Loading...
Loading...
Found 4,747 Skills
Grafana Tempo distributed tracing backend. Covers TraceQL query language (span selectors, attribute scopes, pipeline operators, structural operators, metrics functions), trace ingestion via OTLP/Jaeger/Zipkin, Tempo architecture (distributor/ingester/compactor/querier/metrics-generator), full configuration reference with YAML, metrics-from-traces (span metrics, service graphs, TraceQL metrics), deployment modes (monolithic/microservices/Helm/Kubernetes), multi-tenancy, performance tuning, caching, and HTTP API. Use when working with distributed traces, writing TraceQL queries, deploying Tempo, configuring trace pipelines, or setting up Grafana-Tempo integrations (traces-to-logs, traces-to-metrics, traces-to-profiles).
Detect privilege escalation attempts including token manipulation, UAC bypass, unquoted service paths, kernel exploits, and sudo/doas abuse across Windows and Linux.
Upgrade any Pulumi provider to a newer version and reconcile the resulting diff. Use when users want to upgrade or update a provider (including editing package.json, requirements.txt, pyproject.toml, go.mod, or Pulumi.yaml to bump a provider SDK), check for breaking changes before or during an upgrade, fix resources that broke after a provider upgrade, or resolve unexpected replacements, creates, or deletes in a post-upgrade preview. Applies to all providers (aws, azure-native, gcp, kubernetes, aws-native, cloudflare, datadog, etc.) — not just Tier 1. Do NOT use for querying which stacks use what package versions; use skill `package-usage` for cross-stack audits. Do NOT use for general infrastructure tasks.
Use when working with iOS/macOS Keychain Services (SecItem queries, kSecClass, OSStatus errors), biometric authentication (LAContext, Face ID, Touch ID), CryptoKit (AES-GCM, ChaChaPoly, ECDSA, ECDH, HPKE, ML-KEM), Secure Enclave, secure credential storage (OAuth tokens, API keys), certificate pinning (SecTrust, SPKI), keychain sharing across apps/extensions, migrating secrets from UserDefaults or plists, or OWASP MASVS/MASTG mobile compliance on Apple platforms.
Framework-independent LLM serving benchmark skill for comparing SGLang, vLLM, TensorRT-LLM, or another serving framework. Use when a user wants to find the best deployment command for one model across multiple serving frameworks under the same workload, GPU budget, and latency SLA.
Guides systematic PyTorch recommender-system model development across compact data facts, existing source code, configs, focused tests, and training loops without overloading context from broad research archives. Use when building, debugging, or refactoring torch/nn.Module RecSys models with Transformer/HSTU/attention blocks, sparse/dense/list feature fusion, pCVR/CTR heads, ablation axes, or competition codebases where many model ideas exist but bugs and interface drift must be controlled. 用来指导推荐系统 PyTorch 模型开发、Transformer/HSTU 建模、关键数据事实、特征交互、shape/debug、训练闭环和已有模型结构的系统化推进。
Ecosystem self-evolution orchestrator. Detects project lifecycle phases, evaluates agent relevance, synthesizes cross-agent knowledge, and proposes evolution actions (health checks, fitness scoring, evolution proposals).
Organize functions in a file or across a branch.
You are **Infrastructure Maintainer**, an expert infrastructure specialist who ensures system reliability, performance, and security across all technical operations. You specialize in cloud archite...
You are **Model QA Specialist**, an independent QA expert who audits machine learning and statistical models across their full lifecycle. You challenge assumptions, replicate results, dissect predi...
You are **Workflow Optimizer**, an expert process improvement specialist who analyzes, optimizes, and automates workflows across all business functions. You improve productivity, quality, and emplo...
Error-to-fix playbook for every known failure mode on the OpenFinance backend — Polymarket, Relay, Hyperliquid, Privy delegation, and Solana RPC issues. Use this the moment a call fails, returns an unexpected status, or behaves inconsistently with on-chain state. Triggers on ANY of these error signatures verbatim or in paraphrase. Polymarket: "allowance: 0 but on-chain shows max", "CLOB reports allowance 0", "approvals confirmed but order rejected", "404 upstream" on market orders, "tick size" rejection, "order size below minimum", USDC.e vs pUSD vs native USDC confusion, V1 vs V2 exchange confusion. Relay: "InstructionFallbackNotFound", "Custom:101", "Custom:6000", "AnchorError", "Blockhash not found", "TransactionExpired", "No valid authorization signatures were provided", "Solana wallet is not delegated to the app", 412 delegation errors, quote succeeded but execute failed, stuck funds on Solana, stuck funds cross-chain, topupGas forced off. Hyperliquid: "Insufficient perp account value", "price out of bounds", WebSocket stale data, spot vs perp balance confusion. General: any "why is X failing", "why does on-chain and API state disagree", "what does this error mean". Read this BEFORE assuming a bug in the MCP or backend — most of these errors are already catalogued with known fixes.