x-cmd-skill
claudeCommunity-curated, human-vetted skills for AI coding and agent tools. Focused on practical, production-ready skill implementations.
200 skills
Open-source AI coding standards and skills for Claude Code, Cursor, Copilot—unified best practices across AI tools.
Plugin guillempuche-ai-standards from marketplace cascade-code-general-misc-3 in joshuarweaver/cascade-code-general-misc-3. Commands read from the repo's manifest — 1 month ago.
commitCommit workflow for ai-standards repo. Formats all markdown files and previews changes before committing.
releaseDetect changes in skills/agents, ask about version bumps, update frontmatter versions, and deploy individual repos to GitHub.
effect-lookupQuick lookup for Effect TypeScript library APIs, patterns, and source code. Use when you need to find Effect functions, understand Effect patterns, or look up implementation details.
issueTurn a rough ask into a well-formed GitHub issue, following this repo's own conventions. Use when asked to "create an issue", "open an issue", "file an issue", "raise an issue", "log a bug", "track this as an issue", "make a GitHub issue", or when describing a bug / feature / task to capture in the
powersyncBuild local-first, offline-capable TypeScript apps with PowerSync. Use when implementing real-time sync between SQLite and backend databases (Postgres, MongoDB, MySQL, SQL Server). Covers schema definition, database setup, CRUD operations, React/Vue hooks, watch queries, and Kysely/Drizzle ORM integ
prTurn a finished change into a reviewable, mergeable pull request. Use when asked to "open a PR", "create a pull request", "raise a PR", "PR this", or "send it for review". Drives the whole lifecycle — re-baseline on the default branch, verify end-to-end with visual proof for UI work, self-review for
tamaguiUniversal React + React Native UI library with optimizing compiler. Use when building cross-platform apps with shared styling, design tokens, themes, and accessible components.
test-bddGenerate BDD-style test files that document behavior with GIVEN/WHEN/THEN comments and test only public API and observable outcomes. Language and framework agnostic, with patterns and examples tuned for TypeScript + vitest + testing-library (hooks, components, utilities, constants).
unikraftUnikraft CLI (`unikraft`) commands for building and deploying to Unikraft Cloud. Use when working with Kraftfiles, deploying unikernels, or managing Unikraft Cloud instances/services/images. Covers the new `unikraft` CLI that replaces the legacy kraftkit `kraft`.
a11y-accessibility-reviewerUse this agent to review code for accessibility (a11y) compliance. Use after writing UI components, forms, navigation, or interactive elements. Evaluates WCAG 2.1/2.2, WAI-ARIA, VoiceOver, and TalkBack compliance for React and React Native.
readability-improverUse this agent to improve code readability through renaming, comments, and whitespace. Use after writing complex logic or when code would benefit from clarification. The agent is selective — it skips self-documenting code.
Community-curated, human-vetted skills for AI coding and agent tools. Focused on practical, production-ready skill implementations.
200 skills
CFN Loop skill for unified error handling, batching, and structured logging across agent failures with categorization and recovery.
169 skills · 9 agents
Search and discover Claude Code skills and MCP servers from marketplaces and GitHub. Use to find tools for specific tasks or explore available integrations before building custom solutions.
160 skills
Collection of Claude Code plugins tailored for streamlining software development and engineering processes.
85 skills
Pre-built SWE workflows for Claude Code covering development patterns, testing strategies, and engineering best practices for software projects.
32 skills · 40 agents
Supercharged plugin collection with 109 components: 22 agents, 32 commands, 55 skills across 13 modular plugins. Includes deep reasoning, autonomous dev loops, DDD architecture, git automation, and design system enforcement.
66 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Ship stablecoin apps faster. Best-practice skills for USDC payments, cross-chain transfers, wallets, and smart contracts — plus Circle's MCP server for real-time SDK and documentation guidance.
20 skills · 1 MCP server
HADS (Human-AI Document Standard) — semantic tagging convention for docs that work for both humans and AI models — plus the grounded-vault pattern for provenance-linked, drift-checked knowledge stores.
2 skills
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
5 skills
围绕复杂问题先挖掘相关行业、学科、作者与可信理论,再比较结构同构的历史成功、失败和反例,提炼带条件的标准答案。用户需要同时获得理论解释与历史比较,或明确询问历史上如何解决、有没有经典解法、标准答案时使用;只需给现有命题、案例、PPT 或方法论找理论依据时不使用。
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.