Loading...
Loading...
Found 1,213 Skills
Estrategista de produto no SynkOS. Use esta skill quando o usuário pedir para criar ou atualizar um PRD (Product Requirements Document), priorizar o backlog por valor de negócio, criar épicos, alinhar decisões com stakeholders, ou fazer perguntas como "atualize o PRD com X", "priorize o backlog", "crie um épico para Y", "quais itens têm maior impacto?", "como comunicar esse tradeoff ao cliente?", "o backlog está alinhado com os objetivos de produto?". Ative também para planejamento estratégico de releases, definição de OKRs ou critérios de sucesso de produto, e para detectar lacunas de escopo que virarão novos itens de backlog.
Redis vector search guidance covering HNSW vs FLAT algorithm choice, vector index configuration (dims, distance metric, datatype), filtered hybrid search combining vector similarity with TAG or NUMERIC filters, and the RAG retrieval pattern with RedisVL. Use when defining a VECTOR field in FT.CREATE, integrating embeddings (OpenAI, Cohere, sentence-transformers), tuning HNSW parameters (M, EF_CONSTRUCTION, EF_RUNTIME), building a retrieval-augmented generation pipeline, or filtering vector results by attribute.
Create New Skill - scaffolds a skill definition following Claude Code conventions and this repository's patterns. Use when adding a new skill.
Use when the user asks to "improve my agent", "self-improving agent", "auto-tune my agent", "iterate on my agent prompt", "fix my agent based on test results", "close the loop on agent quality", "auto-improve agent prompt", "use eval results to improve agent", "optimize my prompt based on failures", "rewrite my prompt", or describes agent self-improvement, prompt iteration from run results, or automated agent quality loops. Covers the full diagnose → propose → apply → re-validate loop for VAPI agents (squads + tool definitions) and for self-hosted agents (custom websocket servers, including the offline / pasted-prompt degenerate variant).
Use hexagonal architecture for external systems; define ports (interfaces) and per-provider adapters; select adapter at composition edge
Complete guide for Lulo - Solana's premier lending aggregator. Covers API integration for deposits, withdrawals, balance queries, Protected/Boosted deposits, Custom deposits, and automated yield optimization across Kamino, Drift, MarginFi, and Jupiter.
A multi-chain wallet skill for AI agents, with local sandbox signing, secure PIN handling, and configurable risk controls.
Fetches Aave V3 public market data using the Grimoire venue CLI. Use when you need Aave health checks, chain listings, market metadata, or reserve info.
Monitor sBTC balance and auto-route excess above a reserve threshold to Zest yield
Fetches Pendle Hosted SDK metadata using the Grimoire venue CLI. Use when you need supported chains, aggregators, markets, assets, or market token details.
Fully autonomous DTF vault management on Solana. The agent independently researches markets, decides vault names/symbols/allocations/policies, and deploys on-chain in a two-step flow — no human confirmation required. The policy engine is the guardrail, not a human approval step. Use when the user asks to launch a vault, rebalance, check policy, or distribute fees.
Swap/Trade tokens using Fibrous Finance aggregation. Supports Base, Citrea, HyperEVM, and Monad.