AI model or service
Dify agent skills for Claude Code, Codex and other agents.
- skills
- 31
- Type
- AI model or service
- Website
- dify.ai
- Official GitHub
- langgenius
- Reviews
- See Dify on Enlisted
Dify skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Reviews frontend changes under `web/` or `packages/dify-ui/` for concrete defects and broken project contracts, using routed rule packs and a severity scale for findings. | langgenius/ | 158k | — | ~938 | Automated safety check: Pass | Unknown | today |
| 2 | Use when implementing or refactoring React/TypeScript components and the task requires decisions about component ownership, feature boundaries… | langgenius/ | 158k | — | ~626 | Automated safety check: Pass | Unknown | today |
| 3 | Base skill for the difyctl CLI: discover a Dify server's operations through help output and run them as commands, always with JSON output. | langgenius/ | 158k | — | ~1.4k | Automated safety check: Pass | Unknown | today |
| 4 | Conduct comprehensive deep research on any topic using Dify-powered workflow - searches documentation, academic papers, tutorials, APIs, best practices, and returns structured analysis with insights. | 21pounder/ | 120 | 2 repos | ~883 | Automated safety check: Notes | Apache-2.0 | 4 mo ago |
| 5 | Use when writing or changing Vitest or React Testing Library tests under `web/` or `packages/dify-ui/`, or when the user explicitly requests… | langgenius/ | 158k | — | ~242 | Automated safety check: Pass | Unknown | today |
| 6 | Generate Vitest + React Testing Library tests for Dify frontend components, hooks, and utilities. | Ohh-889/ | 795 | 1 repo | ~2.5k | Automated safety check: Pass | MIT | 1 mo ago |
| 7 | 从 AI 产品经理视角撰写微信公众号文章。涵盖 AI 产品拆解、场景解决方案、效率提升实战、产品方法论、行业观察。当用户说"写一篇关于XXX的文章"、"分析一下XXX产品"、"聊聊XXX"时使用。 | BND-1/ | 318 | — | ~2.6k | Automated safety check: Notes | No licence | 8 mo ago |
| 8 | Research a Dify feature before writing or optimizing documentation. | langgenius/ | 178 | — | ~2.6k | Automated safety check: Pass | CC-BY-4.0 | 7 days ago |
| 9 | Generate Dify workflow DSL files from natural language descriptions. | LingyiChen-AI/ | 175 | — | ~3.6k | Automated safety check: Pass | No licence | 4 mo ago |
| 10 | Tests LangBot's WebUI and core flows through an automated browser and backend logs, with a routing table to reference guides per feature area. | langbot-app/ | 18k | — | ~1k | Automated safety check: Notes | Apache-2.0 | today |
| 11 | Check formatting compliance in changed documentation against writing-guides/formatting-guide.md and tools/translate/formatting-{zh,ja}.md. | langgenius/ | 178 | — | ~2.7k | Automated safety check: Pass | CC-BY-4.0 | 7 days ago |
| 12 | Refactor high-complexity React components in Dify frontend. An agent skill from Ohh-889/skyroc. | Ohh-889/ | 795 | 1 repo | ~3.5k | Automated safety check: Pass | MIT | 1 mo ago |
| 13 | Audit terminology consistency across documentation against the codebase UI labels and the glossary — in prose and in the UI strings shown in screenshots. | langgenius/ | 178 | — | ~2.3k | Automated safety check: Pass | CC-BY-4.0 | 7 days ago |
| 14 | SOP for building LLM applications on Dify — visual workflow + chatflow + agent + RAG knowledge base + plugin marketplace + observability, self-hostable. | agentsope/ | 457 | — | ~5.4k | Automated safety check: Notes | MIT | 1 mo ago |
| 15 | Rule pack for the Service API specs ({en,zh,ja}/api-reference/openapiservice.json): spec conventions, app-type scoping, code-verification rules, and the audit machinery. | langgenius/ | 178 | — | ~2.5k | Automated safety check: Pass | CC-BY-4.0 | 7 days ago |
| 16 | Rule pack for the environment variable reference — en/self-host/deploy/configuration/environments.mdx. | langgenius/ | 178 | — | ~2.5k | Automated safety check: Pass | CC-BY-4.0 | 7 days ago |
| 17 | Builds Opik tracing integrations that live outside the Opik repository, either as standalone opik-* packages or as contributions into projects such as LiteLLM or Dify. | comet-ml/ | 22k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | today |
| 18 | The entry point for writing or revising any documentation in this repo: user guides, deployment pages, plugin-dev pages, API specs, the env-var reference, CLI pages. | langgenius/ | 178 | — | ~3.2k | Automated safety check: Pass | CC-BY-4.0 | 7 days ago |
| 19 | Judge a finished draft as the docs owner would: a fresh agent reads it against the style guide and the reference page in its genre, marks the sentences that fall short, and returns a ship verdict on… | langgenius/ | 178 | — | ~1.5k | Automated safety check: Pass | CC-BY-4.0 | 7 days ago |
| 20 | Rule pack for Dify user-guide pages — en/{cloud,self-host}/use-dify/, en/develop-plugin/, and en/self-host/deploy/. | langgenius/ | 178 | — | ~2k | Automated safety check: Pass | CC-BY-4.0 | 7 days ago |
| 21 | Post-writing verification from the reader's perspective. An agent skill from langgenius/dify-docs. | langgenius/ | 178 | — | ~1.3k | Automated safety check: Pass | CC-BY-4.0 | 7 days ago |
| 22 | Judge a zh or ja page as the owner of that edition would: a fresh agent reads it beside its English source against the language's formatting guide and the glossary, marks the sentences that fall… | langgenius/ | 178 | — | ~1.2k | Automated safety check: Pass | CC-BY-4.0 | 7 days ago |
| 23 | Neutral, framework-agnostic decision tree for project kickoff: "which agent / RAG / LLM framework should I reach for?" Synthesizes the ecosystem sections of 7 landmark-project SOPs (LangGraph… | agentsope/ | 457 | — | ~5.8k | Automated safety check: Pass | MIT | 1 mo ago |
| 24 | Wrapper for the Dify workflow DSL CLI. An agent skill from HKUDS/CLI-Anything. | HKUDS/ | 52k | — | ~445 | Automated safety check: Pass | Apache-2.0 | 15 days ago |
| 25 | Rule pack for the Dify CLI (difyctl) doc set: en/cli/ and the Enterprise develop/cli/ trees. | langgenius/ | 178 | — | ~1.9k | Automated safety check: Pass | CC-BY-4.0 | 7 days ago |
| 26 | Project-kickoff rubric for the self-host vs managed-cloud decision — when is running your own inference engine / LLM platform worth the ops cost vs paying per-token for a managed API? | agentsope/ | 457 | — | ~6.3k | Automated safety check: Pass | MIT | 1 mo ago |
| 27 | 专为Dify工作流案例分享设计的公众号文章生成器,遵循小灰灰公众号写作规范,自动生成包含前言、工作流制作、总结的完整Dify案例文章,配有详细的节点配置、插件安装步骤、代码示例,并支持自动生成图片上传到腾讯云COS图床 | wwwzhouhui/ | 282 | — | ~2.2k | Automated safety check: Notes | No licence | yesterday |
| 28 | 28.Veadk Skills 根据用户的功能需求，完成与 VeADK 相关的功能。 | LeoYeAI/ | 2.2k | 1 repo | ~293 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 29 | 专业的 Dify 工作流 DSL/YML 文件生成器，根据用户业务需求自动生成完整的 Dify 工作流配置文件，支持各种节点类型和复杂工作流逻辑 | wwwzhouhui/ | 282 | — | ~2.7k | Automated safety check: Pass | No licence | yesterday |
| 30 | When the user wants open source strategy, OSS commercialization, or open source growth. | kostja94/ | 1k | — | ~1.4k | Automated safety check: Pass | MIT | yesterday |
| 31 | Review Dify frontend code for correctness, accessibility, component design, dify-ui usage, data/query boundaries, performance, and tests. | aiskillstore/ | 430 | — | ~1.4k | Automated safety check: Pass | No licence | today |
Questions, answered from the data.
What is the best Dify skill?
Frontend Code Review from langgenius/dify ranks first of the 31 Dify skills listed here, with the highest score: its repository has 158k GitHub stars, its SKILL.md loads about 938 tokens and it passes the automated safety check with no findings. Next come Dify Component Writing Guide and Dify Command Line with difyctl.
Is there an official Dify skill?
None yet. All 31 Dify skills 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.