メニュー
このリポジトリの skills
SkillsMP は tomevault-io/skills-registry から 17,125 件の skill を収集しています。skill を開くとソースと詳細を確認できます。
tomevault-io/skills-registry収集済み skill 17,125 件中 40 件を表示しています。
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
原文の言語: 英語
Use when given a GitHub issue URL or number to investigate and implement a fix. Triggers on "fix issue", "fix bug", "fix
原文の言語: 英語
Use when a DeerFlow maintainer needs comment-only GitHub issue or PR handling: resolve issue/PR scopes with gh, analyze issues, post or draft issue comments, perform PR review comments, review PR or issue batches, compare competing PRs that target the same…
原文の言語: 英語
FlowGram 物料组件开发指南 - 用于在 form-materials 包中创建新的物料组件 Use when this capability is needed.
原文の言語: 中国語
Used to invoke the PXMeter tool for rigorous quality assessment of biomolecular structure prediction models (e.g., proteins, nucleic acids, small molecules). This skill covers single-sample CIF evaluations and large-scale dataset benchmarks, providing rich…
原文の言語: 英語
Use this skill when adding or refreshing a patchgen-generated modeling file for a VeOmni model under veomni/models/transformers/<model>/generated/ — GPU-only or GPU+NPU, dense or MoE, text-only / VLM / Omni-thinker+talker. Covers: creating…
原文の言語: 英語
Internal helper contract for calling the Gemini-backed gemini-companion runtime from Claude Code Use when this capability is needed.
原文の言語: 英語
Render slide images sequentially from DESIGN.md and slide prompt JSON using Codex native image generation, saving each output into the workspace with page-number filenames. Use when this capability is needed.
原文の言語: 英語
Generate a complete, project-specific Claude Code harness — agents, skills, hooks, CLAUDE.md rules — tailored to any codebase. Use whenever someone says 'create a harness', 'set up agents for this project', 'configure Claude Code', 'build an agent team',…
原文の言語: 英語
Install, update, test, or remove a cost-optimized Codex multi-agent setup where GPT stays the planner-reviewer and DeepSeek runs through a single Python runtime with visible routing, SSE events, and approved repository tools. Use when this capability is…
原文の言語: 英語
Configure Better Auth server and client, set up database adapters, manage sessions, add plugins, and handle environment variables. Use when users mention Better Auth, betterauth, auth.ts, or need to set up TypeScript authentication with email/password, OAuth,…
原文の言語: 英語
Automatically activated when user asks about test quality, code coverage, test reliability, test maintainability, or wants to analyze their test suite. Provides framework-agnostic test quality analysis and improvement recommendations. Does NOT provide…
原文の言語: 英語
Automatically activated when user works with Jest tests, mentions Jest configuration, asks about Jest matchers/mocks, or has files matching *.test.js, *.test.ts, jest.config.*. Provides Jest-specific expertise for testing React, Node.js, and JavaScript…
原文の言語: 英語
Expert technical writer for Logseq Template Graph project. Generates comprehensive, accurate, and well-structured documentation for modules, features, guides, and APIs. Activates when asked to "write docs", "document this", "create README", "update…
原文の言語: 英語
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js…
原文の言語: 英語
Use when managing Google Suite from the command line with the `gs` CLI — Gmail (tail/stream as JSON, send with attachments, delete, mark read/unread, labels, move), Google Calendar (list calendars, list/create/delete events, invite attendees), Google Drive…
原文の言語: 英語
Connect your agent to a Minibook instance for project collaboration. Use when this capability is needed.
原文の言語: 英語
Build LVGL touchscreen applications that communicate with JanOS ESP32C5 firmware over UART. Use when creating screens for Tab5, CoreS3, Cardputer, or any ESP-IDF device that sends UART commands like scan_networks, start_deauth, list_hosts, show_pass. Covers…
原文の言語: 英語
Build LVGL touchscreen applications that communicate with JanOS ESP32C5 firmware over UART. Use when creating screens for Tab5, CoreS3, Cardputer, or any ESP-IDF device that sends UART commands like scan_networks, start_deauth, list_hosts, show_pass. Covers…
原文の言語: 英語
Rust coding conventions and patterns for auth9-core development. Use when this capability is needed.
原文の言語: 英語
Rust coding conventions and patterns for service development. Use when this capability is needed.
原文の言語: 英語
Build and maintain command-line interfaces with CAC. Use when a task involves the `cac` package, authoring or reviewing CLI apps, defining commands/options/arguments, generating help or version output, handling parse errors, or explaining CAC-specific…
原文の言語: 英語
Coordinates marketing strategy, campaigns, product marketing, and SEO via question-based delegation. Use for tier 2+ marketing work — GTM, brand positioning, multi-channel campaign planning, competitive intelligence, launch planning, and organic-search…
原文の言語: 英語
结合深度调研（Deep Research）与人工洞察（Human-in-the-loop），为大模型生态合作生成商业落地规划与极度颗粒度的宣发物料。当用户希望通过严谨的两阶段调研（前期探索与深度研究）、引入人工战略判断，并最终生成全套合作与 GTM 方案时，使用此技能。 Use when this capability is needed.
原文の言語: 中国語
>- Use when this capability is needed.
原文の言語: 英語
Use when preparing torchsparsegradutils PRs, releases, packaging metadata, test-stability changes, reviewer follow-up, or devcontainer-aware validation commands.
原文の言語: 英語
Local development workflow for list-github-stars. Use when orienting in the workspace, choosing just/go/Docker/GoReleaser commands, or validating general changes. Use when this capability is needed.
原文の言語: 英語
Write security checks using the CheckDefinitionV2 system. Use when creating new checks, converting V1 checks to V2, or when the user asks to implement a vulnerability scanner check. Covers defineCheckV2, defineRegexCheck, CheckContext API, parameter…
原文の言語: 英語
Manages AI agent context window usage - truncation rules, clear truncation markers, and tools for chunked reading or search. Use when building or modifying agent context, system prompts, user messages, or tools that inject large content into the LLM.
原文の言語: 英語
| Use when this capability is needed.
原文の言語: 中国語
In-depth multi-pass code review of a GitHub change (local checkout). Decomposes the diff into logical review units, reviews each on the best available model (docs on the Haiku model), runs an advisory architectural pass on the highest-risk units, scores…
原文の言語: 英語
Audit code comments and agent-facing docs against a repository's comment policy. Use when asked to review comments, audit stale or redundant comments, check AIDEV-NOTE anchors, evaluate comment-policy.md / CLAUDE.md / AGENTS.md compliance, or inspect changed…
原文の言語: 英語
Use when project documentation must be generated or updated from verified codebase facts
原文の言語: 英語
Use when existing project documentation must be discovered and converted into colony context
原文の言語: 英語
Use when the project uses Flutter/Dart for cross-platform mobile, web, or desktop applications
原文の言語: 英語
Use when the project uses GraphQL for API queries and mutations
原文の言語: 英語
Use when the project designs or consumes RESTful HTTP APIs
原文の言語: 英語
Use when the project uses Rust for systems programming, CLI tools, WebAssembly, or backend services
原文の言語: 英語
Use when the project needs automated testing with Jest, Vitest, pytest, or similar frameworks
原文の言語: 英語
Creates a new CLI command following the Commander.js pattern in src/commands/. Handles command registration in src/cli.ts, telemetry tracking via tracked() wrapper, and option parsing. Use when user says add command, new CLI command, create subcommand, or…
原文の言語: 英語