Use Jujutsu (jj) for version control. Covers workflow, commits, bookmarks, pushing to GitHub, absorb, squash, and stacked PRs. Use when working with jj, creating commits, pushing changes, or managing version control.

Run Claude Code programmatically in headless mode or via bidirectional stream-json protocol. Use when building agents, automating Claude, running headless Claude, implementing multi-turn conversations, or integrating Claude CLI into applications.

Compare production WordPress sites against their baked static versions to find differences. Use when testing Bake deployments, checking for missing assets, broken styles, console errors, or any visual/functional discrepancies between production and static sites. Triggers on requests to compare sites, verify bake output, check for differences, or test static deployments.

Run Go unit tests. Use after code changes to verify correctness.

Run gosec and govulncheck to find security vulnerabilities. Use before releases or after dependency changes.

Trigger reindexing of a specific WordPress extension. Use to rebuild the search index for a plugin, theme, or core version.

Run Go race detector to find data races in concurrent code. Use after any change to mutexes, goroutines, or channels.

Run CPU and memory profiling with pprof to identify performance hotspots. Use when investigating high resource usage.

Create and manage database migrations using goose. Use for schema changes, new tables, or index optimization.

Run golangci-lint and static analysis on Go code. Use before pushing or to check code quality.

Run integration tests that require Docker (Postgres, MinIO via testcontainers). Use to validate database and storage behavior.

Run go generate to build templ templates and frontend assets. Use after changing templates or CSS/JS.

Check and tidy Go module dependencies. Use after adding/removing imports or before releases.

Run tests with coverage analysis and identify untested code paths. Use to find gaps before releases.

Run pre-push quality checks (vet + lint + tests with race detector). Use before pushing code.

Run Go benchmarks and compare results to detect performance regressions. Use before and after performance-related changes.

Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements.

Unified spec-folder workflow + context preservation: Levels 1-3+, validation, Spec Kit Memory. Required for file modifications.

Routes non-trivial requests to matching skills through standalone MCP metadata and stable advisor tool ids.

Structural code indexing and mk-code-index MCP workflows for graph readiness, impact queries, context retrieval and structural checks.

Prompt engineering specialist: structured AI prompts via 7 frameworks, DEPTH thinking, CLEAR scoring.

Sentinel for small-model optimization patterns covering SWE-1.6 + DeepSeek-v4-pro + Kimi-k2.6 + Qwen3.6 + GLM-5.1 + MiniMax across cli-devin and cli-opencode (DeepSeek API + opencode-go + MiniMax Token Plan `minimax-coding-plan` default / MiniMax Direct API `minimax` providers) dispatch paths. Routing anchor only; real patterns live in cli-devin/references/ and cli-opencode/references/.

Git workflow orchestrator: worktree setup, clean commits, finish/PR creation across git-worktrees, git-commit, git-finish.

Markdown and OpenCode component specialist: doc quality, content optimization, component scaffolds, install guides, playbooks.