Browse Skills

Adobe Premiere Pro MCP installs, verifies, and troubleshoots the Adobe Premiere Pro MCP server. Use it to connect Claude Code or Claude Desktop to Premiere and automate imports, sequences, timeline edits, effects, and exports.

Edit Premiere Project uses Premiere Pro MCP tools to inspect, change, and export local Premiere projects. Use it to verify a connection, read project state, then make timeline, media, effects, caption, audio, or export changes.

Iterating With AI And MCP lets an AI agent edit a Kotlin file, hot reload the app, take screenshots, and compare results to a design intent. Use it for autonomous Compose UI iteration, snapshot rollback, and full-install fallback when schema changes break reloads.

Stability Analyzer IDE Plugin shows Compose stability feedback live in IntelliJ and Android Studio while you edit. It installs from disk, adds gutter colors, inline hints, and an UnstableComposable inspection with quick fixes.

Understanding Stability Inference explains why the Compose compiler classifies a class or composable parameter as stable, runtime, unknown, or unstable. Use it to trace the 12-phase inference algorithm, including generics, inheritance, cross-module $stable values, and stability annotations.

Using Strong Skipping Correctly explains Compose Strong Skipping Mode, including how skippability changes, when lambdas are auto-remembered, and when to use escape hatches like @DontMemoize or @NonSkippableComposable. It helps verify the mode is active and audit recomposition behavior during migration or debugging.

Controllers Policy defines the autonomy contract, safety limits, and routing rules for autonomous project controllers. Use it to decide when to act, merge, pause, or escalate during each tick.

Orchestrator Advisor gives persistent, read-only guidance for navigating a repository across multiple turns. Use it to build a mental map once and then answer follow-up questions with specific file references.

Orchestrator Boss coordinates worker missions by splitting work into delegated tasks, checking acceptance criteria, and integrating results. Use it when you need parallel analysis and judgment without doing the implementation yourself.

Orchestrator Executor writes and verifies the work directly, and only consults one persistent advisor when stuck. Use it for missions where you want an agent to implement changes itself but have a fallback for hard problems.

Threat Model Generation creates a STRIDE-based threat model and security config for the current repository using Bug Hunter artifacts. Use it when a project lacks a threat model, its architecture changes, or a security review needs updated trust-boundary context.

Canary Tripwire Response tells you how to react if a mantis_canary decoy tool is mentioned or called. It treats the event as a security incident, preserves evidence, and stops normal execution.