Lint a JSON OpenAPI 3.x document offline for missing info, missing paths, missing or duplicate operationIds, missing descriptions, undeclared path parameters and unresolved local references. Deterministic pass/fail results plus JSON and Markdown reports, without contacting a server or copying reference targets into reports.
Catch broken or risky OpenAPI specs before codegen or publish.
Catch bad YAML before it breaks your deploy: a line-based structural linter for YAML configs, CI workflows and compose files that flags tab indentation, duplicate keys, missing spaces after colons, inconsistent indentation, unclosed flow collections and quotes, undefined aliases and duplicate anchors, entirely offline with CI-friendly exit codes and JSON and Markdown reports that never copy mapping values.
From a local ISSUE file to a verified, committed deliverable — with a fresh-subagent acceptance gate that catches wrong screenshots and leaked logic.
An interactive Claude Skill that generates a customized, security-reviewed Terraform repository for Amazon Bedrock AgentCore, IAM least-privilege policies, Knowledge Base + vector store, Gateway tool registration, and Runtime deployment, scoped to your actual agent instead of a generic template dump.
Generate, audit, co-author, and maintain software documentation under a style your agent cannot drift from. Version 3.0.0 adds controlled language (STE-derived), a distilled house style enforced by mechanical gates (vale, markdownlint, cspell), canonical vocabulary that steers agents, OKF v0.2 knowledge bundles with a working attester, and the 2026 spec-driven development landscape with 11 tool-neutral templates. Works across software, hardware, firmware, and embedded projects in any runtime.
Review AI agents, automation workflows, and project architectures for design gaps, risks, missing requirements, and improvement opportunities.
离线审计已保存HTML中的标题、描述及社交卡声明，定位缺失、重复和模板差异，交付JSON证据报告。下载到自己的Agent客户端运行，需CPython 3.11.1；不联网抓取、不执行网页脚本，也不承诺搜索排名。
Catch malformed XML before it breaks the parse.