菜单
这个仓库中的 skills
SkillsMP 已收集 tomevault-io/skills-registry 中的 17,125 个 Skill。打开任一 Skill 可查看来源和详情。
tomevault-io/skills-registry已展示 40 / 17,125 个已收集 Skill。
Coordinate comprehensive literature reviews on any research topic in philosophy. Manages 6-phase workflow including domain decomposition, literature search, and synthesis. Use proactively when user requests a literature review. Use when this capability is…
原文语言：英语
Search philosophy literature across SEP, IEP, PhilPapers, Semantic Scholar, OpenAlex, CORE, arXiv, and NDPR. Supports paper discovery, citation traversal, content enrichment, and recommendations. Verifies citations via CrossRef. Use when this capability is…
原文语言：英语
DREAM decomposition protocol — 8-slot magnitude routing, plan types (SP/PP), _overview.md frontmatter schema, sibling firewall, MANAGER/WORKER lifecycle, and context isolation. Covers magnitude assessment, plan/task hierarchy, directory-based decomposition,…
原文语言：英语
Orchestrator discussion preset — structured multi-agent discussion protocol for collaborative problem solving. Coordinates N-way discussions between specialist agents through Propose, Challenge, and Synthesize phases to reach consensus. Use this skill when…
原文语言：英语
Orchestrator expedition preset — coordinating the 8-phase expedition pipeline for exporting ADHD agents to external projects. Manages L1 Bundle architecture with 3 mandatory stop points, agent delegation (HyperExped, HyperSan, HyperDream, HyperSmith,…
原文语言：英语
Orchestrator implementation preset — coordinating implementation tasks across specialist agents with mandatory quality gates. Manages the full lifecycle: PRE-CHECK (HyperSan) → IMPLEMENT (HyperArch) → POST-CHECK (HyperSan) → DOC-UPDATE (HyperDream). Includes…
原文语言：英语
Orchestrator routing preset — routing user requests to the correct specialist agent based on task analysis. Supports single-agent, multi-phase, and parallel routing patterns. Maps user intent to the appropriate Hyper agent using keyword matching, context…
原文语言：英语
Orchestrator testing preset — coordinating comprehensive testing workflows across specialist agents. Manages the full test lifecycle: PLAN (HyperSan) → SPEC-TEST (HyperArch) → ATTACK (HyperRed) → FINAL (HyperSan). Includes adversarial testing, fix cycles, and…
原文语言：英语
Analyze entire codebases using Gemini CLI's 1M token context. Generates architecture reports covering structure, security, performance, and improvement roadmaps. Use when auditing code quality or running /analyze. Use when this capability is needed.
原文语言：日语
Save and restore session state for continuity across Claude Code sessions. Captures tasks, changed files, context, and decisions. Use when ending a session, preserving progress, or running /checkpointing. Use when this capability is needed.
原文语言：日语
Generate distinctive, production-grade frontend UI code that avoids generic AI aesthetics. Follows opinionated design principles for unique visual identity. Use when building web UIs, components, or running /frontend-design. Use when this capability is needed.
原文语言：日语
Generate native-quality iOS/macOS mockup PNGs using SwiftUI Preview rendering. Use when designing Apple platform UIs, creating native app mockups, or running /mockup-swift. Use when this capability is needed.
原文语言：日语
Run the full design-to-deploy pipeline using 3 AIs (Claude + Codex + Gemini). Use when starting a new feature, running /project, or needing end-to-end development with requirements, specs, implementation, testing, review, and deployment phases. Use when this…
原文语言：日语
Generate a requirements document with user stories, acceptance criteria, and constraints. Use when defining features, writing specs, or running /requirements before implementation. Use when this capability is needed.
原文语言：多语言混合
Conduct technical research using Gemini CLI, producing comparison reports with recommendations and code examples. Use when evaluating technologies, comparing libraries, or running /research. Use when this capability is needed.
原文语言：多语言混合
Run code review against design documents, checking acceptance criteria, security, performance, and test coverage. Use when reviewing implementation quality or running /review. Use when this capability is needed.
原文语言：日语
Generate UI screen design documents with component lists, state transitions, interactions, and responsive breakpoints. Use when designing screens, creating wireframes, or running /spec. Use when this capability is needed.
原文语言：英语
Generate E2E and unit test code from requirements using Playwright, delegated to Codex. Use when writing tests, checking acceptance criteria coverage, or running /test. Use when this capability is needed.
原文语言：多语言混合
Architecture Decision Records (ADRs) for documenting significant technical decisions. Use for capturing decision context, rationale, consequences, and maintaining decision history. Use when this capability is needed.
原文语言：英语
MVP definition, MoSCoW prioritization, and phased delivery planning. Use for scoping minimum viable products, ordering features by value and dependency, or creating implementation roadmaps. Use when this capability is needed.
原文语言：英语
Modern Python 3.10+ development standards including type hints, async patterns, pathlib, dataclasses, and recommended tooling (uv, Ruff, pytest). Use for Python code review, new feature implementation, refactoring legacy code, or making architecture decisions…
原文语言：英语
Security and privacy compliance patterns for B2B SaaS (SOC 2, GDPR). Use for audit preparation, control design, compliance gap analysis, or building compliance into features. Use when this capability is needed.
原文语言：英语
Development standards for Python projects including code style, git conventions, testing patterns, timing measurement, and validation requirements. Use when writing code, reviewing PRs, or making commits. Loaded by all implementation agents. Use when this…
原文语言：英语
Modern Terraform patterns for module design, state management, and CI/CD integration. Use for structuring Terraform projects, managing remote state, implementing environment separation, or enforcing code quality. Use when this capability is needed.
原文语言：英语
Angular 21+ testing patterns with Vitest, signal component testing, and Playwright E2E. Use for writing unit tests, integration tests, or E2E tests for Angular applications. Use when this capability is needed.
原文语言：英语
Python unit test standards including naming conventions (test__<what>__<expected>), behavioral testing patterns, coverage requirements (80% minimum), and tautological test detection. Use when reviewing tests, writing tests, or enforcing test quality. Trigger…
原文语言：英语
Creating and using OpenBench framework adapters for LangChain, CrewAI, AG2, E2B, and Google ADK. Use when wrapping external AI frameworks, creating new adapters, or integrating third-party agents into workflows. Use when this capability is needed.
原文语言：英语
Working with OpenBench chat layer - ChatEngine, A2UI v0.10 builder, content renderers, SSE + REST transport, and ChatLayer L2 orchestrator. Use when building chat interfaces, streaming A2UI JSONL, rendering rich content (charts, forms, files), or composing…
原文语言：英语
Building and extending the @openbench/chat-ui TypeScript/React SDK. Use when creating chat components, A2UI v0.10 renderers, custom components, hooks, SSE + REST transport, or styling the chat interface. Use when this capability is needed.
原文语言：英语
Creating and composing OpenBench workflows with L1/L2 patterns, DAG structures, and chainable operators. Use when building workflows with | or & operators, creating DAG patterns, or working with DataLayer/IntelligenceLayer/OutputLayer composition. Use when…
原文语言：英语
Implementing DataSource, Agent, OutputGenerator and other OpenBench abstractions. Use when creating new data sources, agents, output generators, data stores, or framework adapters. Use when this capability is needed.
原文语言：英语
Working with OpenBench data layer - vector stores, chunking, embeddings, and RAG patterns. Use when implementing PineconeStore, chunking documents, generating embeddings, or building RAG workflows. Use when this capability is needed.
原文语言：英语
Working with OpenBench intelligence layer - BaseAgent, LLM providers, tool execution, memory, and RAG patterns. Use when creating agents, configuring LLM providers, adding tools, or building RAG-augmented agents. Use when this capability is needed.
原文语言：英语
Working with OpenBench output generators for PDF, PowerPoint, Dashboard, Audio, and Markdown. Use when creating output generators, generating reports, or working with the OutputLayer. Use when this capability is needed.
原文语言：英语
Writing tests for OpenBench components, workflows, and integrations. Use when writing unit tests, running test suite, creating test fixtures, or mocking components. Use when this capability is needed.
原文语言：英语
Rules and guidelines for implementing Action Connectors in OM Cortex Runtime Use when this capability is needed.
原文语言：英语
Rules and guidelines for implementing Providers in OM Cortex Runtime Use when this capability is needed.
原文语言：英语
Rules and guidelines for writing pytest tests for Providers in OM Cortex Runtime Use when this capability is needed.
原文语言：英语
Rules and guidelines for implementing Sensors (Inputs) in OM Cortex Runtime Use when this capability is needed.
原文语言：英语
Database, API, and integration conventions for Red Cliff Record. Use when working with Drizzle ORM, tRPC routers, database migrations, integration syncs, or media alt-text workflows in this project. Triggers on database queries, API routes, Drizzle v2, tRPC,…
原文语言：英语