Loading...
Loading...
Found 1,900 Skills
Use when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI/CD quality gates, observability, or cost optimization. Triggers on: "evaluate my agent", "add evaluator", "measure quality", "quality gate", "run evals", "agent too slow", "why is it slow", "reduce latency", "set up observability", "CloudWatch dashboard", "how much does my agent cost", "cost optimization", "logs not showing up", "logs missing", "spans not found", "eval failing", "eval error", "dev traces", "local traces", "agentcore dev traces", "traces to CloudWatch". Not for debugging errors or crashes — use agents-debug. Slow but correct routes here; broken routes to debug.
Investment-banking pitch book for strategic alternatives — trading comps, precedent transactions, valuation football field, DCF sensitivity, strategic-options matrix, process recommendation. Built by adapting `assets/template.html` so IB-specific chrome, disclosure bands, and source labels are preserved. Use for Board / sell-side discussion materials. Not a VC fundraising deck (see html-ppt-pitch-deck). Workflow adapted from Anthropic financial-services Pitch Agent (Apache-2.0).
Write, refine, run, and QA promptfoo evaluation suites: promptfooconfig.yaml, prompts, providers, vars, tests, assertions, model-graded rubrics, transforms, datasets, exports, and CI gates. Use for non-redteam eval coverage, regression tests, or new eval matrices. Do not use for adversarial redteam plugin or strategy setup.
Guides ML/research engineering for safeguards—safety classifier development, harm benchmarks and eval suites, labeled dataset design, fine-tuning and ablations, calibration and slice analysis, attack-surface research memos, and promotion criteria for new moderation models. Use when building or evaluating guardrail models, designing safety benchmarks, measuring precision/recall on policy categories, comparing mitigation techniques, or writing research reports on classifier improvements—not for production inference gateways (ml-infrastructure-engineer-safeguards), PII/leakage privacy research (privacy-research-engineer-safeguards), red-team attack campaigns (ai-redteam), AI governance policy (ai-risk-governance), general non-safety research (ai-researcher), or token-efficiency studies (research-engineer-scientist-tokens).
Query and browse evaluation results stored in MLflow. Use when the user wants to look up runs by invocation ID, compare metrics across models, fetch artifacts (configs, logs, results), or set up the MLflow MCP server. ALWAYS triggers on mentions of MLflow, experiment results, run comparison, invocation IDs in the context of results, or MLflow MCP setup.
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.
Design and evaluate presentations that communicate effectively. Use when designing a presentation, creating slides, getting presentation feedback, structuring a talk, or reviewing slides. Keywords: presentation, slides, talk, PowerPoint, Keynote, reveal.js.
Analyzes events through environmental lens using ecological principles, systems thinking, sustainability frameworks, and conservation biology to assess ecosystem health, biodiversity impacts, and long-term environmental sustainability. Provides insights on climate change, resource management, pollution, habitat conservation, and human-nature relationships. Use when: Environmental policy, climate decisions, conservation planning, resource extraction, pollution assessment. Evaluates: Ecosystem health, biodiversity, sustainability, climate impacts, carrying capacity, environmental justice.
Evaluate UI/flows from cognitive load, error prevention, and accessibility perspectives. Apply when reviewing UX, discussing user confusion, high drop-off, or form usability issues.
Measure the valuation range (overvalued/undervalued) of the mining stock sector relative to the metal itself using the ratio of Silver Mining Stock Price to Silver Price, and derive 'bottom/top' signals and scenario projections through historical percentiles and analogous intervals.
MCP (Model Context Protocol) server build and evaluation guide, including local conventions for tool surfaces, config, and testing
Prevents sycophantic reasoning through checklist-based analysis, categorical integrity, and evidence-following to uncomfortable conclusions. Red Flags: "I agree that", "You are right", "Great point", "Absolutely", "That is a fair point", "I can see why", agreement without validation, softening conclusions, hedging without evidence, retracting under pressure. Use when analyzing conflicts, evaluating ethical claims, or noticing sycophantic thought patterns. Do not use for routine implementation or simple factual questions. CRITICAL: This skill overrides conversational tendencies toward politeness. Agreement requires validity and accuracy.