Loading...
Loading...
Found 1,310 Skills
Review generated or changed production code before it ships, using Clean Code, SOLID, DRY, KISS, YAGNI, and LLM-specific failure-mode checks in any programming language. Best used reactively after an agent writes, edits, refactors, or fixes code, before presenting, committing, or merging the result. Use when the user asks "review this PR", "is this safe to merge?", "make this cleaner", "audit this code", "refactor this", "fix this bug", or after a coding agent produced implementation code. Can also guide writing when explicitly invoked before a risky edit. DO NOT USE for factual/conceptual questions, CI/tooling config, git workflow, running/debugging tests, pure architecture discussion, prose writing, data analysis, or test-code review (use test-guard).
Writes, rewrites, diagnoses, and improves any LLM prompt with minimal, high-signal edits. Use when the user wants to create a new prompt from scratch, review or fix a prompt that produces poor output, simplify or tighten instructions, restructure a long prompt, port a prompt between models, or expand an existing prompt. Covers system prompts, agent instructions, CLAUDE.md rules, SKILL.md prompt bodies, chat templates, structured-output prompts, RAG context templates, and prompt strings embedded in code. Also use when editing any file whose primary content is LLM instructions.
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RAG", "create few-shot examples", "analyze token usage", or "design AI workflows". Use for prompt engineering patterns, LLM evaluation frameworks, agent architectures, and structured output design.
LLM prompt testing, evaluation, and CI/CD quality gates using Promptfoo. Invoke when: - Setting up prompt evaluation or regression testing - Integrating LLM testing into CI/CD pipelines - Configuring security testing (red teaming, jailbreaks) - Comparing prompt or model performance - Building evaluation suites for RAG, factuality, or safety Keywords: promptfoo, llm evaluation, prompt testing, red team, CI/CD, regression testing
Markdown documentation standards for LLM and Pandoc PDF. TRIGGERS - markdown standards, section numbering, documentation style.
Detect and flag AI-generated content markers in documentation and prose. Use when reviewing documentation for AI markers, cleaning up LLM-generated content, or auditing prose quality. Do not use when generating new content (use doc-generator) or learning writing styles (use style-learner).
Generate context-aware quality checklists for code review and QA using IEEE 1028 base standards plus LLM contextual additions
Use this skill when working with Apple's Foundation Models framework for on-device AI and LLM capabilities in iOS/macOS apps
Hugging Face Transformers best practices including model loading, tokenization, fine-tuning workflows, and inference optimization. Use when working with transformer models, fine-tuning LLMs, implementing NLP tasks, or optimizing transformer inference.
Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.
Build, validate, and deploy LLM-as-Judge evaluators for automated quality assessment of LLM pipeline outputs. Use this skill whenever the user wants to: create an automated evaluator for subjective or nuanced failure modes, write a judge prompt for Pass/Fail assessment, split labeled data for judge development, measure judge alignment (TPR/TNR), estimate true success rates with bias correction, or set up CI evaluation pipelines. Also trigger when the user mentions "judge prompt", "automated eval", "LLM evaluator", "grading prompt", "alignment metrics", "true positive rate", or wants to move from manual trace review to automated evaluation. This skill covers the full lifecycle: prompt design → data splitting → iterative refinement → success rate estimation.