Loading...
Loading...
Found 2,119 Skills
Run a targeted local React Doctor Evals loop against an uncommitted rule change. Use after focused rule tests pass, while inspecting real open-source hits, or when rule-validate needs local false-positive evidence before pull request parity.
Use when conversation context is too long, hitting token limits, or responses are degrading. Compresses history while preserving critical information using anchored summarization and probe-based validation.
Requirements Discovery Specification, applicable to exploratory scenarios, helps users identify high-ROI functional directions when they are confused through role-playing. Automatically triggered, purely conversational inspiration.
A safe calculator for mathematical expressions
Run Microsoft's eval-recipes benchmarks to validate amplihack improvements against baseline agents. Auto-activates when testing improvements, running evals, or benchmarking changes.
Produce an LLM Build Pack (prompt+tool contract, data/eval plan, architecture+safety, launch checklist). Use for building with LLMs, GPT/Claude apps, prompt engineering, RAG, and tool-using agents.
Generate and explore ideas effectively. Use when starting new projects, solving problems, or exploring solutions. Covers ideation techniques and divergent thinking.
Polars fast DataFrame library. Use for fast data processing.
Use when raising startup capital (pre-seed through Series C+): decide raise vs bootstrap, size a round, build a deck + data room, run investor targeting/outreach, negotiate SAFEs/term sheets, manage diligence, and set investor reporting cadence post-close.
PostHog feature flags for Android applications
Use when a user asks for CEO review, founder-mode review, think bigger, strategy review, rethink this plan, is this ambitious enough, or critique of an existing product, strategy, roadmap, or implementation plan.
Import datasets from HuggingFace and convert them to Coval test sets. Use when the user wants to create test cases from HuggingFace dataset or repository.