全部 Agent Skills
41,263 个结果
- Lit Searchhongtongzhou-design文献检索与筛选规范。当用户要求围绕某个课题检索学术文献、做系统综述检索、制定纳入/排除标准、或把候选文献筛选成最终清单时使用。按深度分档（快筛/标准/严格检索）执行，检索过程全程留痕可复现。严格检索档不等于完整系统综述。产出 papers/screening.md、papers/included.md、papers/included.json、papers/to-fetch.md、papers/to-fetch.ris、papers/endnote-import.ris。
- Lit Watchhongtongzhou-design文献监控规范。当用户要求跟踪某个课题的最新文献、订阅 arXiv/期刊关键词、做每日/每周新文献巡检，或流水线中配置了文献监控步骤时使用。按 papers/watchlist.md 的关键词检索新文献，去重、精选后把命中追加到 notes/inbox.md。
- Live CheckHanafubukiLoad the working copy of prismantis into a real Claude Code session and render how replies draw, with no screenshot. Use after any visual change, when asked to "screenshot", "see it", "try it live", or before claiming a rendering fix works.
- Live CopygwpicardWork with the live copy safely. Pass a secret a check needs by its location, ask before any change to a live service, and roll back to an earlier version on a yes. Used by setup-hosting, maintain, merge, repair and what-now.
- Live CopygwpicardWork with the live copy safely. Pass a secret a check needs by its location, ask before any change to a live service, and roll back to an earlier version on a yes. Used by setup-hosting, maintain, merge, repair and what-now.
- Livekit Agent ToolsOkeysir198Comprehensive guide for building functional tools for LiveKit voice agents using the @function_tool decorator. Use when creating tools for LiveKit agents to enable capabilities like API calls, database queries, multi-agent coordination, or any external integrations. Covers tool design, RunContext handling, interruption patterns, parameter documentation, testing, and production best practices.
- Livewire PrinciplesohnotnowPrinciples for writing simple, maintainable Laravel/Livewire code. Use when writing Livewire components, tests, or Blade views. Focuses on avoiding over-engineering.
- LlamaindexalivirgoBuild LlamaIndex ingestion, retrieval, and query pipelines and evaluate RAG behavior on task-relevant examples.
- Llm Cost Latency BenchmarkalivirgoBenchmark AI workflow cost and latency with TTFT/TPOT/ITL/e2e percentiles, cache-aware token billing, goodput under SLOs, and a quality floor. Use before claiming a model, prompt, or infra change is cheaper or faster.
- Llm Json Contract CheckalivirgoValidate AI-generated JSON against schema and business rules, separating refusals, truncation, parse failures, schema violations, and domain invariant breaches. Use before any tool call, DB write, or external side effect consumes model output.
- Llmtrack Release CommitrustrakPrepara el release commit con changeset. Use when user says 'prepare release commit' or 'create release version' or 'hacer release'.
- Lm Studio Local OffloadingalivirgoRoute suitable mechanical tasks to locally hosted models through LM Studio or Ollama and verify their outputs.
- Lnazhuga79Локализация РФ. Локальные нормативные акты: кто вправе принимать (ст. 8 ТК), запрет ухудшать положение работника против ТК / коллективного договора, учёт мнения профсоюза (ст. 372), ознакомление под роспись до начала работы и при изменении (ст. 22, 68), последствия неознакомления.
- local-agentsghosthat-studioGuides building, configuring, running and debugging agents on locally hosted models (Ollama, vLLM, llama.cpp, LM Studio, MLX, opencode, any local OpenAI-compatible endpoint) - measuring the stack and memory, choosing engine and model, sizing context, chunking and rolling history, stop-reason loops, tools, prompts, forced structured output, extraction and reconciliation, coding and review agents…
- LocalizeJoblessJoeUse the user's local LLM so bulk tokens stay out of your context. Use when you are about to run a test suite, build or command with long output, read a log, or open a large file just to find one thing (offload); when you need to look something up on the web, check docs or verify current versions (research, instead of WebSearch/WebFetch); or when asked to add, write or implement a small function…
- Lode Agent Corebinary1215Initialize, recover, or operate a provider-neutral Lode Project with common user direction and independently routed logical Sessions, graph-first discovery, direct work, optional bounded delegation, and durable recovery. Use for Lode Agent Core, context recovery, compaction, selected context handoff, multi-step Runs, or worker coordination.
- Lode Agent Onboardingbinary1215Explicitly activate or resume optional Lode Product, World, Graph, or governed-document onboarding inside Claude Code, Codex, or OpenCode, including bounded source/storage choices and evidence-linked semantic proposals and review.
- Lode Conversationbinary1215Explain Lode work using available context, including material choices, meaningful progress, failures and results. Use for user-facing Lode conversations, not general writing or deciding execution and recovery authority.
- Logic AuditsrinitudeUse when finding contradictions or reasoning gaps.
- Logic ProalivirgoAutomate Logic Pro MIDI with Scripter JavaScript, configure Audio Units, and troubleshoot CoreAudio or spatial-audio workflows.
- Logit Bias Token SteeringalivirgoConfigure token-bias controls on supporting model APIs for constrained generation, then validate the returned values.
- Lokalisasi Slang IndonesiaadamriofcTranslate or adapt standard English marketing copy into natural Indonesian business casual or colloquial slang.
- Looker Studio Reportyusuke-suzukiDesign Looker Studio reports for ongoing monitoring. Use when creating reports to visualize operations, costs, or metrics.
- LosslesscutalivirgoTrim and join media with LosslessCut, inspect keyframe boundaries, and choose between stream copying and smart-cut rendering.