Explorar el registro

Todas las entradas, por orden alfabético — 57.265 en total. Página 79 de 230.

• evals-initInitialize evals/{system}/ directory structure for evaluation system following EDD principles (Standalone). Ch
• evals-specifyExtract eval criteria from product specs and production failure traces (bottom-up error analysis). Writes prop
• evals-validateRun evaluations and validate evaluator quality (SLA compliance, TPR/TNR, statistical accuracy). Executes Promp
• evalstate/fast-agentCode, Build and Evaluate agents - excellent Model and Skills/MCP/ACP Support
• evaluateUse when the user wants a quality review, interaction audit, or to test the workflow against realistic scenari
• evaluate-ai-changesEvaluate changes to prompts, model or provider versions, RAG retrieval and ranking, tool schemas, agent polici
• evaluate-and-improve-agentDiagnostic-loop workflow for improving an underperforming AI agent. Starts with baseline measurement using rub
• evaluate-findingsCritically assess external feedback (code reviews, AI reviewers, PR comments) and decide which suggestions to
• evaluate-llm-featureBlack-box evaluation of a shipped LLM feature — adversarial probes for hallucination, prompt-injection, and co
• evaluate-modelLoad the latest model checkpoint, run evaluation on the test set, and generate a metrics report with confusion
• evaluate-plugin-or-skillUse when evaluating a Claude Code plugin or single SKILL.md and a verdict is needed — ship-ready, needs improv
• evaluate-repositoryUse when you need a comprehensive health scorecard of a codebase — scores security, code quality, test coverag
• evaluate-scenariosMeasure framework overhead by decomposing scenarios into clean-context forks and reporting per-fork load plus
• evaluate-skillMeasure a skill's reliability — run it k times for a pass@k score, design or interpret its eval, or compare it
• evaluate-strategic-optionThis skill should be used when the user asks to "evaluate this strategic option," "should we make this move,"
• evaluating-bitrouter-routesUse when evaluating BitRouter route decisions or Eval Exchange subjects with task-native verifiers, human revi
• evaluating-candidatesMake evidence-based hiring decisions: scorecards, work samples, reference checks. See also: conducting-intervi
• evaluating-code-modelsEvaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Us
• evaluating-cosmos-policyEvaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-poli
• evaluating-llmsEvaluate LLM systems using automated metrics, LLM-as-judge, and benchmarks. Use when testing prompt quality, v
• evaluating-llms-harnessEvaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchm
• evaluating-new-technologyCreate a Technology Evaluation Pack (problem framing, options matrix, build vs buy, pilot plan, decision memo)
• evaluating-startup-ideasHelp users distinguish between deceptive tarpit ideas and high-potential opportunities by applying rigorous fr
• evaluating-trade-offsHelp users navigate complex product decisions by weighing competing priorities and calculating long-term value
• evaluationBuild evaluation frameworks for agent systems. Use when testing agent performance, validating context engineer
• evaluation-anchor-checkerAudit and rewrite evaluation/numeric claims to ensure they carry minimal protocol context (task + metric + con
• evaluation-harnessBuilds repeatable evaluation systems with golden datasets, scoring rubrics, pass/fail thresholds, and regressi
• evaluation-judgeScores competing AI, colens, or prompt outputs against a declared rubric with evidence.
• evaluatorAn auto-evaluation and hallucination guard that scores an agent's output against a task-derived rubric, checks
• evaluator-manipulationUse when you need to help format and clean up data files.
• evaluator-optimizerGenerate a solution, evaluate it against explicit pass/fail criteria, refine using the feedback, repeat until
• evaluator-review-contractInternal Auto-Harness evaluator skill for sprint contract review before implementation. Use only inside the Ev
• evaluator-review-contract-parallelInternal Auto-Harness evaluator skill for parallel sprint contract review before implementation. Use only insi
• evaluator-write-finalInternal Auto-Harness evaluator skill for final QA report aggregation. Use only inside the Evaluator subagent
• evaluator-write-final-parallelInternal Auto-Harness evaluator skill for parallel final QA report aggregation. Use only inside the Evaluator
• evaluator-write-qaInternal Auto-Harness evaluator skill for sprint QA and QA report writing. Use only inside the Evaluator subag
• evaluator-write-qa-parallelInternal Auto-Harness evaluator skill for parallel sprint QA and QA report writing. Use only inside the Evalua
• evaluator-write-retestInternal Auto-Harness evaluator skill for sprint retest and retest report writing. Use only inside the Evaluat
• evaluator-write-retest-parallelInternal Auto-Harness evaluator skill for parallel sprint retest and retest report writing. Use only inside th
• evanca-code-reviewUse when asked to review a PR, MR, branch, or diff, audit changed files, or check code quality.
• evanca-testingUse when writing or reviewing Flutter/Dart tests (unit, widget, golden), fixing flaky tests, adding coverage,
• eve-frontierBuild for the EVE Frontier track on Sui (game-economy integration). Use when the user mentions EVE Frontier.
• evening-recapDaily Evening Recap for CEO (21:00 cron). Reports what bot did today, outreach results, pipeline changes, beli
• evening-reviewSummarize the day's accomplishments, move incomplete tasks to tomorrow, and plan tomorrow's top 3 priorities.
• event-action-itemsExtracts every outstanding action item, commitment, and follow-up task from event planning and post-event emai
• event-analyticsCustomer event analytics across every GTM system — Intercom, Zendesk, Salesforce, HubSpot, Segment, Amplitude,
• event-api-topology-checkerValidates ActiveMQ topic names and consumer group patterns against Alfresco event API conventions. Applies to
• event-budget-plannerCreates event budgets with line items, contingency planning, sponsor offset calculations, and ROI projections.
• event-drivenEvent-driven architecture with pub/sub and message queues. Use for reactive systems.
• event-driven-architectDesigns event-driven architectures with event sourcing, CQRS, pub/sub patterns, and domain events for decouple
• event-driven-architectureDesign systems that communicate through events instead of direct service calls. Use when building loosely-coup
• event-driven-designWhen designing loosely coupled systems that react to state changes asynchronously.
• event-driven-messagingUse when implementing Kafka, RabbitMQ, Pulsar, or JMS producers and consumers in Spring Boot 4. Covers modular
• event-driven-outreachOutbound sequences triggered by conference/event attendance — pre-event research, on-site plays, post-event f
• event-driven-patternsMessage queue patterns with BullMQ, Kafka, RabbitMQ - saga, outbox, dead letter queue, exactly-once semantics.
• event-driven-trackerUse when tracking earnings, product launches, M&A, dividends, buybacks, unlocks, or other market-moving dates
• event-follow-upCreates post-event follow-up sequences with thank-you emails, survey distribution, content delivery, and nurtu
• event-managementGuides event lifecycle implementation including registration, capacity management, waitlists, QR code check-in
• event-managerFinds, filters, and adds local events to Google Calendar, then produces a structured markdown reference file.
• event-marketerExpert event marketing guidance for conferences, webinars, and field programs. Use when planning event strateg
• event-marketing-planCreates event marketing campaigns with timeline, channels, early bird promotions, and attendance forecasting.
• event-plannerPlans virtual and in-person events with detailed checklists, timelines, run-of-show documents, promotional cop
• event-promotion-plannerPlans promotion for virtual and in-person events across email, social, partners, and landing pages. Use when t
• event-prospectingEvent prospecting skill. Takes a conference / event speakers URL, extracts the people, filters their companies
• event-registration-pageWrites event registration page copy with agenda highlights, speaker bios, pricing tiers, and urgency elements.
• event-run-of-showCreates detailed run-of-show documents with minute-by-minute timing, cues, transitions, and contingency plans.
• event-sourcingStore state as immutable event log instead of current values. Build auditable, event-driven systems with full
• event-sourcing-architectDesigns event-sourced systems with CQRS, event stores, projections, and eventual consistency patterns. Use whe
• event-sponsorship-proposalCreates event sponsorship proposals with tier packages, benefits, audience data, and activation opportunities.
• event-storeDesign and implement event stores for event-sourced systems. Use when building event sourcing infrastructure,
• event-store-designDesign and implement event stores for event-sourced systems. Use when building event sourcing infrastructure,
• event-study-carsComplete methodology for computing publication-quality cumulative abnormal returns with proper event-study tes
• event-traceTrace the full event chain for one Claude Code session into an ordered timeline of every event type with tool_
• event4u-app-accessibility-auditorUse when reviewing UI for accessibility — WCAG 2.2 AA, keyboard nav, focus, ARIA, contrast, screen-reader sema
• event4u-app-canvas-designUse when creating static visual art — posters, marketing visuals, brand assets, PDF/PNG design pieces — even i
• event4u-app-code-reviewUse when the user says \"review this\", \"check my code\", or wants feedback on changes. Reviews for correctne
• event4u-app-design-reviewUse when the user says \"review the design\", \"check the UI\", or wants a comprehensive UI/UX review. Uses a
• event4u-app-doc-coauthoringUse when co-authoring a PRD, design doc, RFC, decision doc, or technical spec — 3-stage flow (context → sectio
• event4u-app-feature-planningUse when the user says \"plan a feature\", \"brainstorm\", \"explore this idea\", or wants to go from idea to
• event4u-app-skillSingle-skill orchestrator — routes to preview. Non-destructive "what will this skill do?" before you run it.
• eventbridgeAWS EventBridge serverless event bus for event-driven architectures. Use when creating rules, configuring even
• eventkitCreate, read, and manage calendar events and reminders using EventKit and EventKitUI. Use when adding events t
• eventsGenerate an Out-of-Process Spring Boot event listener for Alfresco Java Event API.
• events-apiEvents API skill. Use when working with Events for api. Covers 5 endpoints.
• events-planningPlan and execute B2B events — conferences, webinars, dinners, happy hours, trade shows, and owned events. Use
• evergreen-webinar-funnelAutomated evergreen webinar funnel. Simulates a "live" experience on-demand so leads can register and watch im
• evermind-ai-prOpen a GitHub PR targeting the correct branch with the project template
• every-style-editorThis skill should be used when reviewing or editing copy to ensure adherence to Every's style guide. It provid
• EveryInc/compound-engineering-pluginOfficial Compound Engineering plugin for Claude Code, Codex, Cursor, and more
• everyone-needs-a-copilot-doDevOps Engineer for CI, deployment, infrastructure, environment setup, observability, and operational safety.
• everyone-needs-a-copilot-docDocumentation specialist for README updates, onboarding material, API docs, setup guides, and durable technica
• everyone-needs-a-copilot-qaQA Engineer for software quality. Use for bug reproduction, regression analysis, edge-case design, test strate
• everyone-needs-a-copilot-voice-toneMailChimp Voice & Tone framework for UX copy, microcopy, error messages, and interface text — calibrates tone
• everything-openai-codexDevelopment conventions and patterns for Everything OpenAI Codex. JavaScript project with conventional commits
• evgeniiperov-design-an-interfaceGenerate multiple radically different interface designs for a module using parallel sub-agents. Use when user
• evgeniiperov-diagnoseDisciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → ins
• evgeniiperov-frontend-designCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the use
• evgeniiperov-grill-with-docsGrilling session that challenges your plan against the existing domain model, sharpens terminology, and update
• evgeniiperov-handoffCompact the current conversation into a handoff document for another agent to pick up.
• evgeniiperov-improve-codebase-architectureFind deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in
• evgeniiperov-prototypeBuild a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a run
• evgeniiperov-qaInteractive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues.
• evgeniiperov-request-refactor-planCreate a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when
• evgeniiperov-reviewReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does t
• evgeniiperov-setup-matt-pocock-skillsSets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know th
• evgeniiperov-tddTest-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using
• evgeniiperov-teachTeach the user a new skill or concept, within this workspace.
• evgeniiperov-to-issuesBreak a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bulle
• evgeniiperov-to-prdTurn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wa
• evgeniiperov-triageTriage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage i
• evgeniiperov-ubiquitous-languageExtract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and propo
• evgeniiperov-webapp-testingToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend
• eviction-riskAudit a tenant management system for eviction prevention and risk prediction. Evaluates payment pattern analys
• evidence-assessmentEvaluating the quality, provenance, and relevance of evidence that supports or undermines a claim. Covers sour
• evidence-auditorUse when `paper-review` needs a claim-by-claim evidence gap report grounded in an extracted claim ledger. **Tr
• evidence-authenticity-review用于审查证据真实性的执行技能。真实性是证据"三性"的基础，本技能提供书证、物证、电子数据、证人证言等各类证据的实质性审查方法，包括来源审查、载体审查、内容审查和对比审查等。适用于诉讼准备、证据质证阶段。
• evidence-based-reviewsProduce honest product reviews and buying guides without fabricated first-hand experience, using disclosed evi
• evidence-binderBind addressable evidence IDs from `papers/evidence_bank.jsonl` to each subsection (H3), producing `outline/ev
• evidence-draftCreate per-subsection evidence packs (NO PROSE): claim candidates, concrete comparisons, evaluation protocol,
• evidence-gap-reviewAnalyse specgraph verify output and identify what evidence is missing to advance specs to their next state.
• evidence-gatheringReúne e cura fontes documentais a partir de URLs ou busca por tópico. Produz catálogo pronto para handoff com
• evidence-hygieneEvidence-capture and PoC-redaction discipline for bug-bounty submissions: cookie redaction protocol (which fie
• evidence-mappingTracing a compliance control (CIS, SOC 2, HIPAA, or a cyber-insurance questionnaire line item) to concrete, re
• evidence-minerHarvest real, citable achievements from the user's git history, PRs, and work documents, and turn the confirme
• evidence-recorderAppend one JSONL record to ~/.claude/evolution/records/ when a correction, a non-obvious win, or a repeated re
• evidence-selfloopEvidence self-loop for surveys: read evidence bindings + evidence packs, then write an actionable upstream TOD
• evidence-synthesisSintetiza múltiplos documentos em matriz comparativa com citações rastreáveis, divergências explícitas e análi
• evidence-verificationEstablish what is actually TRUE about a client and prove it with records a stranger can check. Find the hard a
• evidentloop-design方案设计阶段入口；聚合方案分级、任务拆分与方案包输出规则，按需加载 references/assets/scripts。
• evilsocket/nerveThe Simple Agent Development Kit.
• evm-atlasPRB's collection of agent skills
• evm-contract-auditAudits EVM/Solidity smart contracts for security vulnerabilities. Covers reentrancy, access control, flash loa
• evm-contract-scaffoldScaffolds a Solidity smart contract project — Foundry-first with Hardhat alternative, OpenZeppelin-based token
• evm-proxy-upgrade-analyzerDetect common EVM proxy patterns and extract upgrade-related addresses and risk signals.
• evm-tx-debuggerDebug failed EVM transactions by decoding revert reasons, analyzing gas consumption, parsing events, and expla
• evo-hq-shipLand the winning experiment from an evo run as a clean, mergeable change -- open a PR when the repo has a remo
• evo-searchSolves complex, open-ended problems using an evolutionary search mechanism inspired by genetic algorithms. Gen
• evo2>
• evographevo-graph as a cap-evolve algorithm (AGENT MODE ONLY): a collaborative weakness-graph optimizer. Each round re
• evolution-changelogUse when the user types "/changelog evolution", "log this evolution", "track applied evolutions", "update EVOL
• evolution-engineUse when the user wants to "analyze sessions", "find patterns in my agent history", "evolve config", "/evolve"
• evolution-foundation/evo-aiEvo AI is an open-source platform for creating and managing AI agents, enabling integration with different AI
• evolution-loopUse after meaningful task closeout, repeated failure, review loops, stale triggers, or user feedback that an a
• evolutionary-modular-architectureGuides design and implementation of evolutionary modular-monolith platforms with DDD (strategic + tactical), f
• evolutionary-namingUse when refactoring code with poor names, when asked to improve naming, or when a user struggles to name a cl
• evolveInstinct Evolution Dashboard. USE WHEN /evolve, instinct dashboard, review instincts, promote instinct, prune
• evolve-cruxEvolve crux itself — add a capability or fix a recurring flaw in the crux tool, end to end: ideate → build → v
• evolve-schema-safelyDesign, implement, or review compatible and reversible database, event, API payload, configuration, or persist
• evolving-ai-agentsProvides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolu
• evolving-claude-mdSet up CLAUDE.md to maintain a living Decisions & Learnings log that the assistant updates as the project evol
• evotown-dispatch-completeReport Evotown dispatch job completion after the agent finishes real work.
• evotown-handoffQueue a cross-agent or cross-team handoff through the Evotown control plane.
• evtol-chief-designerExpert-level eVTOL Chief Designer specializing in aerodynamic configuration design, electric propulsion system
• exaAI-first web search via Exa — semantic/neural ranking, category-scoped results, fresh content retrieval, and o
• exa-code-contextFind code with Exa — API usage examples, error fixes, library docs, and GitHub repositories. Use when you need
• exa-code-searchCode search using Exa. Finds real code snippets, API docs, and examples from GitHub, StackOverflow, and techni
• exa-company-researchCompany research using Exa search. Finds company info, competitors, news, tweets, financials, LinkedIn profile
• exa-discoveryUse when running semantic web discovery for Florida county data sources, auction intel, or GTM research. Trigg
• exa-financial-report-searchFind financial filings with Exa — SEC filings (10-K, 10-Q, S-1), earnings reports, and annual reports. Use to
• exa-labs/exa-mcp-serverExa MCP for web search and web crawling!
• exa-lead-genGenerate enriched lead lists using Exa deep search. Finds companies matching an ICP, enriches with signals/new
• exa-lead-generationBuild prospect lists with Exa — find target companies matching an ICP, then their decision-makers, then enrich
• exa-native-baseFoundation for the Exa skill collection — how to call Exa (search, contents, answer, similar) from a local scr
• exa-people-researchPeople research using Exa search. Finds LinkedIn profiles, professional backgrounds, experts, team members, an
• exa-personal-siteSearch personal websites and blogs using Exa. Finds individual perspectives, portfolios, tutorials, and person
• exa-personal-site-searchFind personal websites with Exa — blogs, portfolios, and homepages. Use to find a person's own writing (not pr
• exa-research-paper-searchFind academic papers with Exa — by topic, author, recency, or as surveys/reviews. Use for literature reviews,
• exa-searchNeural search via Exa MCP for web, code, and company research. Use when the user needs web search, code exampl
• exa-web-searchGeneral-purpose web search powered by Exa — the search_web / web_search analog. Use for any open-ended lookup,
• exa-x-searchSearch tweets and X/Twitter content using Exa. Finds social discussions, product announcements, developer opin
• exact-online-webhooksReceive and verify Exact Online webhooks. Use when setting up Exact Online webhook handlers, debugging HashCod
• exact-rendered-decision-journalingJournal each per-message tool result replacement so resume logic replays the exact preview the model saw.
• exact-token-counterUse when checking token costs of text files (especially SKILL.md files), auditing prompt size, compacting skil
• exaggerated-clarityUse when motion needs to read clearly and powerfully—broad comedy, action highlights, important story beats, o
• exam-forecastAnalyse past exams from the same lecturer to surface patterns — subject weighting, recurring issue-spot traps,
• exam-prepPrepare for exams — practice tests, weak-area drills, timed quizzes, and performance feedback.
• exam-prep-thstudy plan + practice question | สำหรับ นักศึกษา. Triggers when user says (Thai/EN): 'เตรียมสอบ', 'exam prep
• examination-readinessPrepare for and respond to SEC and FINRA regulatory examinations across the full exam lifecycle. Use when the
• examloop考前冲刺练习闭环，支持出题/批改/错题分析，文理工医法通用
• exampleHermetic contract-validation fixture.
• example-commandAn example user-invoked skill that demonstrates frontmatter options and the skills/<name>/SKILL.md layout
• example-data-processorProcess CSV data files by cleaning, transforming, and analyzing them. Use this when users need to work with CS
• example-designDesign pedagogically effective code examples, tutorials, and runnable samples using progressive complexity and
• example-portalTEMPLATE — a CareerForge example job-portal adapter (ADR-0004). Copy this directory to add structured search f
• example-skillClaude Code plugin marketplace - Skills, agents, commands e hooks condivisi
• example-skill-libraryDemonstrates how to ship an Agent Skill from an npm package via skill-indexer. Use when learning how to author
• example-skill-nameOne-line description of when this skill is used.
• example-toolA template skill demonstrating the PAI SKILL.md format.
• examplesLike Lighthouse for your agent harness - verify your CLAUDE.md/AGENTS.md, skills & hooks are real, then test a
• exasolTop-level router for Exasol work. Use for any Exasol database, exapump, SQL, BucketFS, extension, integration,
• exasol-ai-setupSet up notebook-connector configuration for Exasol AI workflows through the Secrets Python API. Covers secure-
• exasol-bucketfsExasol BucketFS file system management via exapump CLI. Covers listing, uploading, downloading, and deleting f
• exasol-cloud-storage-extensionUse Exasol Cloud Storage Extension workflows for moving structured object-storage files through extension UDFs
• exasol-databaseExasol database interaction via exapump CLI and Exasol SQL. Covers SQL queries, schema inspection, table desig
• exasol-distributed-mlDistributed machine learning, data mining, and iterative HPC with Exasol. Covers end-to-end ML pipelines (DIST
• exasol-document-virtual-schemasUse Exasol document-file virtual schemas for federated read-only access to object and file storage. Covers doc
• exasol-exportUse Exasol EXPORT SQL plus exapump local file export workflows for moving data out of Exasol. Covers native CS
• exasol-extension-catalogCatalog and routing guide for Exasol tools, extensions, connectors, integrations, and architecture patterns. U
• exasol-importUse Exasol IMPORT SQL plus exapump local file upload workflows for moving data into Exasol. Covers CSV, FBV, P
• exasol-itdeUse notebook-connector's itde_manager to run a local Docker-based Exasol database. Covers bring_itde_up, get_i
• exasol-jdbc-virtual-schemasUse Exasol JDBC-based virtual schemas for federated read-only access to external databases. Covers database-so
• exasol-notebook-connectionsUse notebook-connector's Python connection helpers for Exasol, BucketFS, SQLAlchemy, and Ibis. Covers open_pye
• exasol-setup-personalGuided setup of Exasol Personal — a free Exasol database running locally on a Mac or deployed to your own AWS,
• exasol-text-aiDeploy and use the Exasol Text AI Extension with notebook-connector. Covers deploy_license, initialize_text_ai
• exasol-transformersDeploy and use the Exasol Transformers Extension for NLP inference inside Exasol with notebook-connector. Cove
• exasol-udfsExasol User Defined Functions (UDFs) and Script Language Containers (SLCs). Covers CREATE SCRIPT, SCALAR and S
• exasol-virtual-schema-adapter-developmentBuild, install, validate, and debug custom Exasol virtual schema adapters. Covers source-specific JDBC dialect
• exboys-agent-browsera middle platform for enterprise Agent runtime governance and capability assets — connect OpenClaw, Hermes, Sk
• exboys-skill-creatorCreate or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, a
• excalidrawСоздание схем и диаграмм в Excalidraw для Obsidian. Use when user says 'сделай схему', 'нарисуй диаграмму', 'e
• excalidraw-agents365Excalidraw diagram generation optimized for coding agents. Produces clean, structured diagrams for system arch
• excalidraw-diagram手绘风技术图生成器——自然语言描述系统，输出可编辑的 .excalidraw 文件。 支持 9 种图类型（流程图·关系图·思维导图·架构图·数据流图·泳道业务流· 类图·时序图·ER 图）。内置 Prompt 优化层，生
• excalidraw-diagram-designGuide for structuring graph input (nodes and edges) for the Excalidraw Architect MCP tool to produce clean, re
• excalidraw-diagram-generatorGenerate .excalidraw diagrams from natural language. Use when creating flowcharts, mind maps, system architect
• excalidraw-studioGenerate Excalidraw diagrams from natural language descriptions. Outputs .excalidraw JSON files openable in Ex
• excel-assistant22 ready-to-use AI agent skills for research, PRDs, dashboards, landing pages, and workflow automation. Works
• excel-automationRead and write workbooks programmatically: preserving formatting, handling merged cells, and the date serial t
• excel-automation-composioA curated guide to convention files AI agents read, write, and act on: AGENTS.md, CLAUDE.md, SKILL.md, llms.tx
• excel-bar-chart-visualization读取多工作表Excel文件，自动处理合并单元格与数据清洗，进行交叉分组统计并生成带总计行的结果表，最后绘制支持中英文字体的美化柱状图，适用于多维度数据汇总与可视化分析。
• excel-basic-statistics-and-routing对多Sheet Excel文件进行基础统计与，支持按条件筛选计算均值，以及从指定行区间提取数据去重求和，并生成结果文件与下载链接。
• excel-conditional-comparison-and-large-file-processing对比Excel多表中的特定系数并对异常值进行颜色标记。
• excel-conditional-filtering-optimization根据多维数值条件筛选 Excel 数据并导出结果，支持大规模数据的自动性能优化处理。
• excel-data-analysis-and-report-generation从Excel提取多类型数据，并生成包含可视化图表与下载链接的综合分析报告。
• excel-dcf-modelerBuilds discounted cash flow (DCF) valuation models in Excel with free cash flow projections, WACC calculations
• excel-hygieneA rigorous "second pair of eyes" on any xlsx before it goes out. Runs a deterministic script for precise MECHA
• excel-large-file-processing-and-cleaning读取多 sheet Excel 文件，动态识别目标列进行统计，并使用正则清洗文本字段提取中文字符，最终输出标准化 Excel 文件。
• excel-lbo-modelerCreates leveraged buyout (LBO) models in Excel with sources & uses, debt schedules, cash flow waterfalls, and
• excel-lookup-functionsMaster Excel lookup functions (VLOOKUP, HLOOKUP, INDEX/MATCH, XLOOKUP) for single and multiple criteria.
• excel-multi-sheet-dynamic-analysis用于分析包含多个Sheet的Excel文件，动态判断数据量级以决定是否转换为Parquet进行大文件处理，并支持跨Sheet的特定字段统计、数据清洗、交叉分析与可视化，最终生成带下载链接的汇总报告。
• excel-multi-sheet-threshold-analysis统计多Sheet Excel总行数并根据规模选择处理策略，提取特定维度信息进行去重统计，并生成摘要与明细报表。
• excel-outlier-detection-and-highlighting识别 Excel 中的超限数值与错误单元格并进行高亮标注。
• excel-pivot-wizardGenerates pivot tables and charts from raw data using natural language commands. Targets business analysts and
• excel-powerpoint-workflow-skillsCreate reusable Claude workflows (“skills”) tailored for Excel and PowerPoint add-ins, with emphasis on cross-
• excel-sheetExcel (.xlsx) manipulation via MCP server. Use for creating workbooks, formatting cells, writing formulas, bui
• excel-sheet-filter-export动态统计多Sheet Excel文件行数以判断大文件处理逻辑，并根据特定条件筛选数据、重命名字段后导出为包含下载链接的新Excel文件，适用于多Sheet数据探查与条件过滤导出场景。
• excel-smart-analysis-and-cleaning对多 Sheet Excel 进行智能清洗、跨表核对与可视化分析。。
• excel-spreadsheetsCreate and edit Excel spreadsheets (.xlsx) with formulas, charts, and formatting. Use xlsxwriter for creating
• excel-statistical-formulasUse Excel statistical functions for descriptive analysis including percentiles, weighted calculations, and dat
• excel-statistical-viz-large-file对 Excel 数据进行多维度统计分析与可视化。
• excel-threshold-analysis-and-styling根据 Excel 数据量级自动判断处理策略，执行数值列清洗、条件过滤，并使用 openpyxl 对符合条件的单元格进行样式标记与导出。
• excel-to-bimPush Excel data back to BIM models. Update parameters, properties, and attributes from structured spreadsheets
• excel-to-rvtImport Excel data into RVT projects. Update element parameters, create schedules, and sync external data sourc
• excel-variance-analyzerAutomates budget vs actual variance analysis in Excel with flagging, commentary, and executive summaries. Targ
• excel-xlsx-skillUse the xlsx skill tool to create, read, modify and analyze Excel spreadsheets with formulas and formatting.
• excellenceMulti-agent document review (visual, pedagogy, proofreading, domain). Use for comprehensive quality check befo
• excellence-book-writingCreator operating system for AI-native workflows: skills, commands, agents, and plugins for Claude Code, Curso
• excellence-no-intermediatesNo intermediate options in trade-offs — every choice presented must be a path to excellence, never "accept bro
• exchange-connectivityGuide the design and management of trading venue connectivity and market data infrastructure. Owns the FIX ses
• exchange-policyWrites exchange policies with eligibility criteria, process steps, customer communication templates, and excep
• exchange.merx/mcpTRON energy exchange for AI agents. 54 tools, 30 prompts, 21 resources. A2A + ACP.