Loading...
Loading...
Found 2,493 Skills
Points to Michał Zalewski’s (lcamtuf) canonical American Fuzzy Lop (AFL) documentation at lcamtuf.coredump.cx/afl—coverage-guided fuzzing concepts, afl-fuzz usage, and historical technical notes for C/C++ targets. Use when the user cites AFL classic, lcamtuf’s AFL page, or needs the original upstream reference—not as a substitute for current AFL++ docs or authorized fuzzing policy.
Persistent key-value memory storage for agents. Store and recall information across conversations and sessions. Use when you need the agent to remember facts, preferences, or data between interactions.
Manage a team's tasks and use Box as the file storage backend
Shanghai-Shenzhen-Hong Kong Stock Connect capital flow analysis — tracks northbound (foreign capital buying A-shares) and southbound (mainland capital buying HK stocks) net flows, sector allocation, and AH-premium arbitrage signals. Triggers: "北向资金", "南向资金", "沪深港通", "陆港通", "外资流入", "北向净买入", "沪股通", "深股通", "北向加仓", "北向减仓", "北向資金", "南向資金", "滬深港通", "陸港通", "外資流入", "北向淨買入", "北向加倉", "northbound flow", "southbound flow", "Stock Connect", "Shanghai-Hong Kong connect", "foreign capital inflow", "smart money northbound".
ADR / H-share / A-share cross-market pricing analysis via Longbridge Securities — tracks the premium or discount between US-listed ADRs, HK-listed H-shares, and A-shares; calculates theoretical arbitrage spread; analyses constraints (FX controls, transaction costs, liquidity). Triggers: "ADR溢价", "ADR折价", "AH溢价", "ADR套利", "美股ADR", "三地比价", "跨市场套利", "双重上市", "ADR溢價", "ADR折價", "AH溢價", "ADR套利", "三地比價", "跨市場套利", "ADR premium", "ADR discount", "AH premium", "ADR arbitrage", "cross-listing premium", "dual-listed", "three-market comparison", "BABA ADR", "HK ADR".
Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.
Vendor-neutral skill to audit application logs for potential sensitive-data leakage and redaction coverage.
Read and write large cuPyNumeric arrays to HDF5 with Legate's parallel, distributed HDF5 I/O (legate.io.hdf5: to_file, from_file, from_file_batched). Use when a developer needs to save a cuPyNumeric array to an .h5/.hdf5 file, load an HDF5 dataset into a distributed cuPyNumeric array, read a large HDF5 dataset in chunks, hand arrays to an HPC pipeline as a single file, or accelerate HDF5 disk I/O with GPUDirect Storage (GDS). Do not use it for Parquet/cuDF/raw-binary or other sharded/custom layouts (see the cupynumeric-parallel-data-load skill), Zarr or object-store/S3 output, .npz or pickled archives, plain h5py without cuPyNumeric, or pure array compute such as FFT, matmul, or reductions.
Coverage-guided fuzzer built into LLVM for C/C++ projects. Use for fuzzing C/C++ code that can be compiled with Clang.
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when: keywords, file_patterns, code_patterns.
Run LLMs and AI models on Cloudflare's GPU network with Workers AI. Includes Llama 4, Gemma 3, Mistral 3.1, Flux images, BGE embeddings, streaming, and AI Gateway. Handles 2025 breaking changes. Prevents 7 documented errors. Use when: implementing LLM inference, images, RAG, or troubleshooting AI_ERROR, rate limits, max_tokens, BGE pooling, context window, neuron billing, Miniflare AI binding, NSFW filter, num_steps.
Offline-first mobile apps with local storage, sync queues, conflict resolution. Use for offline functionality, data sync, connectivity handling, or encountering sync conflicts, queue management, storage limits, network transition errors.