一个技能，一个新的可能。找到适合你的 AI 工作流。
smoke-tests
【开发与工程】Use when running VS Code smoke tests or working on smoke-test CI steps. Covers npm run smoketest / smoketest-no-compile, grep filtering tests, and a temporary repeat-loop technique for tracking down flaky smoke tests in CI.
reverse-engineer-anything
【数据与研究】Reverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.
status-card-query
【效率与协作】Create and maintain agent-authored Paperclip status cards, or compile a prose interest prompt into bounded CompanySearchQuery objects and write the first summary from the assigned Summarizer run.
dnanexus-integration
【数据与研究】Builds and operates reproducible genomics workloads on DNAnexus with the dx CLI, dxpy, apps/applets, native workflows, dxCompiler, and Nextflow. Supports DNAnexus data transfers, dxapp.json development, execution monitoring, workflow import, and project automation.
research-lookup
【数据与研究】Compiles current scholarly evidence for a scientific manuscript or research brief when the user explicitly asks to gather literature, references, background evidence, competing findings, or a manuscript research packet. Uses Parallel Search by default, Parallel Extract for source retrieval, Parallel Research for explicitly deep/exhaustive work, optio…
anywrite
【开发与工程】Compiled CLI covering all 52 endpoints of the Anytype local API — objects, properties, tags, search, chat, files — one binary, no MCP server needed.
binary-analysis-patterns
【数据与研究】Comprehensive patterns and techniques for analyzing compiled binaries, understanding assembly code, and reconstructing program logic.
compile-knowledge
【效率与协作】Compile durable, non-obvious findings into an interlinked markdown knowledge store — atomic files, [[wiki-links]], a maintained index — so an agent gets smarter across sessions instead of relearning the same facts.
entropy-box
【效率与协作】Entropy Box knowledge-compiler for embodied-AI: turns bounded requirements into grounded workflows via Solution Consult, Search, Lookup, and Evidence. Do not use it to control physical robots.
reverse-engineering
【数据与研究】General reverse-engineering methodology for compiled, obfuscated, packed, or virtualized targets: GDB, Frida, angr, Unicorn, and Qiling workflows across languages and platforms, with anti-analysis countermeasures.
unity-ecs-patterns
【数据与研究】Production patterns for Unity's Data-Oriented Technology Stack (DOTS) including Entity Component System, Job System, and Burst Compiler.
zeroize-audit
【数据与研究】Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C/C++/Rust code handling secrets, keys, passwords, or other sensitive data.
agent-harness
【数据与研究】Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or …
cli-e2e-testcase-writer
【开发与工程】Use when adding or updating Go CLI E2E coverage for one `tests/cli_e2e/{domain}` domain of the compiled `lark-cli`, especially when the work requires live `--help` or `schema` exploration, scenario-based `clie2e.RunCmd` workflows, and per-domain `coverage.md` maintenance.
ara-compiler
【文档与办公】Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, concepts, heuristics), physical layer (configs, code stubs), exploration graph, and grounded evidence. Use when ingesting a paper or codebase into a structu…
distributed-llm-pretraining-torchtitan
【效率与协作】Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
presenting-conference-talks
【文档与办公】Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.
huggingface-zerogpu
【开发与工程】AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring `python_version` or `requirements.txt` for a ZeroGPU Space, or handling ZeroGPU-specific code constraints — pickle-based process isolation, `gr.State` semantics across the worker boundary, no `torch.comp…