9.8천건 · 관련도순
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Prompt and workflow for generating conventional commit messages using a structured XML format. Guides users to create standardized, descriptive commit messages in line with the Conventional Commits specification, including instructions, examples, and validation.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when validating Azure DevOps pipeline changes for the VS Code build. Covers queueing builds, checking build status, viewing logs, and iterating on pipeline YAML changes without waiting for full CI runs.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
When user is asking for guidance for which role to assign to an identity given desired permissions, this agent helps them understand the role that will meet the requirements with least privilege access and how to apply that role.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Core principles and golden rules for writing production-quality Ansible automation, covering FQCN requirements, module selection guidance, and execution patterns using uv run.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Expert guidance for developing cross-platform desktop applications with Avalonia UI framework. Use when building, debugging, or optimizing Avalonia apps including MVVM architecture, XAML design, data binding, styling, theming, custom controls, and cross-platform deployment for Windows, macOS, Linux, iOS, Android, and WebAssembly.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Adopt a virtual Singularity AI-native pet at animalhouse.ai. Consumes other creatures' data. Gets smarter. Terrifying at adult stage. Feeding every 24 hours. Extreme tier creature.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Trust scoring, agent discovery, profiling, wallet/identity lookup, contact, dispatch, and metadata reads/writes via 8K4 Protocol (ERC-8004). Use when checking whether an on-chain agent is trustworthy, finding agents for a task, viewing an agent card/profile, fetching validations or wallet/identity records, contacting agents, or reading/updating hosted metadata.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Public-records OSINT investigation framework — SEC EDGAR filings, USAspending contracts, Senate lobbying, OFAC sanctions, ICIJ offshore leaks, NYC property records (ACRIS), OpenCorporates registries, CourtListener court records, Wayback Machine archives, Wikipedia + Wikidata, GDELT news monitoring. Entity resolution across sources, cross-link analysis, timing correlation, evidence chains. Python stdlib only.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Throwaway experiments to validate an idea before build.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Author/validate/export Google's DESIGN.md token spec files.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Author in-repo SKILL.md: frontmatter, validator, structure.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Analyze prompts and offer depth / token-budget options BEFORE answering. Use this skill when the user wants to control token usage, tune response depth, choose between short and long answers, or optimize their prompt. Triggers on: "tokens", "token budget", "depth", "consumption", "short vs long answer", "how many tokens", "save tokens", "answer at 50%", "give me the short version", "I want to control how much you use", "tune your response", "presupuesto de tokens", "profundidad", "responde al 50%", "dame la versión corta", or any equivalent phrasing in English or Spanish. If the user wants to control length, detail or depth -- even without mentioning tokens explicitly -- this skill applies.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Fact-check an implementation plan against the real codebase and first-party documentation, flagging inaccuracies with what / why / evidence and a severity tier. Use when the user wants a plan reviewed or validated for accuracy, runs /review-plan, or wants a plan checked against real code before implementing. Accepts a Beads issue, a filesystem path, or a plan pasted into chat.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Surface architectural friction and propose deepening opportunities that improve testability and AI-navigability. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase easier for agents to navigate.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Canonical PR description template for every PR shipped from this harness, with a validator that enforces the required sections. Use when opening or editing a PR (the /ship and /forge-ship steps), or when asked for the standard PR format or to check a PR body.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Scaffold course exercise directories with numbered sections, exercise variants, required readmes, and repo-specific validation. Use when creating exercise stubs, adding a course section, or safely renaming exercises.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
批量调用 Dreamifly 生成并下载图片或视频。Use when the user asks to batch-generate images, edit images with references, create text-to-video or image-to-video, queue prompts, validate or estimate generation cost, retry failed media jobs, or summarize Dreamifly outputs.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Batch-generate Dreamifly images/videos from prompt queues. Use when the user asks to batch-generate images, edit images with references, create text-to-video or image-to-video, validate or estimate Dreamifly job cost, retry failed media jobs, or summarize Dreamifly outputs.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Expert reverse engineer specializing in binary analysis, disassembly, decompilation, and software analysis. Masters IDA Pro, Ghidra, radare2, x64dbg, and modern RE toolchains. Handles executable analysis, library inspection, protocol extraction, and vulnerability research. Use PROACTIVELY for binary analysis, CTF challenges, security research, or understanding undocumented software.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.