sangyi

Pre-routing ambiguity analysis — scores request clarity and asks clarifying questions when needed (inspired by ouroboros)

中文简介正在准备中。当前显示原文说明。

On explicit /homework invocation, analyze the current and linked previous sessions, extract mistakes (찐빠), and report them via omcustom-feedback with a confirmation gate. Auto-activation on session cleanup/session-end signals is OPT-IN (default OFF) — requires an explicit project/user directive. Use when explicitly auditing recent work for harness gaps.

中文简介正在准备中。当前显示原文说明。

Quantitative agent evaluation using 4-metric framework (correctness/step_ratio/tool_call_ratio/latency_ratio) with ideal trajectory annotation and capability-categorical taxonomy. Use when measuring agent efficiency, comparing agent variants, or gating new agents through correctness→efficiency phases. Complements harness-eval (SE benchmarks) and evaluator-optimizer (qualitative rubric).

中文简介正在准备中。当前显示原文说明。

Auto-detect project context and optimize harness — deactivate unused agents/skills, suggest missing experts, generate project profile

中文简介正在准备中。当前显示原文说明。

Pre-action boundary checking — validates agent tool calls against declared capabilities and task contracts

中文简介正在准备中。当前显示原文说明。

Routes data engineering tasks to the correct DE expert agent. Use when user requests data pipeline design, DAG authoring, SQL modeling, stream processing, or warehouse optimization.

中文简介正在准备中。当前显示原文说明。

YAML-based DAG workflow engine with topological execution and failure strategies

中文简介正在准备中。当前显示原文说明。

Analyze project and auto-configure agents, skills, rules, and guides

中文简介正在准备中。当前显示原文说明。

Multi-LLM adversarial consensus loop — 3+ LLMs compete to find flaws in designs/specs until unanimous agreement is reached

中文简介正在准备中。当前显示原文说明。

Apache Airflow best practices for DAG authoring, testing, and production deployment

中文简介正在准备中。当前显示原文说明。

Alembic migration patterns for naming conventions, safety checks, expand-contract, env.py configuration, and CI integration

中文简介正在准备中。当前显示原文说明。

Audit agent dependencies and references

中文简介正在准备中。当前显示原文说明。

AWS patterns from Well-Architected Framework

中文简介正在准备中。当前显示原文说明。

Fetch Claude Code official documentation. Use when updating local reference docs or checking official spec.

中文简介正在准备中。当前显示原文说明。

Create a new agent with complete structure

中文简介正在准备中。当前显示原文说明。

code-review-graph (CRG) MCP wrapper — token-efficient context retrieval via AST knowledge graph. Exposes 4 core tools from CRG.

中文简介正在准备中。当前显示原文说明。

CVE triage workflow for vulnerability analysis, reproduction assessment, and patch verification

中文简介正在准备中。当前显示原文说明。

dbt best practices for SQL modeling, testing, and analytics engineering workflows

中文简介正在准备中。当前显示原文说明。

Research-validated planning — research → plan → verify cycle for high-confidence implementation plans

中文简介正在准备中。当前显示原文说明。

Generate 4-6 parallel design mockups for rapid visual comparison — adapted from gstack /design-shotgun pattern

中文简介正在准备中。当前显示原文说明。

Refactor code for better structure and patterns

中文简介正在准备中。当前显示原文说明。

Review code against language-specific best practices

中文简介正在准备中。当前显示原文说明。

Parameterized evaluator-optimizer loop for quality-critical output with configurable rubrics

中文简介正在准备中。当前显示原文说明。

FastAPI patterns for high-performance async APIs

中文简介正在准备中。当前显示原文说明。