AI Agent Skills

Verify NaCl code, tests, QA, synchronization, review evidence, or stubs without converting missing runtime proof into success.

Use when designing, debugging, training, researching, or evaluating an AI agent and the decision concerns one of seven areas: minimum agent loop, inference-time compute…

Use immediately after the user writes or revises a strategy artifact (strategy kernel, DHM, strategy blocks, empowered-team charter) to stress-test it before it propagat…

Use when the user is setting or pressure-testing product strategy, direction, or the case for an opportunity, before committing resources. Triggers on "product strategy"…

Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in C…

Use when writing, refactoring, or deciding how to test an HDL module, component, or IP block (ROHD, Chisel, SpinalHDL, Verilog, VHDL) and you need it parameterized, vali…

Use when writing hardware, firmware, verification, or tooling code that will reach real silicon, and you face a tradeoff between shipping fast and shipping correct; cove…

Route safe 1C:Enterprise development work involving an infobase, configuration metadata, selective object export, configuration extensions, Designer batch mode, BSL chan…

Switch existing text-to-speech code from OpenAI TTS (audio.speech) or ElevenLabs to Svara TTS Turbo, usually by changing only the base URL and API key, or port it to the…

Investigate StatePort replay mismatches or test frontend behavior with request remaps, replay/block/local-live routes and JSON response overlays, then compare or restore…

Compares A/B variants of a WebAsk survey and checks whether the difference is real or within noise. Use when someone asks which variant performs better or is about to ma…

Design, write, run, and review tests for React, Next.js, or Vite frontends. Use for Vitest/Jest, React Testing Library, MSW, Playwright, E2E, accessibility testing, visu…