Loading...
Loading...
Found 2,401 Skills
Conduct expert heuristic evaluations using Nielsen's heuristics and domain-specific criteria.
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
This skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, baseline comparison, and outcome measurement for agent pipelines.
Technology stack evaluation and comparison with TCO analysis, security assessment, and ecosystem health scoring. Use when comparing frameworks, evaluating technology stacks, calculating total cost of ownership, assessing migration paths, or analyzing ecosystem viability.
Use when testing Ralph's hat collection presets, validating preset configurations, or auditing the preset library for bugs and UX issues.
Evaluate LLM systems using automated metrics, LLM-as-judge, and benchmarks. Use when testing prompt quality, validating RAG pipelines, measuring safety (hallucinations, bias), or comparing models for production deployment.
Structured 8-factor vendor evaluation framework for AI marketing tools, based on Venkatesan & Lecinski's The AI Marketing Canvas (2nd ed., Stanford Business Books, 2026). Scores each tool against EA market accessibility, data requirements, integration compatibility, team capability, and total cost in UGX, then produces a shortlist with 30-day experiment briefs. Invoke when a client has completed the ai-readiness-diagnostic and is at Canvas Step 2 (Experimentation) and is ready to select specific AI tools for structured trials. Also invoke when a client wants to compare 2–4 named tools before purchasing or committing budget.
Evaluate options for a specific design decision node and recommend one with explicit trade-offs. Use when the design already exposes a concrete choice such as architecture style, state management approach, auth model, storage pattern, sync strategy, multi-agent coordination model, language or runtime, UI framework, data-layer library, or tooling selection. Trigger when the user needs structured comparison and recommendation for a bounded design decision. Do not use for broad design discovery, full-system decomposition, or final readiness review.
Create validated LLM-as-a-Judge evaluators following best practices — binary Pass/Fail judges with TPR/TNR validation for measuring specific failure modes. Use when you need to automate quality checks, build guardrails, or measure a specific failure mode identified during trace analysis. Do NOT use when failures are fixable with prompt changes (use optimize-prompt) or when failure modes are unknown (use analyze-trace-failures first).
Luau language fundamentals: syntax, tables, control flow, string patterns, math, idioms, scope, closures, sharp edges, and JS-to-Luau translation.
Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.