AI model or service
Anthropic API agent skills for Claude Code, Codex and other agents.
- skills
- 74
- official
- 4
- Type
- AI model or service
- Website
- anthropic.com
- Official GitHub
- anthropics
Anthropic API skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
Official (4 skills)
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Wires up an Airbyte connector for use in a PydanticAI, Claude SDK, or other agent. | airbytehq/ | 135 | — | ~1.7k | Automated safety check: Notes | Unknown | today |
| 2 | Builds a complete agent with multiple Airbyte connectors using PydanticAI or Claude SDK. | airbytehq/ | 135 | — | ~1.7k | Automated safety check: Notes | Unknown | today |
| 3 | Reference documentation for the Airbyte per-connector typed SDK packages | airbytehq/ | 135 | — | ~202 | Automated safety check: Pass | Unknown | today |
| 4 | A skill your agent uses when the user wants to migrate code that calls OpenAI, Gemini/Google AI, or the Anthropic API to Amazon Bedrock — a pure model/SDK rewrite. | aws/ | 2.8k | — | ~16k | Automated safety check: Pass | Apache-2.0 | today |
Community
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 5 | Reference of Claude API examples and guides covering tool use, vision, RAG, classification, summarization, text-to-SQL, prompt caching and agent patterns. | 2025Emma/ | 23k | 1 repo | ~2.2k | Automated safety check: Pass | MIT | 9 mo ago |
| 6 | Fetches current documentation for third-party APIs and SDKs with the chub CLI before the agent writes code against them, instead of relying on remembered API shapes. | andrewyng/ | 14k | 2 repos | ~775 | Automated safety check: Pass | MIT | 4 mo ago |
| 7 | Gives text-only models sight by running the modlens CLI on an image path or URL and returning structured JSON evidence with transcribed text, layout and semantics. | liustack/ | 4.1k | — | ~1.3k | Automated safety check: Notes | MIT | 3 days ago |
| 8 | Build apps with the Claude API or Anthropic SDK. An agent skill from Kocoro-lab/Kocoro. | Kocoro-lab/ | 414 | 8 repos | ~4.5k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 9 | Map of the agent-squad Python framework for async multi-agent orchestration: which agent, classifier, storage and tool provider to pick, and the pitfalls to avoid. | 2FastLabs/ | 7.8k | — | ~4.7k | Automated safety check: Pass | Apache-2.0 | today |
| 10 | 10.Perfup Autonomous performance optimization: research, PoC, benchmark, implement, review, PR | raullenchai/ | 3.9k | — | ~1.6k | Automated safety check: Notes | Unknown | today |
| 11 | Bump or upgrade the pinned versions of Helmor's bundled agent CLIs, SDKs, and supporting binaries — Claude Code + claude-agent-sdk (lockstep), Codex, Cursor SDK, OpenCode, Kimi, Pi, and gh / glab /… | dohooo/ | 1.3k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 12 | Scans Python agent code for framework imports and recommends the matching Omnigent executor type, or says when the framework is not natively supported yet. | omnigent-ai/ | 11k | — | ~610 | Automated safety check: Pass | Apache-2.0 | today |
| 13 | Evaluate US stocks under an Alpaca trend and relative-strength framework, and prioritize defined-risk net-credit income spreads: Bull Put/Bear Call first, Iron Condor second. | starriv/ | 174 | — | ~4.5k | Automated safety check: Notes | No licence | 4 days ago |
| 14 | 14.Release mlx-serve pre-release validation checklist, CalVer versioning, release steps, and CHANGELOG style. | ddalcu/ | 1.8k | — | ~1.8k | Automated safety check: Pass | Unknown | today |
| 15 | Operates the ccproxy inspector MITM system for intercepting, inspecting, and transforming LLM API traffic. | starbaser/ | 348 | — | ~2.7k | Automated safety check: Pass | Unknown | 1 mo ago |
| 16 | Routes a NanoClaw agent group to a local Ollama model instead of the Anthropic API, using environment overrides and an optional block on Anthropic hosts. | nanocoai/ | 31k | 1 repo | ~1.5k | Automated safety check: Pass | MIT | today |
| 17 | 17.Deepdive Meta-research под вопрос или решение: веб-поиск, источники, Q&A отчёт с цитатами по файлам для повторного использования. | Socialpranker/ | 372 | — | ~5.2k | Automated safety check: Pass | MIT | 3 days ago |
| 18 | Stop and consult this skill whenever your response would include specific facts about Anthropic's products. | syahiidkamil/ | 397 | 4 repos | ~651 | Automated safety check: Pass | No licence | 3 mo ago |
| 19 | Guides users through ccproxy as an OpenAI-compatible and Anthropic-compatible LLM API server with SDK integration, OAuth authentication, sentinel key substitution, model routing, and troubleshooting. | starbaser/ | 348 | — | ~4k | Automated safety check: Pass | Unknown | 1 mo ago |
| 20 | 20.Catchup Answer "where did I stop?" for this project. An agent skill from Avijit07x/claude-db. | Avijit07x/ | 231 | — | ~489 | Automated safety check: Pass | Apache-2.0 | today |
| 21 | 21.Update Libs Update the libs/ SDK submodules (openai-go, anthropic-sdk-go, go-genai) to new upstream/fork versions, adapt tingly-box to API changes, and verify with build + vet + tests. | tingly-dev/ | 351 | — | ~830 | Automated safety check: Pass | MPL-2.0 | today |
| 22 | Guides building, debugging and tuning apps on the Claude API and Anthropic SDK, including prompt caching, and migrating code between Claude model versions. | warpdotdev/ | 65k | 3 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 | today |
| 23 | 23.Get API Docs A skill your agent uses when you need documentation for a third-party library, SDK, or API before writing code that uses it — for example, "use the OpenAI API", "call the Stripe API", "use the… | sudomakes/ | 162 | — | ~1k | Automated safety check: Pass | MIT | 3 mo ago |
| 24 | 24.Cdb Scan Map this codebase into project memory — a code graph of every symbol and how they connect, plus a written profile of stack, layout, conventions and workflows. | Avijit07x/ | 231 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | today |
| 25 | Audit coherence across an arrow of intent by running two parallel fresh Claude sessions — one reconstructs code from a single EARS, the other reconstructs the EARS from stripped code — then… | jszmajda/ | 104 | — | ~2.9k | Automated safety check: Pass | MIT | today |
| 26 | 改 VS Code 语言模型提供商、多协议请求/流解析、工具调用、thinking、models.dev 发现或 Commit Message。Use when: genericProvider, lmChatProviderAdapter, coding-plans.vendors, apiStyle, anthropic/openai 兼容。 | jqknono/ | 138 | — | ~256 | Automated safety check: Pass | MIT | today |
| 27 | 27.Handoff Write a short handoff note for the next chat or a teammate, with what is done, what is open and what comes next. | Avijit07x/ | 231 | — | ~575 | Automated safety check: Pass | Apache-2.0 | today |
| 28 | 28.Aivis Claude API web-search 可见度(代理测量):用冻结题库反复探测 Claude API(websearch), 以确定性规则统计品牌被提及/被引用的频率与结构,输出带不确定区间、可审计的报告。 | onism1767-creator/ | 166 | — | ~757 | Automated safety check: Pass | MIT | 3 mo ago |
| 29 | 29.Deploy Claude Inspector macOS 배포 스킬. An agent skill from kangraemin/claude-inspector. | kangraemin/ | 131 | — | ~739 | Automated safety check: Notes | MIT | today |
| 30 | Gives patterns for generating a minimal, valid Omnigent agent directory: the config.yaml fields, the right executor type, and the files each agent needs. | omnigent-ai/ | 11k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | today |
| 31 | A developer guide to adding compact memory to an agent: when to trigger compaction, how to fork a compactor sub-agent, what the summary holds, and how to restore it. | simbajigege/ | 184 | — | ~2.5k | Automated safety check: Pass | MIT | 1 mo ago |
| 32 | 32.Relay Probe 探测AI中转站连接性、延迟和吞吐量。支持Anthropic原生API和OpenAI兼容格式. An agent skill from AetherCore-Dev/relay-radar. | AetherCore-Dev/ | 141 | — | ~331 | Automated safety check: Notes | No licence | 2 days ago |
| 33 | 33.Dev Bounce 코드를 고치거나 새로 짜는 작업을 단계별 워크플로우로 진행한다. An agent skill from kangraemin/claude-inspector. | kangraemin/ | 131 | — | ~1.8k | Automated safety check: Pass | MIT | today |
| 34 | 更新编码套餐与 OpenRouter 指标/套餐 JSON、修复抓取失败或 pending。Use when: pricing:fetch, metrics:fetch, openrouter:plans:fetch, provider-pricing.json, dashboard 数据过期或 CI 定价 issue。 | jqknono/ | 138 | — | ~263 | Automated safety check: Notes | MIT | today |
| 35 | 35.Code Review AI-powered code review for diffs and individual files using LLM analysis | initializ/ | 223 | — | ~3k | Automated safety check: Pass | Apache-2.0 | 6 days ago |
| 36 | Extracts research papers from .bib and .html venue files, filters them by relevance, labels them with a two-level taxonomy through Claude and rebuilds a website. | PurCL/ | 637 | — | ~5.2k | Automated safety check: Warn | No licence | 2 mo ago |
| 37 | 37.E2E Run e2e and unit tests for Claude Inspector. An agent skill from kangraemin/claude-inspector. | kangraemin/ | 131 | — | ~682 | Automated safety check: Pass | MIT | today |
| 38 | Wire encrypted credentials to environment variables using the credential: convention. | growthxai/ | 440 | — | ~930 | Automated safety check: Notes | Apache-2.0 | today |
| 39 | 39.Claude API Anthropic Claude API 的 Python 和 TypeScript 使用模式。涵盖 Messages API、流式处理、工具使用、视觉功能、扩展思维、批量处理、提示缓存和 Claude Agent SDK。适用于使用 Claude API 或 Anthropic SDK 构建应用程序的场景。 | loulanyue/ | 272 | 1 repo | ~1.9k | Automated safety check: Pass | MIT | 2 days ago |
| 40 | Builds and queries a local contextual BM25 index over an Obsidian vault, with optional Nomic reranking through Ollama and strict consent rules before any text leaves the machine. | AgriciDaniel/ | 15k | — | ~1.4k | Automated safety check: Pass | MIT | 26 days ago |
| 41 | EdgeOne Makers platform development router — the single entry point for building, storing data, and deploying on Tencent EdgeOne Makers. | TencentEdgeOne/ | 1.9k | 1 repo | ~516 | Automated safety check: Pass | MIT | 14 days ago |
| 42 | Detect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the claude-verify project. | agentscope-ai/ | 867 | 1 repo | ~5k | Automated safety check: Pass | Apache-2.0 | 26 days ago |
| 43 | Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. | spec-kitty/ | 1.7k | — | ~8.5k | Automated safety check: Pass | MIT | today |
| 44 | 44.E2E Live 実 Claude API を叩く総合テスト(全カテゴリ)を実行する。リリース前ではなく、定期的に手動で回して回帰を検出するための skill。yarn dev が起動済みであることが前提。 | receptron/ | 367 | — | ~580 | Automated safety check: Pass | MIT | today |
| 45 | 実 Claude API + Docker サンドボックスを叩く docker カテゴリの総合テストを実行する。DISABLESANDBOX を unset した状態で yarn dev が起動済みであることが前提(サンドボックス off だと全 test が test.skip で抜ける)。 | receptron/ | 367 | — | ~544 | Automated safety check: Pass | MIT | today |
| 46 | Has a fresh-context adversary attack a blog post, recommendation, analysis brief or piece of code before you ship it, using a profile suited to that kind of artifact. | oaustegard/ | 150 | — | ~3.4k | Automated safety check: Pass | MIT | 5 days ago |
| 47 | Starter: one-screen provider health summary — availability, auth method, version drift, and cost posture for every seatable provider | nyldn/ | 4.2k | 1 repo | ~491 | Automated safety check: Pass | MIT | today |
| 48 | 48.Claude API Help with Claude/LLM API usage, models, and integration patterns. | terrense/ | 121 | — | ~155 | Automated safety check: Pass | No licence | 3 mo ago |
Questions, answered from the data.
What is the best Anthropic API skill?
Bootstrapping Agent (official) from airbytehq/airbyte-agent-sdk ranks first of the 74 Anthropic API skills listed here, with the highest score: its repository has 135 GitHub stars, its SKILL.md loads about 1.7k tokens and it has informational notes only in the automated safety check. Next come Building Multi Connector Agent and Airbyte SDK Reference.
Is there an official Anthropic API skill?
4 of the 74 Anthropic API skills are official, published by the vendor's own GitHub organization: Bootstrapping Agent, Building Multi Connector Agent, Airbyte SDK Reference and LLM To Bedrock.
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.