All Agent Skills
41,263 results
- Life DesignerZhouYinLong-lab斯坦福人生设计课 AI 助手 — 基于 Bill Burnett 和 Dave Evans 的《斯坦福大学人生设计课》方法论， 通过 6-9 轮深度苏格拉底式追问，帮你：(1) 看清现状（健康/工作/娱乐/爱四个仪表盘）， (2) 区分重力问题与可设计的真问题，(3) 校准工作观与人生观指南针， (4) 发现心流时刻与能量模式，(5) 生成三个完全不同的五年奥德赛计划， (6) 输出 8000-12000 字的《个人人生设计蓝图》含原型行动清单。 Trigger keywords: 人生设计, 设计人生, life design, 人生蓝图, 奥德赛计划, 职业困惑, 人生方向, 人生规划, 斯坦福人生设计课, 重力问题, 心流, 工作观, 人生观, 原型行动, 设计思维, 帮我设计人生, 人生迷茫, 职业规划, 人生困惑, 人生选择, 五年计划。
- Load Resumption StateBerryKuipersLoad conductor workflow state from previous session and determine resumption point by analyzing git state and saved JSON state file
- Lowes CheckoutZincDiscover, buy, track, and return real products from Lowe's (lowes.com) through the Zinc API (zinc.com) — and from almost any other US retailer on the same API. Needs no account to begin — the agent mints its own test key, then earns a live key and a $5 starter credit once its operator approves it. Pay from a pre-funded wallet, per request over MPP or x402, or with a Stripe Link card.
- Machine LearningpluginagentmarketplaceSupervised/unsupervised learning, model selection, evaluation, and scikit-learn. Use for building classification, regression, or clustering models.
- meeting-sdk/linuxZoomZoom Meeting SDK for Linux - C++ headless meeting bots with raw audio/video access, transcription, recording, and AI integration for server-side automation
- Mem SearchthedotmackSearch rad-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.
- Metric Design ExperimentationParth SanganiUse when designing a metric framework, selecting a North Star metric, building a metric decomposition tree, designing A/B experiments, setting up retention cohort analysis, or diagnosing whether a metric is being gamed. Encodes NSM rubrics, Goodhart's Law countermeasures, statistical validity for PMs, and retention curve methodology.
- Mochi CreatorJoshuaOliphantCreate evidence-based spaced repetition flashcards using cognitive science principles from Andy Matuschak's research. Use when user wants to create Mochi cards, flashcards, study materials, or mentions learning, memorization, spaced repetition, SRS, Anki-style cards, or knowledge retention.
- Mr MetadataitsOmidKaramiWrites the title, labels, reviewers and description of the merge request Kraft opens from a finished branch, following the repository's own templates and rules. Use when Kraft is about to open that merge request, after the work is done and reviewed locally.
- Mr Metadata RepairitsOmidKaramiRepairs a merge request's metadata, such as a missing or wrong label or a missing description section, so its checks can pass. Kraft runs it as the on_failure repair of the merge request's CI wait, on every failure; it acts only when the failed job's trace names a label or a description section.
- Multi Channel PublishingParth SanganiUse when repurposing long-form content into channel-specific formats — LinkedIn posts, conference abstracts, podcast briefs, newsletter summaries, tweet threads, or spoken scripts. Encodes compression methodology, channel format rules, evidence density calibration, and audience adaptation. Produces channel-ready derivatives, not summaries.
- Multi Model ResearchkrishagelOrchestrate multiple frontier LLMs (Claude, GPT-5.1, Gemini 3.0 Pro, Perplexity Sonar, Grok 4.1) for comprehensive research using LLM Council pattern with peer review and synthesis
- NanobananagargantuaxGemini-native Nano Banana image generation and editing across Nano Banana, Nano Banana 2, and Nano Banana Pro. Use when you need text-to-image, image-to-image edits, repeated local references, batch generation, dry-run request inspection, or a custom Gemini-compatible base URL such as a self-hosted gateway.
- Narrative BuildingParth SanganiUse when building product positioning, crafting strategy narratives, preparing stakeholder pitches, writing launch narratives, or constructing the 'why now' story for a product or initiative. Encodes Narrative Arc Construction, April Dunford-inspired Positioning, Why Now analysis, Audience Adaptation, Evidence-Narrative Integration, Objection Anticipation, Competitive Narrative Analysis, and…
- Netapp VolumesDomino Data LabWork with Domino Volumes for NetApp ONTAP - enterprise-grade, multi-terabyte storage with near-instant snapshots. Covers volume creation, snapshot versioning with commit messages, cross-project sharing, mount paths (/mnt/netapp-volumes/ or /domino/netapp-volumes/), and the NetApp Volumes REST API.
- NetworkingpluginagentmarketplaceRetrofit, OkHttp, REST APIs, JSON serialization, network security.
- NextitsOmidKaramiRuns the next node of a Kraft Lite chain from its recorded state and reports the finished run's time and attempts per node. Use when continuing a chain: right after `kraft-lite:start`, after a gate answer, or in a new or cleared session. A chain blocked at a gate belongs to `kraft-lite:gate`; a read-only progress question belongs to `kraft-lite:status`.
- Ocr Servicelin-a1高精度光学字符识别（OCR）服务。支持多语言、多格式图像的文字检测与提取，并提供文本区域坐标与置信度评分，适用于文档数字化与图像内容分析。
- Office Automationtexiaoyao自动化处理 Word 和 Excel 文件。使用 Python 脚本读取、写入、格式化文档和表格。支持批量处理、模板填充、数据提取和格式转换。
- OnboarditsOmidKaramiConnects a repository to Kraft and verifies that its test and setup commands work in a fresh worktree. Use when a repo is not yet connected to Kraft, or a newly connected repo has not been verified. Config drift in an onboarded repo belongs to kraft:check, an unhealthy server to kraft:doctor.
- OracleandreasasprouStrategic technical advisor with two modes. Use for second opinions, architecture decisions, debugging, security analysis, and research. REPO MODE explores your codebase autonomously (finds gaps, reviews code, traces bugs). WEB MODE researches external info via @steipete/oracle CLI (current best practices, library comparisons, docs).
- Pixitrotsky1997Comprehensive guide for using Pixi, a fast and reproducible package management tool for Python, Rust, C/C++, and other languages. Use when (1) Managing Python project dependencies and environments, (2) Setting up reproducible development environments with conda and PyPI packages, (3) Creating cross-platform task runners and build pipelines, (4) Managing multiple isolated environments for testing…
- PlanitsOmidKaramiWrites the implementation plan for a work item from its human-approved spec, as small independently reviewable tasks. Kraft runs it as the library's plan_author task, after the spec gate and before implementation. Use when a chain needs that plan written or revised.
- Platform Integration (GitHub/GitLab)evangelosmeklisThis skill should be used when the user asks to "fetch GitHub issue", "get GitLab issue", "analyze GitHub PR", "search GitHub repo", "check GitLab commits", "use GitHub API", "use GitLab API", or mentions fetching data from GitHub or GitLab for incident investigation. Provides guidance for integrating with GitHub and GitLab APIs for RCA.