OliverOuyang
47 verified skills
sql-validate-and-export
SQL 分段验证、自我修复、结果导出与智能分析。流程：解析SQL → Dataphin MCP 验证元数据 → 自动修复 → 分段执行验证 → 导出 CSV → 智能分析（漏斗解读、异常识别、预判用户问题）。适用场景："跑一下这个SQL"、"验证这个查询"、"帮我执行并导出"、"分析一下结果"等。
tools
ai-slop-cleaner
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
development
ask
Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly
tools
autopilot
Full autonomous execution from idea to working code
development
cancel
Cancel any active OMC mode (autopilot, ralph, ultrawork, ultraqa, swarm, ultrapilot, pipeline, team)
development
ccg
Claude-Codex-Gemini tri-model orchestration via /ask codex + /ask gemini, then Claude synthesizes results
development
configure-notifications
Configure notification integrations (Telegram, Discord, Slack) via natural language
business
deep-dive
2-stage pipeline: trace (causal investigation) -> deep-interview (requirements crystallization) with 3-point injection
devops
deep-interview
Socratic deep interview with mathematical ambiguity gating before autonomous execution
tools
external-context
Invoke parallel document-specialist agents for external web searches and documentation lookup
development
skills/guanyuan-monitor
> 🚧 **IN DEVELOPMENT - 功能未完整实现** > > 本 skill 当前处于**原型阶段**，核心功能尚未实现（所有主要方法为 TODO stubs）。 > > **已实现**: 项目结构、配置模板、日志框架 > **未实现**: MonitorConfig 加载、AlertRule 逻辑、DataFetcher MCP 集成、DingTalkNotifier、SchedulerManager > > **预计完成时间**: 待定 # guanyuan-monitor 观远数据监控技能 - 基于观远数据API和钉钉通知的自动化监控 ## Version 1.0.0 ## Description 自动化数据监控系统,支持: - 从观远数据平台获取指标数据 - 基于规则的告警判断(阈值、环比、同比) - 钉钉消息推送 - 定时任务调度 ## Dependencies ### MCP Tools - `sh_guanyuan_data` - 观远数据查询 - `sh_messagengine_dingtalk` - 钉钉消息发送 ### Python
tools
hud
Configure HUD display options (layout, presets, display elements)
tools
learner
Extract a learned skill from the current conversation
tools
mcp-setup
Configure popular MCP servers for enhanced agent capabilities
tools
omc-reference
OMC agent catalog, available tools, team pipeline routing, commit protocol, and skills registry. Auto-loads when delegating to agents, using OMC tools, orchestrating teams, making commits, or invoking skills.
tools
omc-setup
Install or refresh oh-my-claudecode for plugin, npm, and local-dev setups from the canonical setup flow
tools
omc-teams
CLI-team runtime for claude, codex, or gemini workers in tmux panes when you need process-based parallel execution
tools
omc-plan
Strategic planning with optional interview workflow
tools
project-session-manager
Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions
development
ralph
Self-referential loop until task completion with configurable verification reviewer
tools
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution
tools
release
Automated release workflow for oh-my-claudecode
development
skills/rta-exclude-strategy
# rta-exclude-strategy RTA排除策略分析技能 - 基于V8和V9RN双模型交叉分析的智能排除策略生成 ## Version 1.1.0 ## Description 自动化RTA（Real-Time Advertising）排除策略分析系统，支持： - 基于V8和V9RN模型的二维交叉分析 - 智能置入置出算法自动生成排除区域 - 新老策略全面对比评估 - 生成企业规范Excel分析报告 - 安全过件率阈值约束和交易占比约束 ## Dependencies ### Python Packages - pandas>=1.3.0 - numpy>=1.20.0 - openpyxl>=3.0.0 ### Installation ```bash pip install -r scripts/requirements.txt ``` ## Usage ```bash /rta-exclude-strategy --data_path <path> --ctrl_group_value <value> [options] ``` ## Param
development
sciomc
Orchestrate parallel scientist agents for comprehensive analysis with AUTO mode
testing
setup
Use first for install/update routing — sends setup, doctor, or MCP requests to the correct OMC setup flow
tools
skill-governance
Skills 库治理规范 - 新增、更新、删除 skill 的强制性守门流程。当 CC session 操作 skills/ 目录时自动触发。
development
skill
Manage local skills - list, add, remove, search, edit, setup wizard
tools
trace
Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode
testing
ultraqa
QA cycling workflow - test, verify, fix, repeat until goal met
tools
ultrawork
Parallel execution engine for high-throughput task completion
tools
visual-verdict
Structured visual QA verdict for screenshot-to-reference comparisons
testing
writer-memory
Agentic memory system for writers - track characters, relationships, scenes, and themes
documentation
self-improving-agent
A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.
development
skills/guanyuan-data-fetcher
# Guanyuan Data Fetcher 通用观远数据看板抓取工具，支持任意看板和卡片配置，输出CSV或Excel格式。 ## 功能描述 从观远数据平台的任意看板抓取卡片数据。支持: - **JSON配置文件驱动**: 通过配置文件定义看板、卡片、筛选模板 - **CLI参数覆盖**: 运行时覆盖日期范围、输出目录、看板ID等 - **多输出格式**: CSV (每卡片一个文件) 或 Excel (多Sheet单文件) - **向后兼容**: 无参数调用时使用内置默认配置 (1.2 核心指标看板, 5个卡片) ### 默认配置 (内置) 当不指定 `--config` 时，默认抓取看板 `1.2 核心指标` 的以下5个卡片: 1. **首借交易额_重主营_by 6大客群** (默认tab, Template A) 2. **首借交易金额** (规模tab, Template B) 3. **过件率-排年龄_分渠道** (质量tab, Template B) 4. **1-3过件率-排年龄_分渠道** (质量tab, Template B) 5. **申完成本_排年龄
tools
notebook-standardizer
Standardize Jupyter notebooks (.ipynb) for interactive data analysis workflows. Enforces a mandatory cell manifest (M1-M8 + archetype chapters) with tags ([CONFIG]/[SETUP]/[FUNC]/[RUN]/[VIZ]/[EXPORT]), structured markdown sections, and output prefixes ([OK]/[WARN]/[SKIP]). Use when the user wants to standardize, clean up, or create a notebook from scratch. Two archetypes: problem-driven (question-answer analysis) and monitoring (dimension-based periodic reporting).
data-ai
claude-dir-governance
.claude 目录配置治理和性能优化规范
development
skill-auto-evolver
Skills 自动进化器 - 数据驱动的性能分析和自动优化
tools
html-report-framework
HTML 报告生成通用框架 - CSS 变量设计系统、专业组件库、ECharts 图表、Mermaid 流程图、动态居中布局、可折叠侧栏、规则驱动结论。当用户需要生成 HTML 报告、数据看板、SOP 文档、KPI dashboard 或任何自包含网页报告时使用。
development
monthly-report-html-generator
从数据源自动生成月度运营数据 HTML 报告，支持 ECharts 图表、规则驱动结论、可折叠侧栏导航
development
notebook-executor
Execute Jupyter notebooks end-to-end with SQL pre-validation, error diagnosis, and auto-fix loops. Use when "run notebook", "execute notebook", "test notebook", or "validate notebook execution".
testing
skill-vetter
Security-first vetting for OpenClaw skills. Use before installing any skill from ClawHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
testing
sql-optimizer
Optimize and clean SQL queries with structured comments, format improvements, and syntax validation. Use this skill whenever users mention "optimize SQL", "clean SQL", "add comments to SQL", "format SQL", "refactor SQL", or want to improve SQL readability. Specifically designed for Hive/MaxCompute SQL with support for variables like ${bizdate}, partitioning, and window functions.
development
skills/sql-runner
> ⚠️ **PROTOTYPE - 开发中 / DO NOT USE IN PRODUCTION** > > 当前 `run_sql.py` 中的 MCP 集成为 **mock 实现**，不会真正调用 Dataphin API。 > 实际使用时，Claude Code 会直接通过 MCP 协议调用 `sh_dp_mcp` 工具，无需运行此脚本。 > > **正确用法**：直接在 Claude Code 对话中要求执行 SQL，Claude 会调用 MCP 工具。 --- name: sql-runner description: Execute optimized SQL files using Dataphin MCP tools. Automatically submits queries, polls for results, and saves output to CSV with timestamped filenames. Use this skill when users mention "run SQL", "execute query", "submit to D
tools
deepinit
Deep codebase initialization with hierarchical AGENTS.md documentation
development
omc-doctor
Diagnose and fix oh-my-claudecode installation issues
development
skill-lifecycle-manager
Skills 生命周期管理器 - 版本管理、依赖检查、使用统计和健康报告
tools
team
N coordinated agents on shared task list using Claude Code native teams
development