Loading...
Loading...
Found 1,267 Skills
Framework adoption decision matrix: custom vs large frameworks in the Claude Code era. Use when evaluating whether to adopt a large framework or build custom with AI.
Create narrative lore entries that transform technical work into mythological stories. Use when generating agent memory, documenting changes as narrative, or building persistent knowledge through storytelling.
Query fan-out coverage for AI visibility. Covers semantic variation analysis and sub-question targeting.
Coin comparison. Use this skill whenever the user asks to compare two or more coins. Trigger phrases include: compare, versus, vs, which is better, difference. MCP tools: info_marketsnapshot_get_market_snapshot, info_coin_get_coin_info per coin (or batch/search when available).
Human-led curation of accumulated metis and guardrails. Surface patterns across sessions, propose what to promote, compact, or dismiss. Use after multiple sessions, before a new phase, or when search results feel noisy.
This skill should be used when the user asks to "audit prompts for safety", "check prompts for injection vulnerabilities", "manage a prompt catalog", "version control prompts", or "review prompt quality and compliance".
Подробная русскоязычная справка по Open WebUI: архитектура, авторизация, функции, пайплайны, API, RAG, масштабирование, отладка и скрытые возможности. Используй этот скилл при любых вопросах об Open WebUI — как он устроен, как развернуть, настроить авторизацию (OAuth, LDAP, JWT), написать функцию или пайплайн, подключить модель (Ollama, OpenAI), настроить RAG/knowledge base, масштабировать на production, отладить проблему. Также используй при написании кода для Open WebUI: функции (filter, pipe, action), пайплайны, конфигурации, docker-compose.
This is a skill for benchmarking the efficiency of automatic prefix caching in vLLM using fixed prompts, real-world datasets, or synthetic prefix/suffix patterns. Use when the user asks to benchmark prefix caching hit rate, caching efficiency, or repeated-prompt performance in vLLM.
Compare Replicate models by cost, speed, quality, and capabilities.
Discover PUDA experiment workflows for bears and choose the right experiment for the task. Use when you need to run, set up, or understand a PUDA experiment such as colour mixing optimization.
Read production traces, identify what's failing, and build failure taxonomies using open coding and axial coding methodology. Use when debugging agent or pipeline quality, investigating "why are my outputs bad?", or before building any evaluator — error analysis must come first. Do NOT use when you already have identified failure modes and need evaluators (use build-evaluator) or datasets (use generate-synthetic-dataset).
Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.