Loading...
Loading...
Found 1,150 Skills
Use when you need multi-agent orchestration for OpenAI Codex CLI. Triggers on: omx, $plan, $ralph, $team, $autopilot, $deep-interview. v0.11.10 — 30+ agents, 35+ workflow skills, tmux team runtime, sparkshell, explore, ralplan.
Index skill for the blockint-skills bundle—includes a “choosing a skill” routing map and routes to focused skills on blockchain intelligence fundamentals, address clustering, analytics, tokenomics, investigation ethics, Phalcon Compliance documentation pointer, Chainalysis public Sanctions API/oracle router, FATF official AML/CFT glossary, Arkham Intel research article on leading crypto analysis tools for traders, Christoph Michel cmichel.io guide on becoming an EVM smart contract auditor, risk exposure, behavioral risk, address and transaction screening workflow concepts, Range AI investigation playbook (MCP), crypto market mechanics, OSINT (Bellingcat toolkit), Solana external stacks (Helius, Range MCP, Tavily, PayAI, React Flow, Solana Policy Institute), DeFi/MEV/rug skills, privileged-access mitigation lessons (Chainalysis Drift case study), coral-xyz sealevel-attacks Solana security examples, Neodyme Solana Security Workshop (workshop.neodyme.io), Osec (osec.io) Solana auditor introduction blog post, canonical X post citation for @armaniferrante status 1411589629384355840, BlockchainSpider open-source data collection, MoTS (Know Your Transactions / transaction semantics research repo), Impersonator dApp devtools (EVM + Solana read-only address presentation), Katana web crawling, lcamtuf American Fuzzy Lop (AFL) classic documentation (lcamtuf.coredump.cx/afl), and the official Agent Skills open-format specification (agentskills/agentskills, agentskills.io/llms.txt doc index). Use when the task spans multiple topics or the user needs help picking which named skill to load.
Builds multi-layer features as vertical end-to-end slices instead of horizontal layers. Each slice is verified before the next begins. Use when: starting any task that spans 2+ layers (DB, API, UI, tests), building CRUD features, implementing multi-step flows, decomposing features into subtasks, or planning implementation order.
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.
Buttons, inputs, pills, badges, calendars, and other interactive components form a visual family — they share the same border-radius, colour logic, shadow scale, border style, and spacing rhythm. Inconsistency between them breaks the sense of a coherent product. Use when building or reviewing a component library, design system, or any set of UI components.
Use when securing FastAPI API endpoints with JWT Bearer token validation, scope/permission checks, or stateless auth - integrates auth0-fastapi-api for REST APIs receiving access tokens from SPAs, mobile apps, or other clients. Also handles DPoP proof-of-possession token binding. Triggers on: Auth0FastAPI, FastAPI API auth, JWT validation, require_auth, DPoP.
Beehiiv platform help — newsletter publishing, audience growth, monetization (ad network, paid subscriptions, Boosts), referral programs, email automations, website builder, API. Use when beehiiv emails are going to spam on shared IPs, ad network isn't generating revenue, Boosts aren't converting, paid subscriptions have Stripe issues, automations are limited to 30 days, referral program rewards aren't working, website builder is buggy, or API calls are failing. Do NOT use for general newsletter monetization strategy (use /sales-newsletter) or growing your subscriber list strategy (use /sales-audience-growth).
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
Multi-perspective adversarial review. 4 Agents are spawned in parallel (full mode), each identifying issues from different perspectives, and the main thread makes a comprehensive ruling. Trigger methods: /story-review, /审查, "审查一下", "帮我审一下"
Build the optimal 250-byte Amazon backend search term string. Collects every candidate keyword, removes anything already indexed in the title and bullets, strips duplicates and Amazon-prohibited terms, prioritizes by search value, and packs the field to the byte limit. Use when a user asks about backend keywords, search terms, the hidden keyword field, generic keywords, "Search Terms" in the listing back end, or wants to fix wasted backend space. Trigger phrases: "backend keywords", "search terms field", "hidden keywords", "250 bytes", "generic keywords". Works with zero tools. the user pastes the current title, bullets, and any keyword list.
Layout structure for web interfaces, from grouping and alignment to reading order, progressive disclosure, and adaptive breakpoints. Use when structuring a page or component, spacing or aligning controls, deciding what collapses at small sizes, handling RTL layout direction, or reviewing frontend code for layout. Triggers on layout, spacing, alignment, grouping, negative space, whitespace, visual hierarchy, reading order, progressive disclosure, breakpoints, responsive layout, container queries, safe area, full-bleed, edge-to-edge, layout margins, RTL layout, logical properties.
CRITICAL: Use for concurrency/async. Triggers: E0277 Send Sync, cannot be sent between threads, thread, spawn, channel, mpsc, Mutex, RwLock, Atomic, async, await, Future, tokio, deadlock, race condition, 并发, 线程, 异步, 死锁