Use `/spicetify <prompt>` for safe local Spicetify customization, existing plugin/theme research, audit, repair, dry-run plans, rollback, and eval-driven evolve workflows. Always infer the safest next artifact, never arbitrary shell, and never install, trust, or run third-party code without audit and confirmation.
How this skill is triggered — by the user, by Claude, or both
Slash command
/spicetify-agent-skill:spicetifyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when the user wants to research, inspect, plan, modify, repair, audit, compare, or roll back local Spicetify customizations through a safety-gated agent workflow.
agents/openai.yamlassets/README.mdassets/schemas/asset-analysis.schema.jsonassets/schemas/asset-manifest.schema.jsonassets/schemas/asset-source.schema.jsonassets/schemas/asset-workflow-plan.schema.jsonassets/schemas/audit-report.schema.jsonassets/schemas/command-invocation.schema.jsonassets/schemas/command-registry.schema.jsonassets/schemas/confirmation.schema.jsonassets/schemas/consent-grant.schema.jsonassets/schemas/desired-state-manifest.schema.jsonassets/schemas/docs-page.schema.jsonassets/schemas/docs-site-config.schema.jsonassets/schemas/docs-site-content.schema.jsonassets/schemas/docs-site-manifest.schema.jsonassets/schemas/error.schema.jsonassets/schemas/eval-case.schema.jsonassets/schemas/eval-result.schema.jsonassets/schemas/eval-suite.schema.jsonUse this skill when the user wants to research, inspect, plan, modify, repair, audit, compare, or roll back local Spicetify customizations through a safety-gated agent workflow.
The user-facing interface is natural language:
/spicetify <prompt input>
The helper CLI is spicetify-agent. The official Spicetify CLI remains a separate user-installed dependency and must not be bundled, replaced, shadowed, or auto-installed by this skill.
spicetify-agent; never pass through arbitrary shell or user-provided argv.Internal modes remain implementation details for traces, reports, and tests. Do not ask the user to choose one up front. Route /spicetify <prompt> to the safest next artifact:
Use evolve only as an eval-driven improvement review mode. It may inspect local redacted eval results, operation reports, and user-provided redacted transcripts, then propose new evals and skill/runtime/doc improvements. It must not self-apply changes, weaken safety gates, scrape private chat history, upload evidence, run hosted evals, or treat pass-rate improvement as permission to reduce protections.
references/runtime.mdreferences/mode-router.mdreferences/research.mdreferences/asset-workflows.mdreferences/safety-policy.mdreferences/troubleshooting.mdreferences/spicetify-facts.mdreferences/examples.mdreferences/evals.mdGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub wyattowalsh/spicetify-agent-skill