Loading...
Loading...
Found 6,941 Skills
Expert guidance on AI Agent Harness architecture based on the comprehensive Claude Code analysis book
Analyze a software codebase for algorithmic complexity and performance hotspots, then propose or implement safe optimizations without breaking behavior. Use when Codex is asked to scan many files, find inefficient loops, nested iteration, repeated scans, costly rendering/recomputation, N+1 queries, avoidable O(n^2) or O(n) operations, or reduce complexity such as O(n^2) to O(n log n) / O(n), while preserving tests, APIs, outputs, and maintainability.
BepInEx-based cooperative multiplayer mod for Subnautica 2 with synchronized session management, shared inventory, and dynamic scaling
Maintain portfolio allocations over time using calendar-based, threshold-based, and tax-efficient rebalancing strategies. Use when the user asks about when to rebalance, rebalancing bands, transaction cost trade-offs, tax-efficient rebalancing, or the rebalancing premium. Also trigger when users mention 'my portfolio drifted', 'how often should I rebalance', 'rebalancing across taxable and IRA accounts', 'volatility harvesting', 'buy low sell high automatically', or ask whether to use cash flows to rebalance.
Guides information security engineering—implementing and operating security controls, identity and access systems, encryption and secrets management, security tool integrations (SIEM, EDR, SOAR), cloud guardrails, hardening baselines, and remediation engineering for vulnerabilities. Use when building SSO/RBAC/PAM patterns, configuring KMS or certificate lifecycle, deploying WAF/DLP or EDR connectors, writing security-as-code policies (OPA, SCPs, CIS benchmarks), integrating logging to SIEM, automating security workflows, or validating control fixes—not for SOC triage (soc-analyst), pentesting (penetration-tester, network-pentester, web-pentester), red team (red-team-specialist), CI gates only (devsecops), platform provisioning without security ownership (infrastructure-engineer), CISO/exec program (chief-information-security-officer), security program strategy (cybersecurity), GRC program and audit prep (compliance-specialist), or product tenancy isolation (product-infrastructure-security-engineer).
Select and configure evaluation metrics for an AI agent. Guides through metric selection using use-case recommendations, custom LLM-based metric creation with prompt engineering, and agent default attachment. Use when user says "set up metrics", "configure metrics", "create a metric", "what metrics should I use", "add evaluation criteria", or "customize scoring".
Write a high-quality prompt for any LLM or AI assistant — Claude, Claude Code, ChatGPT, Gemini, Cursor, Windsurf, Copilot, or any coding / chat agent. Use this skill whenever the user asks to write, improve, refine, shorten, or rewrite a prompt; asks "how should I phrase this for [model]" or "what's a good prompt for [task]"; describes a task they want an AI to do but hasn't yet formulated it as a prompt; or pastes an existing prompt and asks for revision. Based on Boris's (Anthropic, Claude Code creator) prompt methodology — short and accurate prompts, plan-before-code, feedback loops, persistent context in files. The universal principles (short, plan-first, feedback-loop, no-padding) apply to any LLM; the Claude-Code-specific anchors (CLAUDE.md, @file, slash commands) only apply when the target is Claude Code. If the user's intent is unclear (target model, deliverable, scope, or whether the AI has a way to self-verify is missing), ask 1–3 targeted clarifying questions via AskUserQuestion before writing the prompt.
Fast synchronous key-value storage for React Native via react-native-mmkv (Nitro-backed). Covers creating and configuring MMKV instances, reading/writing all value types (string, number, boolean, buffer), React hooks for reactive UI, value-change listeners, encryption, AsyncStorage migration, and state-management integrations (zustand, redux-persist, jotai, react-query). Also covers storage limits, multi-process mode, and the V4 upgrade from the class-based API.
Run commands inside a remote Docker container via the file-based command relay (tools/debugger). Use when the user says "run in Docker", "run on GPU", "debug remotely", "run test in container", "check nvidia-smi", "run pytest in Docker", or needs to execute any command inside a Docker container that shares the repo filesystem. Requires the user to have started server.sh inside the container first.
Systematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper. Covers the Three Walls framework, parallel folding, recompute strategy, dispatcher choice, and CUDA-graph bring-up.
Use this skill when the user asks about Goldsky Edge — the managed RPC endpoint service for EVM chains. Triggers on: 'Edge RPC', 'Goldsky RPC endpoint', 'edge.goldsky.com', 'eth_getLogs is slow', 'RPC rate limit', 'hedged requests', 'flashblocks', 'HyperEVM system transactions', 'x402 pay-per-request RPC', 'Goldsky Edge pricing', 'Edge dashboard', 'gs_edge_ API key', 'rpc-edge'. Also use this skill when the user wants a resilient, low-latency JSON-RPC endpoint for EVM chains (Ethereum, Base, Arbitrum, Optimism, Polygon zkEVM, BSC, Avalanche, Berachain, HyperEVM, Monad, Sei, Sonic, Unichain, zkSync, etc.), is debugging RPC errors like -32005/-32012/-32014/-32015/-32016, or is comparing providers (Alchemy, Infura, QuickNode, Ankr) against Edge. For questions about self-hosting eRPC or custom eRPC configuration beyond what Edge exposes, point them at https://docs.erpc.cloud/llms.txt. Do NOT trigger on Goldsky Mirror, Turbo, or Subgraph pipeline questions — those belong to their respective skills.
Audit and harden a repository test suite so tests carry their weight. Use when the user asks whether tests are useful, flaky, duplicated, slow, under-covering critical behavior, missing contract/regression coverage, or when a codebase needs a test strategy before major refactors, releases, security work, or production hardening.