Loading...
Loading...
Found 7 Skills
Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification
Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality
Use when the user asks for a literature review, academic deep dive, research report, state-of-the-art survey, topic scoping, comparative analysis of methods/papers, grant background, or any request that needs multi-source scholarly evidence with citations. Also trigger proactively when a user question clearly requires academic grounding (e.g. "what's known about X", "compare approach A vs B in the literature", "summarize the field of Y"). Runs an 8-phase (Phase 0..7), script-driven research workflow across 7 federated sources (OpenAlex, arXiv, Crossref, PubMed, DBLP, bioRxiv, Exa) with optional Semantic Scholar / Brave MCP enrichment, with deduplication, transparent ranking, dual-backend citation chasing (OpenAlex + Semantic Scholar), self-critique, and structured report output with verifiable citations.
Create diagrams and visual explanations with iterative render-and-check workflow. Use when asked to 'create a diagram', 'Venn diagram', 'flow chart', 'architecture diagram', 'visualize this'. Renders SVG to PNG, self-critiques using CRAP principles, iterates until right. Composes with brand skills for styling. (user)
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
Launch multiple sub-agents in parallel to execute tasks across files or targets with intelligent model selection and quality-focused prompting