Go performance workflow: benchmark and profile (pprof/trace), identify hotspots, reduce allocations/GC and contention, and verify improvements with repeatable measurement. Use only after you have evidence the Go code is the bottleneck.
Go testing patterns for unit tests, table-driven tests, subtests, test helpers, mocking/fakes, benchmarks, fuzzing, and coverage. Use when writing or reviewing Go tests to improve correctness, stability, and maintainability.
Write a portable handoff document so another agent can continue the current work. Use only when the work must move to a new harness, directory, repo, operator, or a forked parallel session; invoke on explicit request, not autonomously.
Create or revise Pi extensions, plugins, and themes. Use for extension entrypoints, tools, commands, events, UI integration, state, MCP servers, codemode and tool exposure, virtual models, theme files, and packaging.
Create or evolve skill-apps: Agent Skills with executable workflows and consistent deliverables. Use when turning a recurring task into a skill with deterministic helpers, output contracts, runtime diagnostics, or resumable sessions.
Create, revise, evaluate, or package Agent Skills. Use for SKILL.md instructions, activation descriptions, and bundled resources.
Auth/lab dev: Windows syscall-dispatch research; SSN resolution, indirect gates, ntdll stubs, gadget scanning, stack-spoof integration.
Auth/lab dev: Linux internals; ELF loading and program startup, procfs, namespaces/caps, eBPF verifier/maps, LSM hooks for tooling/telemetry design.