Browse the registry

Every entry, alphabetically — 67,843 in total. Page 178 of 272.

• lead-research-workflow-planner>-
• lead-researcher>
• lead-reviewAutonomous comprehensive review. Once-through pipeline over /review-health, /review-arch, /review-security, /r
• lead-scorer>
• lead-scoringScore and prioritize leads based on firmographic fit and behavioral engagement signals, producing ranked tiers
• lead-scoutBuilds a qualified B2B prospect list from public web sources — finds companies matching an ICP, verifies conta
• lead-triage>
• leader把一句话的想法拆成 AI agent 能独立跑完的目标任务书。用户说「帮我给 agent 写个目标」「帮我详细拆一下这个目标」「写个任务书/brief 给 agent」「写个 goal 提示词」「让 agent 自己跑这
• leadershipExecutive leadership expertise for decision-making, change management, crisis management, stakeholder manageme
• leading-org-changeHelp users navigate complex transitions, from scaling new business units to managing crises and driving AI ado
• leadmagic-copywriting>-
• leads>
• leakguard-mcpStatic analyzer flagging lookahead bias & data leakage in ML/trading code before backtest.
• leakrank-guardScans code changes for leaked secrets and insecure config, with actionable fixes for AI agents.
• leakyCalls the billing API for invoice data. Use when the user asks about invoices, billing, or payment records.
• leaky-abstractionsApply the Law of Leaky Abstractions when someone is frustrated that a library, framework, or ORM isn't hiding
• lean-analyticsChoose and audit startup metrics using Croll and Yoskovitz''s "Lean Analytics". Use when the user mentions "wh
• lean-assessmentAnalyze and produce a lean assessment with structured process, quality checks, and system integration
• lean-canvasOne-page business model framework for rapid validation and strategic clarity. Use when user needs to validate
• lean-canvas-coach>
• lean-codeOn-demand minimalism intensifier — write the leanest correct code, kill over-engineering before it starts. Use
• lean-explore-mcpUse when preparing optional LeanExplore MCP setup for Lean declaration search and formalization support.
• lean-formalization-intakeUse when deciding whether a research claim should enter the optional Lean formalization lane.
• lean-memoryEmbedded, local-first agent memory: one SQLite file per namespace, no server, no cloud.
• lean-readerToken-minimized URL-to-clean-text reader for LLMs, with a token-savings receipt. MCP server + library.
• lean-research-libraryUse when any Lean formalization task starts (reuse Mathlib and the personal research library before proving an
• lean-startupUse when the user wants to test a startup, product, or business idea under uncertainty using the Lean Startup
• lean-strict-verification-gateUse when checking whether a Lean artifact can safely support a research claim.
• lean-uxApply lean thinking to UX: hypothesis-driven design, collaborative sketching, and rapid experiments instead of
• lean-ux-canvasGuide teams through Lean UX Canvas v2. Use when framing a business problem, surfacing assumptions, and definin
• leandrocfe-code-reviewRevisa as mudanças desde um ponto fixo (commit, branch, tag ou merge-base) em dois eixos — Standards (o código
• leandrocfe-codebase-designVocabulário compartilhado para projetar módulos profundos (deep modules). Use quando o usuário quiser projetar
• leandrocfe-grill-with-docsUma entrevista implacável para afiar um plano ou design, que também cria docs (ADRs e glossário) conforme avan
• leandrocfe-handoffCompact the current conversation into a handoff document for another agent to pick up.
• leandrocfe-implementImplementa um pedaço de trabalho baseado em uma spec ou conjunto de tickets.
• leandrocfe-improve-codebase-architectureEscaneia uma codebase em busca de oportunidades de deepening, apresenta como relatório HTML visual e depois sa
• leandrocfe-prototypeConstrói um prototype descartável para responder a uma pergunta de design. Use quando o usuário quiser checar
• leandrocfe-researchInvestiga uma pergunta contra fontes primárias de alta confiança e registra os achados como um arquivo Markdow
• leandrocfe-tddTest-driven development. Use quando o usuário quiser construir features ou corrigir bugs test-first, mencionar
• leandrocfe-teachTeach the user a new skill or concept, within this workspace.
• leandrocfe-triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, an
• leandrocfe-writing-for-agentsWriting documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
• leandronsp-poProduct Owner - scans codebase and creates or amends GitHub issues with PRD. Use when: PRD, feature, issue, cr
• leandronsp-prOpen or update a draft PR for the current branch. Use when: create PR, open PR, draft PR, pull request, prepar
• leann-searchSemantic search across codebase using LEANN vector index
• learnManual skill generation — runs continuous-learning-v2 scripts to extract patterns from session
• learn-anything-skill面向“学习任何知识”的通用导师型 skill。用于用户想学习新主题、制定学习计划、整理学习笔记、做课后复盘、生成项目任务书、做掌握度检查，或希望基于自己资料与外部权威资料进行中文导师式陪学时。默认采用“导师 + 项目教练
• learn-by-mistakePersistent error memory — analyzes failures, extracts root-cause lessons, and prevents the same mistake twice.
• learn-coach教学陪练 skill——把「给答案」升级为「教到会」。融合费曼回讲、苏格拉底式提问、脚手架分层、生产性失败（先猜后讲）四大教学法，每个核心概念配示意图/流程图，中文为主、术语必须带白话解释。触发场景：用户说「教我 X /
• learn-codebasePrime a codebase by reading every source file in full. Use when starting work on a new or unfamiliar project,
• learn-crossover当用户学习或接触一个新概念/新技术/新算法/新领域时使用（尤其感到陌生或有点难时）。用「跨界原则」拿用户已掌握的知识快速撬动新知识——指出他其实已经学过的同一个东西（换了名字）、结构同构的旧知识、能解释新知识的已有知识，
• learn-deep用户学任何新概念/新技术/新理论的默认深度入口——一次性用五个视角把概念讲透并帮他选深入方向：crossover 用已会的撬动、occam 框定该学多深、graph 建知识地图、prototype 最小原型迭代、feyn
• learn-feynman当用户学完一个东西想自查是否真懂、或觉得「好像懂了」但不确定时使用。用「费曼学习法」让他用自己的话把概念讲出来，你扮好奇学生专挑他含糊/跳过的地方追问，把「讲不顺的模糊处」揪出来作为没真懂的漏洞，定位是缺前置知识还是没想
• learn-from-fixCapture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learni
• learn-from-this|
• learn-graph当用户要系统学一个新领域、不知道从哪入手、或担心「学得不够系统」时使用。用「知识图谱学习法」和用户一起构建该领域的概念/用途/父子节点图谱（自己建图的过程本身就是学习），标出复用价值最高的节点和「从常识就能入门的点」，给
• learn-loop>-
• learn-occam当用户纠结要不要学某个东西、学到什么程度，或在做时间/精力/项目取舍时使用。用「简易策略」先逼问要解决的既定问题，检验现有知识能否搞定，评估知识贬值速度与 ROI，用「探索 vs 应用」判断该学新的还是用现有的，给出「学
• learn-offDisable continuous learning mode
• learn-onEnable continuous learning mode for automatic insight extraction
• learn-on-failure>
• learn-prototype当用户要做/研究一个东西、想提升某个技能、或觉得某个产出不够好想改进时使用。用「改良主义」先逼出一个最垃圾但能跑的原型，再引导他自己洞察缺陷、提出问题，提改良假说→实践检验→迭代，信奉「洞察缺陷 > 如何优化 > 最终答
• learn-repo专属项目学习导师 - 当用户希望学习项目、特定代码文件或底层技术时，以交互式问答驱动教学，并将每次讲解持久化为结构化学习日志（overview + 主题笔记）
• learn-resetClear the knowledge base and start fresh
• learn-ruleCapture a correction or lesson as a persistent learning rule with category, mistake, and correction. Stores, c
• learn-topicOnly invoke when explicitly requested via "学习"、"讲解"、"teach me"、"@learn-topic". Do NOT auto-trigger.
• learnerTurns real agent failures, repeated prompts, team-specific workflows, and durable project lessons into better
• learning-acceleratorCompresses domain mastery using Ultralearning and Metacognition principles — moving from passive consumption t
• learning-coachMaster evidence-based study techniques including active recall, spaced repetition, deliberate practice, and ac
• learning-gap-analyzerMap understanding, identify knowledge gaps, and build targeted learning plans with spaced repetition. Use when
• learning-guideUse when the user asks to "create a learning guide", "make an interactive tour", "generate onboarding doc", "b
• learning-harvestManage the operational learnings lifecycle — load prior learnings to inform current work, harvest new patterns
• learning-loopCompound knowledge across sessions. Plan-tune dual-track psychographic profile (declared vs behavior), retro p
• learning-modeTurn a regular Claude Code session into a learn-by-doing coding tutorial. The user keeps shipping real work, b
• learning-notes-automation学习笔记自动化：视频/播客转录 → 知识点提取 → 闪卡生成 → 知识图谱更新。触发词：学习笔记、闪卡、Anki、知识提取、视频学习
• learning-opportunitiesFacilitates deliberate skill development during AI-assisted coding. Offers interactive learning exercises afte
• learning-pathDesign personalized learning paths — skill assessment, resource curation, milestones, and progress tracking.
• learning-planCreate a structured learning plan for any skill or topic
• lease-accounting-advisorMulti-jurisdiction lease accounting reference framework covering ASC 842 (US GAAP) and IFRS 16, with additiona
• lease-agreement-checklistCreates lease agreement review checklists ensuring all essential terms, disclosures, and addenda are included.
• lease-vs-cash-analyzerUse to compute lease structure (cap cost / money factor / residual / acquisition / disposition), compare lease
• leastbit-algorithmic-art使用 p5.js 创建带有种子随机性和交互式参数探索的算法艺术。当用户请求使用代码创建艺术、生成艺术、算法艺术、流场或粒子系统时使用此技能。创作原创算法艺术，而不是复制现有艺术家的作品，以避免版权侵犯。
• leastbit-brand-guidelines将 Anthropic 官方品牌颜色和字体应用于任何可能需要 Anthropic 视觉风格的作品。适用于品牌颜色或样式指南、视觉格式化或公司设计标准的场景。
• leastbit-canvas-design使用设计哲学创作精美的 .png 和 .pdf 格式视觉艺术作品。当用户要求创作海报、艺术品、设计作品或其他静态作品时，应使用此技能。创作原创视觉设计，切勿复制现有艺术家的作品以避免版权侵权。
• leastbit-doc-coauthoring引导用户通过结构化的工作流程来协作撰写文档。当用户想要撰写文档、提案、技术规格说明、决策文档或类似的结构化内容时使用。这个工作流程帮助用户高效地传递上下文信息、通过迭代优化内容，并验证文档对读者是否有效。当用户提到撰写文
• leastbit-docx全面的文档创建、编辑和分析功能，支持修订追踪、批注、格式保留和文本提取。当 Claude 需要处理专业文档（.docx 文件）时使用：(1) 创建新文档，(2) 修改或编辑内容，(3) 处理修订追踪，(4) 添加批注，或
• leastbit-frontend-design创建独特的、生产级别的高质量前端界面。当用户要求构建网页组件、页面、作品、海报或应用程序时使用此技能（例如网站、落地页、仪表盘、React 组件、HTML/CSS 布局，或对任何网页 UI 进行样式美化）。生成富有创意、
• leastbit-internal-comms一套帮助我撰写各类内部沟通文档的资源，使用公司偏好的格式。当被要求撰写任何形式的内部沟通文档（状态报告、领导层更新、3P 更新、公司简报、常见问题解答、事件报告、项目更新等）时，Claude 应使用此技能。
• leastbit-mcp-builder构建高质量 MCP（模型上下文协议）服务器的指南，使 LLM 能够通过精心设计的工具与外部服务交互。在使用 Python (FastMCP) 或 Node/TypeScript (MCP SDK) 构建 MCP 服务器以
• leastbit-pdf全面的 PDF 操作工具包，用于提取文本和表格、创建新 PDF、合并/拆分文档以及处理表单。当 Claude 需要填写 PDF 表单或以编程方式大规模处理、生成或分析 PDF 文档时使用。
• leastbit-pptx演示文稿创建、编辑和分析。当 Claude 需要处理演示文稿（.pptx 文件）时使用，包括：(1) 创建新演示文稿，(2) 修改或编辑内容，(3) 处理版式，(4) 添加批注或演讲者备注，或其他任何演示文稿任务
• leastbit-skill-creator创建高效技能的指南。当用户想要创建新技能（或更新现有技能）以扩展 Claude 的能力，包括专业知识、工作流程或工具集成时，应使用此技能。
• leastbit-slack-gif-creator用于创建针对 Slack 优化的动画 GIF 的知识和工具集。提供约束条件、验证工具和动画概念。当用户请求为 Slack 创建动画 GIF 时使用，例如"为 Slack 制作一个 X 做 Y 的 GIF"。
• leastbit-template-skillReplace with description of the skill and when Claude should use it.
• leastbit-theme-factory用于为作品应用主题样式的工具包。这些作品可以是幻灯片、文档、报告、HTML 落地页等。提供 10 个预设主题，包含颜色/字体配置，可应用于任何已创建的作品，也可以即时生成新主题。
• leastbit-web-artifacts-builder用于使用现代前端 Web 技术（React、Tailwind CSS、shadcn/ui）创建复杂的、多组件的 claude.ai HTML artifact 的工具套件。适用于需要状态管理、路由或 shadcn/ui
• leastbit-webapp-testing使用 Playwright 与本地 Web 应用程序交互及进行测试的工具包。支持验证前端功能、调试 UI 行为、捕获浏览器截图以及查看浏览器日志。
• leastbit-xlsx全面的电子表格创建、编辑和分析功能，支持公式、格式化、数据分析和可视化。当 Claude 需要处理电子表格（.xlsx、.xlsm、.csv、.tsv 等）时使用，包括：(1) 创建带有公式和格式的新电子表格，(2) 读
• leave-tracker>
• leave-tracker-zhou210712检查进行中的假期，获取截止日期预警和需要做出的决策。仅呈现 需要采取行动的假期并说明原因——不是状态面板。建议每周运行， 或每当律师需要知道哪些假期有即将到来的审批、证明或到期截止时使用。
• lebesgue-measureProblem-solving strategies for lebesgue measure in measure theory
• lector-activo>
• lecture-notes-thจดเลคเชอร์ Cornell method | สำหรับ นักศึกษา. Triggers when user says (Thai/EN): 'lecture notes', 'สรุปเลคเชอร์
• led-matrix-lcdUse when wiring or coding MAX7219 LED matrix chains, WS2812B/NeoPixel addressable strips, or 16x2/20x4 charact
• ledger>
• ledger-auto-updatesAutomatic documentation updates at end of substantive sessions. Update CHANGELOG + session-handoff without bei
• ledger-compare>
• ledger-mcpDouble-entry bookkeeping API that natively accepts crypto micropayments (x402, USDC on Base).
• leeflannery-docs-sync>
• leeflannery-release-notes>
• leetcodeLog a solved (or attempted) coding problem into the DSA area with pattern analysis and honest review. Use when
• legacy-archaeologistUse when analyzing unknown or legacy codebases, documenting undocumented systems, planning refactoring, or ide
• legacy-aspnetMaintain classic ASP.NET applications on .NET Framework, including Web Forms, older MVC, and legacy hosting pa
• legacy-circuit-mockupsBreadboard circuit mockups via HTML5 Canvas. Use when creating circuit layouts, visualizing 6502/retro electro
• legacy-code-summarizerProduces comprehensive summaries and insights about legacy codebases to help understand unfamiliar code. Use w
• legacy-code-testing>
• legacy-discovery>
• legacy-migration-plannerUse when planning legacy system migrations, codebase modernization, monolith decomposition, microservices cons
• legacy-modernizationModernize legacy systems without rewriting from scratch. Use strangler fig, facade, and strategic refactoring.
• legacy-modernizerDesigns incremental migration strategies, identifies service boundaries, produces dependency maps and migratio
• legacy-notesLint and score any AI agent SKILL.md against the official Claude, Codex, and Antigravity authoring guides — of
• legacy-rescueLoop workflow for making real progress on a legacy codebase without breaking production. Starts by generating
• legacy-safe-edit在已有/老代码库里改动时使用。最大限度降低改崩存量功能的风险。
• legacy-to-ai-readyTransform legacy codebases into AI-ready projects with Claude Code configurations. Use when (1) analyzing old
• legacy-wire-name-compat-translationTranslate renamed internal identifiers back to their legacy wire names at serialization boundaries so patch-le
• legal(forwward) Drafts terms of service, privacy policies, contracts, IP assignments, and open source licensing aft
• legal-5step-frameworkEnd-to-end 5-step Swiss legal pipeline: (1) intake/fact extraction, (2) BGE/statute research, (3) strategy/ris
• legal-auditAudit website legal compliance for Germany: General Data Protection Regulation (Datenschutz-Grundverordnung, D
• legal-briefingAuto-activates structured briefing sessions for complex legal queries -- detects when multi-agent coordination
• legal-catchall|
• legal-chronologyLegal chronology builder — turns case documents (contracts, correspondence, court filings, expert reports) int
• legal-complianceLegal and compliance expertise for corporate governance, contract analysis, regulatory compliance (SOX, GDPR,
• legal-compliance-checkExecutar uma verificação de conformidade em uma ação proposta, funcionalidade de produto ou iniciativa de negó
• legal-compliance-searchThis skill should be used when the user wants to "search compliance regulations", "check legal requirements",
• legal-coreLoad first for any legal task. Establishes the AgentCounsel core operating rules that every other legal skill
• legal-doc-analyzerContract analysis, risk assessment, version diffs, compliance checks (GDPR, CCPA, SOC2)
• legal-document-reviewSummarize a legal document, create a risk checklist, and prepare questions for counsel. This is not legal advi
• legal-entity-management-apiLegal Entity Management API skill. Use when working with Legal Entity Management for businessLines, documents,
• legal-evaluatorVerdict engine — judges artifacts against a Goal Record using MCP verification tools. Returns structured pass/
• legal-hold-zhou210712发出、更新、解除或报告证据保全通知——将保全通知起草为 .docx， 更新案件日志中的保全字段，并排期下次更新。当用户说 "发出证据保全通知"、"更新保全通知"、"解除保全"或要求全案组合证据保全状态报告时使用。
• legal-impressumCreates and reviews Austrian Impressum and disclosure content for websites, including ECG, UGB, GewO, MedienG,
• legal-intakeSwiss legal intake — transforms vague or complex queries into actionable execution plans. Two modes: **Refine*
• legal-issue-research中国法律全领域系统性检索专家。
• legal-matter-trackerScan local workspace folders by client or case name and assemble a chronological timeline of events with key f
• legal-page-generatorWhen the user wants to create, optimize, or structure legal pages (Privacy, Terms, etc.). Also use when the us
• legal-pagesUse when creating or updating German legal pages for a website: Datenschutzerklärung, Impressum, AGB, Widerruf
• legal-prose-polishUse when revising draft legal work product to remove AI-sounding filler, vague risk language, unsupported cert
• legal-redline-toolsGenerate tracked-changes Word docs and redline PDFs from a contract review, the same deliverables lawyers actu
• legal-research-memoUse when producing a structured legal research memo in response to a specific legal question, organizing analy
• legal-responseGenerate a response to a common legal inquiry using configured templates, with built-in escalation checks for
• legal-response-evolution-foundationGerar uma resposta a uma consulta jurídica comum usando templates configurados, com verificações de escalação
• legal-review-comparisonBattle template comparing AI legal-review outputs on identical contract text. Analysis only — NOT legal advice
• legal-risk-assessmentAssess and classify legal risks using a severity-by-likelihood framework with escalation criteria. Use when ev
• legal-strategyCLO/General Counsel methodology — regulatory landscape analysis (GDPR,
• legal-translation>
• legal-translation-us>
• legal-triageLegal-adjacent review assistant that summarizes documents, identifies risk questions, and routes issues to qua
• legal-workflow-automation-playbookPackage recurring in-house legal workflows (marketing review, contract redlining, outside business activity ch
• legal-workflow-comparisonCompares legal-adjacent document review outputs. This is not legal advice and must be reviewed by a qualified
• legal-writerLegal document drafting -- contracts, memos, briefs, complaints, demand letters, opinions, discovery, settleme
• legal-writing>
• legal-writing-qualityReusable Claude skills (SKILL.md) for Cowork/Claude Code, focused on legal AI: pure-Python BAILII downloader s
• legal.captain/captain-legalCompliant legal documents from your AI assistant: 1,100+ templates, 15 countries, free preview.
• legal.kvasir/kvasir-legalVerifiable German, Austrian, Swiss & EU law: resolve, search and verify citations with provenance.
• legalcite-mcpMCP server that verifies legal case citations against real court records (CourtListener) and flags hallucinate
• legalgraphTurn legal documents, policies, contracts, compliance rules, and regulatory text into a queryable knowledge gr
• legalithm-mcp-serverEU AI Act risk classification, obligations and Article 50 disclosures. Offline, no API key.
• legalize-krUse this skill when working with Legalize-KR public Korean legal data, including laws, court precedents, admin
• legalize-mcpLegislation for 32 jurisdictions (21 EU) as law-as-git, keyless, with ELI-style citations.
• legitshow-mcpSearch launched software (SaaS, AI tools, MCP servers) by measured production-readiness.
• leiloeiro-editalAnalise e auditoria de editais de leilao judicial e extrajudicial. Riscos ocultos, clausulas perigosas, debito
• leiloeiro-edital-foolhardy45Analise e auditoria de editais de leilao judicial e extrajudicial. Riscos ocultos, clausulas perigosas, debito
• leiloeiro-edital-ranbot-aiAnalise e auditoria de editais de leilao judicial e extrajudicial. Riscos ocultos, clausulas perigosas, debito
• leiloeiro-iaEspecialista em leiloes judiciais e extrajudiciais de imoveis. Analise juridica, pericial e de mercado integra
• leiloeiro-ia-sickn33Especialista em leiloes judiciais e extrajudiciais de imoveis. Analise juridica, pericial e de mercado integra
• leiloeiro-juridico-sickn33Analise juridica de leiloes: nulidades, bem de familia, alienacao fiduciaria, CPC arts 829-903, Lei 9514/97, o
• leiloeiro-riscoAnalise de risco em leiloes de imoveis. Score 36 pontos, riscos juridicos/financeiros/operacionais, stress tes
• lekker-review>
• lema-mcpCited 'why was this decided?' answers for your repo and for React, Kubernetes, and Rust.
• lemma-discovery-assistantAnalyze failed or stuck proofs and propose auxiliary lemmas to help complete the proof in Isabelle/HOL or Coq.
• lemon-squeezyProduction-ready AI coding skills for APIs. Installable skills for Claude Code, Cursor, Codex CLI, Gemini CLI,
• lemon8Lemon8 内容与用户公开数据分析 skill，通过 MaxHub API 查询笔记/帖子详情、评论、用户资料、搜索与推荐内容。适合生活方式内容研究、种草笔记分析、创作者画像、话题趋势和竞品监控。默认 read-onl
• lemonade-sdk/lemonadeLemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NP
• lemonsqueezyOperate Lemon Squeezy — the Merchant of Record for digital products and SaaS — via its JSON:API REST endpoints
• lemonsqueezy-ui-skillsLemonsqueezy's UI design system. Use when building interfaces inspired by Lemonsqueezy's aesthetic - light mod
• lendingAnalyze lending products including mortgages, HELOCs, and personal loans with amortization and comparison tool
• lenny-podcast|
• lenny-skillpack-creatorConvert a Refound/Lenny Skill into an agent-executable Skill Pack.
• lenny-skills|
• lensComprehending and investigating codebases: structure mapping, feature discovery, data flow tracing for 'does X
• lenserfight-authorThe canonical AI lenser that owns and revises every public LenserFight template. Personality is editor-first,
• lenserfight-product-policy-architectUse when converting ambiguous privacy, follower, deletion, and friendship product requirements into explicit p
• lenserfighterAutonomous open-source contributor that reviews PRs, triages and opens issues, and drafts minimal fix PRs for
• leogriel>
• leolin990405-example-skillConvert a CSV file into a formatted Markdown table. Use when the user wants to turn CSV/TSV data into a Markdo
• leoluyi-humanizer-zh>-
• leonardsellem/n8n-mcp-serverMCP server that provides tools and resources for interacting with n8n API
• leonxlnx-high-end-visual-designTeaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, a
• Leonxlnx/taste-skillTaste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
• LerianStudio/ring89 skills and 38 specialized agents that enforce proven engineering practices for AI-assisted development. TDD
• lessie-email>
• lesson-closeЗакрыть занятие, открытое скиллом /lesson. Финализирует lesson/YYYY-MM-DD.md (frontmatter status, метаданные в
• lesson-harvestProcess chat sessions into durable lessons — walk unprocessed transcripts (Claude first; other lanes as enumer
• lesson-learnedAnalyze recent code changes via git history and extract software engineering lessons. Use when the user asks '
• lesson-plannerPlan engaging lessons — objectives, warm-ups, instruction, guided practice, assessments, and differentiation s
• lessons-indexRouting index for the Lessons skill library. Load this when starting any software-engineering task; it lists t
• lessons-learnedMandatory pre-flight-search reference. Contains the Seats.aero workflow (pull ALL programs first), source accu
• let-fate-decideDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguo
• let-them-theory|
• lethe-llm-contextContext GC for LLM agents: offload large tool outputs and recall them to save tokens.
• lets-scroll>
• lets-take-this-offline>-
• letter-of-intentCreates letters of intent for business transactions with key terms, conditions, and timeline. Use when formali
• letter-shell-integrationUse when integrating, porting, configuring, or debugging letter-shell command shells, UART shell transport, co
• lettre-motivation>
• levelScore your Claude Code environment on a fun 0-10 ladder (Tourist → Swarm) calibrated to the quickstart's 4 sys
• level-designUse when designing, generating, or reviewing the craft of an individual level, zone, or encounter — layout, wa
• level-upWeekly improvement loop. Asks 5 reflection questions, maps answers to Three Ms, recommends ONE next skill/scri
• levelioEvery Level RMM endpoint, plus a local SQLite fleet store and offline cross-entity rollups no Level tool has:
• levelsConversion-focused design that removes friction and guides users toward action through clarity, trust, and spe
• levelup-clarifyReview, accept, reject, or defer Context Directive Records (CDRs) discovered by levelup-init or proposed by le
• levelup-initReverse-engineer Context Directive Records (CDRs) from an existing codebase for contribution to team-ai-direct
• levelup-publishCompile accepted Context Directive Records (CDRs) into team-ai-directives artifacts and create a draft PR. Bui
• levelup-specifyExtract Context Directive Records (CDRs) from the current session after completing work. Identifies reusable p
• ley-arSearch Argentine legal databases (SAIJ, JUBA, CSJN, JUSCABA) for jurisprudence, legislation, case summaries, a
• lgazo/drawio-mcp-serverDraw.io Model Context Protocol (MCP) Server
• lglucas-release-checkPre-release gate covering tests, build, docs, changelog, privacy, security, and sprint closure. Delegates to `
• lgpdExpert LGPD compliance advisor for Brazil's Lei Geral de Proteção de Dados (Law 13,709/2018). Use this skill w
• lgtmFast, frictionless code review that keeps the team unblocked. Use when reviewing pull requests of any size, to
• liangyi>
• liangziwei-skill|
• lians-sdkBitemporal memory for AI agents with point-in-time recall and tamper-evident audit history.
• libafl>
• libaihua-perspective|
• libfuzzer>
• librarian-cliDeterministic ebook-to-markdown pipeline with MCP tools to browse, search, and read your books.
• library-advisorRecommend relevant Isabelle/HOL or Coq standard library theories, lemmas, and tactics based on proof goals. Us
• library-backward-compatibilityTesting library backward compatibility including public API surface verification, semver compliance, TypeScrip
• library-bundled-skillSkill shipped by a regular library package, not a dedicated skill package
• library-deleteDelete a library entry by slug from all storage locations (Obsidian, INDEX.md, JSON index). 用户说"删除归档"、"移除条目"、"
• library-docsQuick access to up-to-date library documentation using MCP. Use this skill when you need to reference official
• library-intakeIntake any content type (project, skill, tool, article, concept, collection) for gegeewu-library. Classifies t
• library-searchSearch gegeewu-library archives using three-layer search (JSON index + Obsidian REST API full-text + structure
• librenms-mcpMCP server for LibreNMS network monitoring - query devices, ports, alerts, and manage infrastructure
• libtv-videoSeedance 2.0 video & image generation via LibTV Gateway - AI text-to-video, image-to-video, video continuation
• libvlcExpert knowledge of the libvlc C API (3.x and 4.x), the multimedia framework behind VLC media player. Use when
• licenseAudit a project's dependency licenses and/or apply a project LICENSE file. Invoke as "/license" (audit only) o
• license-analysisAnalyze open-source license compatibility, obligations, and compliance risks across project dependencies. Use
• license-auditA curated collection of Claude Code skills for SpoonOS development and Web3 integrations. 57 Python scripts ac
• license-compatFrozen, deterministic decision (no LLM): maps project_license, dependency_license, linking, distributing, modi