, independent scored critique, fix, against rubrics with hard accessibility, design-token… harness-authoring Decide where an instruction belongs and write it there, then sync and lint. licensing-review Verify a third-party library, asset, model, font, dataset or copied snippet is safe to ship under the project's licensing stance, and record it. migration-safety Write, review or apply a database schema migration without destroying data. plan-authoring Write or revise a plan file, proposal, design doc or handoff the user reviews before approving work; carries the Review Card contract and the addendum rules. sandbox Fence an autonomous or long-running agent loop: the built-in sandbox with network off, or a container with the worktree mounted. spike-contract Frame a spike so its result is a decision: the question, the cheapest experiment, a numeric exit criterion, the measured result, the machine it ran on. transcript-hygiene Bound what subagents return and what tool output enters the transcript; load when briefing a subagent or reading large output. upstream-contribution Contribute from a fork to a repository you do not own without burning maintainer trust. workflow-status Show progress of background Workflow runs: who has returned, who is still working, how much output. worktree-per-agent Isolate an agent's work in its own git worktree branched off the default branch, so two agents never land conflicting changes on the shared checkout.