kanyun-inc

Octopus OpenAPI 接口指南。涵盖 ApplicationKey 与 V1/V2（OC-HMAC-SHA256 / OC-HMAC-SHA256-2）鉴权、Python/Java SDK、日志/Trace/指标（含 V2.0）/错误追踪/告警/服务 APM/大盘/用户/LLM/RUM/事件等 HTTP 接口与限流说明。用于对接 Octopus 可观测数据开放 API。

Query Octopus observability platform — logs, alerts, traces, metrics, issues, services, LLM, RUM, events. Triggers on "logs", "alerts", "traces", "metrics", "octopus", "observability", "error tracking", "RUM", "LLM observability"

Octopus 可观测平台数据采集指南，涵盖 Log/Trace/Metric 三种数据类型的采集方式。包括 octopus-otel-collector 部署、HTTP 接口上传（curl/Java/JS）、Kafka 接收、Java trace javaagent 接入、手动打点（Skywalking/OpenTelemetry）、Node.js 日志与指标上报、Python 日志与指标上报、低内存场景配置。用于指导各语言服务接入 Octopus 可观测数据采集。

Octopus LLM 观测接入指南，涵盖 LLM Trace 核心概念（LLM Span/Span Kind/LLM Trace）、Java SDK（opentelemetry-kanyun-api）完整接入（traceAgent/traceLLM/traceTool/traceFluxWorkflow）、TypeScript SDK（opentelemetry-kanyun-extension）接入、Python SDK 接入、LLM 成本配置、查询语法。用于指导 LLM 应用接入 Octopus 可观测追踪。

Octopus 日志搜索与分析指南，涵盖日志搜索语法（字段搜索/全文搜索/逻辑运算/模糊匹配）、绘图分析（count/avg/max/min/sum/percentile/heatmap + group by）、请求总览、日志生成指标、日志生命周期、数据管理、保留字段、全文检索分词策略。用于指导在 Octopus 平台进行日志查询、分析和指标生成。

Octopus 指标查询指南，涵盖指标类型（Count/Gauge/Histogram）、QL 模式查询语法（时间聚合/空间聚合/as_count/as_rate/表达式）、时间聚合函数（advanced_rollup/rollup/moving_rollup）、Trace Metrics。用于指导在 Octopus 平台进行指标查询和 QL 编写。

Octopus 大前端观测（RUM）与 Web SDK 使用指南。涵盖 RUM 核心概念（Session/View/Action/Resource/Error）、Web 端接入、用户行为追踪、页面性能监控（LCP/INP/CLS）、RUM 查询语法、Browser Logs SDK（@octopus-sdk/browser-logs）完整接入与配置、RUM SDK（@octopus-sdk/browser-rum）、Source Map 上传、部署事件关联。用于指导前端项目接入 Octopus RUM 和日志 SDK。

帮助用户了解和使用 octopus-web-sdk 前端监控 SDK 和 octopus-cli 命令行工具。答疑、配置指导、问题排查。触发："octopus sdk"、"前端监控"、"RUM"、"日志上报"、"octopus-cli"、"sourcemap 上传"

Teaches AI agents how to use reskill — a Git-based package manager for AI agent skills. Covers CLI commands, install formats, configuration, publishing, and common workflows.

Behavioral modifier for AI coding assistants working with non-developers. Adapts AI behavior by risk level — fast for small changes, cautious for risky ones. Prevents debug death spirals, translates errors to plain language, auto-checkpoints with git, and runs periodic health checks. Always active, zero manual trigger needed.

Assesses code comprehensibility and maintainability risk. Use when the user asks about code confidence, risk, maintainability, tech debt, code health, or whether code is safe to change. Also use when the user asks to analyze code quality, scan for risks, check if code is messy or complex, audit code, do a code checkup, find weak spots, assess what needs refactoring, or asks about code trust, hidden risks, gotchas, or onboarding to a codebase.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. Uses reskill as the package manager.

Detects content drift between skill files and their source documents. Helps maintain skills that are derived from other documentation by comparing content and flagging outdated sections.

Read and write company DocSync documents. Triggers on "docs", "documents", "upload file", "read space", "docz", "DocSync", "save file", "rollback", "restore", "trash", "version history", "comment", "share link", "diff"