3,610 skills found · Page 16 of 121
google / google-cloud-networking-observabilityInvestigates Google Cloud networking issues by analyzing GCP logs, metrics, and diagnostics
google / gke-golden-pathProvides GKE golden path configuration defaults, production readiness checklists, and cluster default patterns
google / iam-helper-for-policy-managementStreamlines the creation, modification, and management of IAM allow policies (v1) and deny policies (v2). Manages access control across Resource Manager resources (Organization, Folder, Project) and individual resources
NVIDIA / skill-inspectorReview AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review
muratcankoylan / context-degradationThis skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-pattern issues, and agent performance degradation caused by accumulated or conflicting context.
muratcankoylan / context-optimizationThis skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy, partitioning, token-cost reduction, retrieval scoping, and extending effective context capacity without lowering answer quality.
muratcankoylan / multi-agent-patternsThis skill should be used when designing multi-agent systems that need context isolation, supervisor or swarm coordination, explicit handoffs, parallel execution, or a decision on whether multiple agents are justified.
muratcankoylan / context-compressionThis skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve decisions, files, risks, and next actions.
muratcankoylan / self-managed-contextThis skill should be used when a model gets read-write control over its own live context window instead of a harness-scheduled compaction policy: the context exposed as an editable file the model rewrites with code tools, model-driven eviction and in-place updates, the harness invariants that keep s…
muratcankoylan / latent-briefingThis skill should be used when the user asks to \"share memory between agents\", \"KV cache compaction for multi-agent\", \"orchestrator worker context\", \"latent briefing\", \"reduce worker tokens\", \"cross-agent memory without summarization\", or discusses Attention Matching compaction, recursiv…
wanshuiyin / kill-argumentTwo-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical issues
wanshuiyin / paper-claim-auditZero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh cross-model reviewer with NO prior context to prevent confirmation bias
wanshuiyin / paper-slidesGenerate conference presentation slides (beamer LaTeX → PDF + editable PPTX) from a compiled paper, with speaker notes and full talk script
wanshuiyin / semantic-scholarSearch published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /arxiv (preprints) with citation counts, venue metadata, and TLDR
wanshuiyin / dse-loopAutonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout
wanshuiyin / lean-formalizeDevelop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff
wanshuiyin / paper-figureGenerate publication-quality figures and tables from experiment results
wanshuiyin / meta-applyPrivileged applier that LANDS meta-optimize / corpus-audit patches the user approved — the ONLY skill permitted to mutate the skill corpus from a self-modification proposal, with cross-model jury and human approval at landing
wanshuiyin / invention-structuringStructure a raw invention idea into a formal invention disclosure
wanshuiyin / patent-reviewGet an external patent examiner review of a patent application
wanshuiyin / figure-descriptionProcess user-provided patent figures and generate formal drawing descriptions
wanshuiyin / paper-writeDraft LaTeX paper section by section from an outline
wanshuiyin / pixel-artGenerate pixel art SVG illustrations for READMEs, docs, or slides
wanshuiyin / vast-gpuRent, manage, and destroy GPU instances on vast.ai
wanshuiyin / embodiment-descriptionWrite detailed embodiment descriptions for patent specifications
wanshuiyin / proof-writerWrites rigorous mathematical proofs for ML/AI theory
wanshuiyin / patent-novelty-checkAssess patent novelty and non-obviousness against prior art
larksuite / lark-slides飞书幻灯片：创建和编辑幻灯片。创建演示文稿、读取幻灯片内容、管理幻灯片页面（创建、删除、读取、局部替换）。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。当用户给出 doubao.com 的 /slides/ URL/token 时，也应直接使用本 skill，不要因为域名不是飞书而回退到 WebFetch；路由依据是 URL 路径模式和 token，而不是域名。不负责：云文档内容编辑（走 lark-doc）、云文档里的独立画板对象（走 lark-whiteboard）、上传或下载普通文件（走 lark-drive）。
larksuite / lark-calendar飞书日历：管理日历日程和会议室。查看/搜索日程、创建/更新日程、管理参会人、查询忙闲和推荐时段、预定会议室。当用户需要查看日程安排、创建/修改会议、查询/预定会议室时使用。不负责：查询过去的视频会议记录（走 lark-meeting）、待办任务（走 lark-task）。
larksuite / lark-meeting飞书视频会议：查询会议记录与会议产物(纪要/逐字稿/妙记)、妙记搜索/上传/下载/编辑、机器人参与会议；查询进行中的会议、实时会议内容(发言/聊天/共享文档)问答(会上/会里)、发送会中聊天/表情；基于 meeting_id、meeting_no、event_id、note_id、minute_token、vc-node-id 或妙记 URL 查询相关信息。预约会议、忙闲和会议室管理走 lark-calendar。
