YAML
A human-readable data serialization format widely used for configuration files, data exchange, and persistence. It expresses hierarchy through indentation, and the YAML 1.2 specification is fully compatible with JSON.
Core Facts
YAML has become the de facto standard configuration language in the DevOps domain and is widely adopted by Kubernetes, Ansible, and GitHub Actions.
Skills files typically contain YAML front matter (for trigger condition evaluation) and Markdown body text (for defining workflows and output specifications).
Each Skill declares its own functional description, API endpoint, authentication method, and parameter specifications through a configuration file (typically in YAML or JSON format).
Timeline (last 90 days)
In a test with regular tabular data of 10 rows and 4 fields per row, encoded using the cl100k_base tokenizer, JSON was 323 tokens and 963 characters, while YAML was 221 tokens and 590 characters, with YAML ahead by 31.6%; the TOON format was 97 tokens and 235 characters, 70% fewer than JSON and 56.1% fewer than YAML.
A practical engineering pattern is: keep the data actually flowing inside the system as JSON, convert only the text handed to the model into YAML or TOON, and then require the model to return in JSON format anything that needs to go back into code.
For nested, non-tabular data (application configuration, a single object with sub-objects), the size of YAML and TOON is almost identical, because the TOON specification borrows YAML's indentation syntax to handle non-tabular structures; regular arrays of objects are TOON's home turf, where its advantage is obvious.
In a test with a nested configuration object, encoded using OpenAI's cl100k_base tokenizer, JSON was 99 tokens and 322 characters, while YAML was 66 tokens and 223 characters, with YAML reducing the token count by 33.3%.
The OCR workflow includes steps such as starting from a clear image, extracting relevant information, converting to a suitable format (such as JSON, CSV, XML, YAML), validating the extraction results, and connecting to applications.
Andrej Karpathy proposed the LLM Wiki pattern, which uses Markdown pages plus YAML metadata to organize knowledge, allowing humans and AI agents to maintain it together and query it on demand.
Docker has launched an open-source tool called Docker Agent that allows AI agents to be defined with a single YAML file.
Writing agent definitions as YAML makes them committable to Git, reviewable in code review, shareable across teams, and trackable across versions.
Docker Agent uses YAML declarative configuration to describe agent teams rather than hand-writing agent code.
The team defines their own code specification policies in YAML format.
16 more timeline events
All Facts (20)
YAML has become the de facto standard configuration language in the DevOps domain and is widely adopted by Kubernetes, Ansible, and GitHub Actions.
70%VerifiedSkills files typically contain YAML front matter (for trigger condition evaluation) and Markdown body text (for defining workflows and output specifications).
65%VerifiedEach Skill declares its own functional description, API endpoint, authentication method, and parameter specifications through a configuration file (typically in YAML or JSON format).
65%Unverifiedrunn通过YAML文件定义多步骤测试场景
95%UnverifiedDify采用YAML格式的DSL文件来定义AI应用的所有配置细节
90%UnverifiedIncident.io的Eval以YAML文件的形式存放在Go代码的prompt旁边
90%UnverifiedOrchestrator的YAML模板实现了「流程即代码」（Pipeline as Code）的理念，使团队最佳实践以结构化、可审计、可复用的形式沉淀
85%Unverified正确的AI接口自动化思路是用框架管理用例，让AI维护YAML/CEL格式的用例数据，而非让AI编写代码
80%UnverifiedYAML因语法简洁、支持注释、天然支持嵌套结构，成为存储接口测试数据的首选格式
70%UnverifiedSKILL.md is written in Markdown format, with the top of the file carrying metadata via YAML Front Matter or a header block, containing fields such as name, description, and trigger.
60%UnverifiedHermes的技能系统使用YAML Front Matter作为索引，实现渐进式披露，只在需要时才加载完整技能内容
60%UnverifiedA practical engineering pattern is: keep the data actually flowing inside the system as JSON, convert only the text handed to the model into YAML or TOON, and then require the model to return in JSON format anything that needs to go back into code.
50%UnverifiedIn a test with a nested configuration object, encoded using OpenAI's cl100k_base tokenizer, JSON was 99 tokens and 322 characters, while YAML was 66 tokens and 223 characters, with YAML reducing the token count by 33.3%.
50%UnverifiedIn a test with regular tabular data of 10 rows and 4 fields per row, encoded using the cl100k_base tokenizer, JSON was 323 tokens and 963 characters, while YAML was 221 tokens and 590 characters, with YAML ahead by 31.6%; the TOON format was 97 tokens and 235 characters, 70% fewer than JSON and 56.1% fewer than YAML.
50%UnverifiedFor nested, non-tabular data (application configuration, a single object with sub-objects), the size of YAML and TOON is almost identical, because the TOON specification borrows YAML's indentation syntax to handle non-tabular structures; regular arrays of objects are TOON's home turf, where its advantage is obvious.
50%UnverifiedThe OCR workflow includes steps such as starting from a clear image, extracting relevant information, converting to a suitable format (such as JSON, CSV, XML, YAML), validating the extraction results, and connecting to applications.
50%UnverifiedAndrej Karpathy proposed the LLM Wiki pattern, which uses Markdown pages plus YAML metadata to organize knowledge, allowing humans and AI agents to maintain it together and query it on demand.
50%UnverifiedWriting agent definitions as YAML makes them committable to Git, reviewable in code review, shareable across teams, and trackable across versions.
50%UnverifiedDocker Agent uses YAML declarative configuration to describe agent teams rather than hand-writing agent code.
50%UnverifiedThe team defines their own code specification policies in YAML format.
50%