发现 Skills
为真实工作流程挑选经过整理的 Skill,连接、安装并开始使用。
pipeline-judge-dual
PHASE 9 of the Planitor pipeline. Dual-LLM: Model A (analytical) evaluates from an analytical-rigorous perspective and Model B (creative) from a strategic-creative perspective. Planitor synthesizes both evaluations into a final JUDGE-REPORT.json with auto-fix. Includes tax validation, completeness scoring and documented feedback for re-runs.
postgres-expert
Create, review, and optimise PostgreSQL schemas, migrations, RLS policies, functions, and PgTAP tests for Supabase applications.
test-and-fix-connector
Validate a connector by running the test suite, diagnosing failures, and applying fixes until all tests pass.
databricks-unity-catalog
Manage Unity Catalog resources including catalogs, schemas, and tables. Handles discovery, creation, updates, and deletions with proper naming conventions and governance. Use when exploring catalogs, creating schemas, managing tables, or setting up data governance.
dd-apm
APM - traces, services, dependencies, performance analysis.
excel-to-bim
Push Excel data back to BIM models. Update parameters, properties, and attributes from structured spreadsheets.
specify-with-requirements
Read requirements markdown and generate detailed technical specifications. Analyzes requirements, clarifies ambiguities, and updates the specs document. Use when user has written requirements and wants to generate specs.
testing-standards
Testing conventions for Stock Indicators. Use for test naming (MethodName_StateUnderTest_ExpectedBehavior), FluentAssertions patterns, precision requirements, and test base class selection.
module-improve
Version management, bug fixes, and feature additions for VCV Rack modules
snomedct-query-skill
Use this skill when querying the SNOMEDCT clinical vocabulary graph, including semantic aliases and intent-guided Cypher patterns.
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
eightctl
Control Eight Sleep pods (status, temperature, alarms, schedules).
ilya-sutskever-perspective
Ilya Sutskever的思维框架与表达方式。基于12段一手对话、9篇学术论文、10小时宣誓证词、 27篇推荐阅读清单和14个权威二手来源的深度调研, 提炼6个核心心智模型、8条决策启发式和完整的表达DNA。 用途:作为思维顾问,用Ilya的视角分析AI技术方向、安全策略、研究品味。 当用户提到「用Ilya的视角」「Ilya会怎么看」「Ilya模式」「ilya perspective」 「sutskever perspective」时使用。 即使用户只是说「帮我用Ilya的角度想想」「如果Ilya会怎么做」「切换到Ilya」也应触发。
things-mac
Add, update, list, search, or inspect Things 3 todos, inbox, today, projects, areas, and tags on macOS.
fastmcp-server
Complete guide for building MCP servers with FastMCP 3.0 - tools, resources, authentication, providers, middleware, and deployment. Use when creating Python MCP servers or integrating AI models with external tools and data.
btca-cli
Operate the btca CLI for local resources and source-first answers. Use when setting up btca in a project, connecting a provider, adding or managing resources, and asking questions via btca commands. Invoke this skill when the user says "use btca" or needs to do more detailed research on a specific library or framework.
obsidian-canvas
Create and edit Obsidian Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.
arch-draw
Generate professional draw.io diagrams in XML format from architectural descriptions. Use when Claude needs to create visual diagrams for (1) System architecture diagrams, (2) Microservices layouts, (3) Workflow/BPMN diagrams, (4) Network topology, (5) Data flow diagrams, (6) Any visual representation requiring boxes, containers, arrows, and connections. Handles arrow routing, collision avoidance, consistent layouts, and architectural patterns like three-tier, event-driven, and Camunda/Zeebe clusters.
director-readiness-advisor
Coaches PMs and new Directors through the transition from individual contributor to organizational leader across four situations: preparing, interviewing, newly landed, or recalibrating.
authoring-user-stories
This skill MUST be invoked when the user says "write user stories", "define acceptance criteria", "prioritize features", "user story", "acceptance scenario", or "Given When Then". SHOULD also invoke when user mentions "priority", "P1", "P2", "P3", or "backlog". Produces prioritized user stories with independently testable acceptance scenarios.
quiz-crawler
Extract all questions/answer options from marketing quiz funnels and record final redirect/product URL + screenshots. Use when a user gives a quiz URL and asks to collect questions/answers or capture the offer page. Use output format specified in assets/output.md
zero-to-one
Apply Peter Thiel's Zero to One principles for building new products, evaluating ideas, and strategic thinking. Use when creating something new (not iterating), assessing market opportunities, competitive positioning, startup strategy, deciding what to build, or evaluating whether an idea is truly innovative vs incremental.
security
Information security policies and standards — password policies, data protection, security incident reporting
ladybugdb
Expert guide for LadybugDB — an embedded, in-process property graph database using openCypher. Use this skill whenever the user is working with LadybugDB, writing Cypher queries for LadybugDB, using the `lbug` CLI, importing `real_ladybug` in Python, using `@ladybugdb/core` in Node.js, or building any application with LadybugDB. Also triggers when the user asks about LadybugDB schema design, graph algorithms (PageRank, Louvain), HNSW vector search, full-text search, ATTACH to PostgreSQL/DuckDB/Delta Lake, LLM embeddings with CREATE_EMBEDDING, or bulk data import/export with COPY FROM/TO. Use even if the user just says 'ladybug graph db' or pastes a .lbug file path.