GitHub user
Agent skills by majiayu000
- skills
- 1,379
- repositories
- 3
Repositories by majiayu000
- claude-skill-registrySearchable Claude Code skills catalog with source-linked guides and generated registry artifacts666 stars · 1,273 skills
- spellbookCross-runtime skills for Claude Code, Codex, and multi-agent workflows.286 stars · 97 skills
- litellm-rsSelf-hosted Rust LLM gateway with OpenAI-compatible APIs, load balancing, failover, and a reusable Rust kernel.117 stars · 9 skills
Skills by majiayu000, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Multi-source deep research using firecrawl and exa MCPs. An agent skill from majiayu000/claude-skill-registry. | majiayu000/ | 666 | 6 repos | ~1.1k | Automated safety check: Pass | MIT | today |
| 2 | Audits and repairs how coding-agent Skills are owned, copied and exposed across runtimes, from canonical sources to quarantine and retirement. | majiayu000/ | 286 | — | ~3k | Automated safety check: Pass | MIT | today |
| 3 | Neural search via Exa MCP for web, code, and company research. | majiayu000/ | 666 | 5 repos | ~856 | Automated safety check: Pass | MIT | today |
| 4 | Scans a repository for real evidence and proposes, or on request writes, a small stack of root and scoped AGENTS.md files with validation commands and generated-file boundaries. | majiayu000/ | 286 | — | ~1.5k | Automated safety check: Pass | MIT | today |
| 5 | LiteLLM-RS Authentication Architecture. An agent skill from majiayu000/litellm-rs. | majiayu000/ | 117 | — | ~1.9k | Automated safety check: Pass | MIT | today |
| 6 | Unified media generation via fal.ai MCP — image, video, and audio. | majiayu000/ | 666 | 5 repos | ~1.7k | Automated safety check: Pass | MIT | today |
| 7 | Plans, produces or diagnoses evidence-backed product demo videos: script, capture plan, pacing checks and verified final media built on real product behavior. | majiayu000/ | 286 | — | ~3.3k | Automated safety check: Pass | MIT | today |
| 8 | LiteLLM-RS response caching architecture. An agent skill from majiayu000/litellm-rs. | majiayu000/ | 117 | — | ~2k | Automated safety check: Pass | MIT | today |
| 9 | 9.Pyzotero Interact with Zotero reference management libraries using the pyzotero Python client. | majiayu000/ | 666 | 5 repos | ~1.6k | Automated safety check: Notes | MIT | today |
| 10 | Single entry point that routes long or ambiguous agent tasks, checks live state, bounds autonomous loops and leaves a resumable handoff. | majiayu000/ | 286 | — | ~2.1k | Automated safety check: Pass | MIT | today |
| 11 | LiteLLM-RS Configuration Architecture. An agent skill from majiayu000/litellm-rs. | majiayu000/ | 117 | — | ~3.2k | Automated safety check: Pass | MIT | today |
| 12 | Scans a repository, its lockfiles and node_modules for known malicious npm package versions and install-time indicators, using a read-only Python scanner. | majiayu000/ | 286 | — | ~1.5k | Automated safety check: Pass | MIT | today |
| 13 | Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. | majiayu000/ | 666 | 4 repos | ~619 | Automated safety check: Notes | MIT | today |
| 14 | LiteLLM-RS Error Handling Architecture. An agent skill from majiayu000/litellm-rs. | majiayu000/ | 117 | — | ~2k | Automated safety check: Pass | MIT | today |
| 15 | Product management helpers: a RICE scoring script, an interview transcript analyzer and PRD templates for prioritizing features, synthesizing research and writing requirements. | majiayu000/ | 286 | — | ~2.2k | Automated safety check: Pass | MIT | today |
| 16 | Perform pairwise sequence alignment using Biopython Bio.Align.PairwiseAligner. | majiayu000/ | 666 | 4 repos | ~1.7k | Automated safety check: Pass | MIT | today |
| 17 | LiteLLM-RS Observability Architecture. An agent skill from majiayu000/litellm-rs. | majiayu000/ | 117 | — | ~1.3k | Automated safety check: Pass | MIT | today |
| 18 | Audits a repository's agent-readable context, from AGENTS.md and CLAUDE.md to skills and PRODUCT or TECH specs, and recommends the smallest useful improvements. | majiayu000/ | 286 | — | ~1.9k | Automated safety check: Pass | MIT | today |
| 19 | Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. | majiayu000/ | 666 | 4 repos | ~2.4k | Automated safety check: Pass | MIT | today |
| 20 | LiteLLM-RS provider system in two tiers - data-driven OpenAI-compatible catalog entries auto-routed through OpenAILikeProvider, plus code-based provider modules implementing the LLMProvider trait… | majiayu000/ | 117 | — | ~4.9k | Automated safety check: Pass | MIT | today |
| 21 | Review whether a repository's coding-agent harness can reliably carry work from intent through controlled execution, verification, delivery, and learning. | majiayu000/ | 286 | — | ~3.5k | Automated safety check: Pass | MIT | today |
| 22 | 22.SEO Images Image optimization analysis for SEO and performance. An agent skill from majiayu000/claude-skill-registry. | majiayu000/ | 666 | 4 repos | ~1.7k | Automated safety check: Notes | MIT | today |
| 23 | LiteLLM-RS Routing Architecture. An agent skill from majiayu000/litellm-rs. | majiayu000/ | 117 | — | ~1.9k | Automated safety check: Pass | MIT | today |
| 24 | Route substantial coding or repository-review work through a two-stage Sol commander/verifier and separate Luna Max CLI worker. | majiayu000/ | 286 | — | ~3.3k | Automated safety check: Pass | MIT | today |
| 25 | LiteLLM-RS Streaming Architecture. An agent skill from majiayu000/litellm-rs. | majiayu000/ | 117 | — | ~2.1k | Automated safety check: Pass | MIT | today |
| 26 | Access real-time and historical stock market data, forex rates, cryptocurrency prices, commodities, economic indicators, and 50+ technical indicators via the Alpha Vantage API. | majiayu000/ | 666 | 3 repos | ~1.6k | Automated safety check: Pass | MIT | today |
| 27 | 27.Codex Agent A skill your agent uses when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. | majiayu000/ | 286 | — | ~1.9k | Automated safety check: Pass | MIT | today |
| 28 | 28.AWS S3 Configure S3 buckets, policies, and lifecycle rules. An agent skill from majiayu000/claude-skill-registry. | majiayu000/ | 666 | 3 repos | ~3.1k | Automated safety check: Pass | MIT | today |
| 29 | LiteLLM-RS Provider 开发指南。用于添加新 provider（Tier 1 catalog 条目或 Tier 2 代码实现）、统一错误处理，或把旧错误枚举迁移到 ProviderError。 | majiayu000/ | 117 | — | ~3.1k | Automated safety check: Pass | MIT | today |
| 30 | 端到端产品教练 — 把一句话想法走到 PRD + 可点击 HTML 原型。会顶嘴、强制砍功能、用 Nielsen + Norman 做友好性硬检。Use when user 说"我有一个想法"、"想做一个产品"、"做 MVP"、"写 PRD"、"做用户友好的产品"，或调用插件命令 /idea-coach:idea。Do NOT use when 用户已有完整 PRD 在跑、明确说"只… | majiayu000/ | 286 | — | ~1.2k | Automated safety check: Pass | MIT | today |
| 31 | This skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create belief-desire-intention models", "transform RDF to beliefs", "build cognitive… | majiayu000/ | 666 | 3 repos | ~2.5k | Automated safety check: Pass | MIT | today |
| 32 | 32.Android CLI Orchestrates Android development tasks including project creation, deployment, SDK management, and environment diagnostics using the android command-line tool. | majiayu000/ | 666 | 8 repos | ~2.7k | Automated safety check: Pass | MIT | today |
| 33 | Safely diagnose and improve local network speed, latency, jitter, DNS, Wi-Fi, Ethernet, macOS network services, and bufferbloat. | majiayu000/ | 286 | — | ~2.8k | Automated safety check: Notes | MIT | today |
| 34 | 用于审计Claude技能和命令的质量。支持快速扫描（仅变更技能）和全面盘点模式，采用顺序子代理批量评估. An agent skill from majiayu000/claude-skill-registry. | majiayu000/ | 666 | 7 repos | ~1.9k | Automated safety check: Pass | MIT | today |
| 35 | Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. | majiayu000/ | 666 | 6 repos | ~6.3k | Automated safety check: Notes | MIT | today |
| 36 | Codified expertise for managing carrier portfolios, negotiating freight rates, tracking carrier performance, allocating freight, and maintaining strategic carrier relationships. | majiayu000/ | 666 | 6 repos | ~5.9k | Automated safety check: Pass | Apache-2.0 | today |
| 37 | Filter alignments by flags, mapping quality, and regions using samtools view and pysam. | majiayu000/ | 666 | 3 repos | ~1.9k | Automated safety check: Pass | MIT | today |
| 38 | Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching. | majiayu000/ | 666 | 6 repos | ~1.4k | Automated safety check: Pass | MIT | today |
| 39 | Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. | majiayu000/ | 666 | 6 repos | ~1k | Automated safety check: Pass | MIT | today |
| 40 | Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases. | majiayu000/ | 666 | 6 repos | ~1.6k | Automated safety check: Pass | MIT | today |
| 41 | A skill your agent uses when a skill is brittle, drifting, repeatedly failing, or needs a Reliable Skill Contract. | majiayu000/ | 286 | — | ~1.3k | Automated safety check: Pass | MIT | today |
| 42 | 42.Threads A skill your agent uses when the user explicitly asks for $threads, Codex-native subagents, 开几个子 agent, or a GitHub issue/PR queue needing parallel lanes, worktrees, review/merge gates, and closure… | majiayu000/ | 286 | — | ~8.7k | Automated safety check: Pass | MIT | today |
| 43 | A skill your agent uses when creating elaborate, multi-component claude.ai HTML artifacts with React, Tailwind CSS, shadcn/ui, state management, routing, or complex frontend structure; not for… | majiayu000/ | 286 | — | ~744 | Automated safety check: Pass | MIT | today |
| 44 | 44.Xray Investigate how a concept, code path, application, network flow, system, incident, document, or local artifact actually works, then deliver a two-depth visual HTML explainer with a dead-simple… | majiayu000/ | 286 | — | ~3.4k | Automated safety check: Pass | MIT | today |
| 45 | Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+. | majiayu000/ | 666 | 5 repos | ~2k | Automated safety check: Pass | MIT | today |
| 46 | 46.Scvelo RNA velocity analysis with scVelo. An agent skill from majiayu000/claude-skill-registry. | majiayu000/ | 666 | 5 repos | ~2.6k | Automated safety check: Pass | BSD-3-Clause | today |
| 47 | Trains and applies base-resolution deep learning models on ChIP-seq / ChIP-nexus / CUT&RUN data. | majiayu000/ | 666 | 3 repos | ~3.6k | Automated safety check: Pass | MIT | today |
| 48 | Generate pileup data for variant calling using samtools mpileup and pysam. | majiayu000/ | 666 | 3 repos | ~2.2k | Automated safety check: Pass | MIT | today |
Questions, answered from the data.
What is the best skill by majiayu000?
Deep Research from majiayu000/claude-skill-registry ranks first of the 1,379 skills by majiayu000 listed here, with the highest score: its repository has 666 GitHub stars, 6 other GitHub owners carry a copy, its SKILL.md loads about 1.1k tokens and it passes the automated safety check with no findings. Next come Skill Ecosystem Doctor and Exa Search.
Are majiayu000's skills official?
None yet. All 1,379 skills by majiayu000 listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.