sg
Metacognitive oversight. "$sg review" for on-demand evaluation, "$sg init" to set up, "$sg audit" to review decisions.
Discover Tools skills, compare source repositories and read the instructions for each workflow.
Metacognitive oversight. "$sg review" for on-demand evaluation, "$sg init" to set up, "$sg audit" to review decisions.
Work a GitHub issue to completion in a branch, including review follow-ups, then PR for human review
Open Horizon Labs orchestration. "$bottle init" for setup, "$bottle dive" to start sessions, "$bottle web-context" for fresh docs.
Working memory. "$wm dive" to prep sessions, "$wm compile" for context, "$wm distill" to extract learnings.
Task tracking. "$ba status" for current tasks, "$ba claim " to start work, "$ba finish " when done.
Uber Go style guide rules for guidelines, performance, and code style. Use when writing or reviewing Go code for style compliance.
Goroutine ownership, errgroup patterns, worker pools, and graceful shutdown. Use when writing concurrent code or parallel request handling.
Clean/hexagonal architecture rules, folder structure, interface ownership, and dependency direction. Use when creating new packages, services, or understanding codebase structure.
Testing patterns including table-driven tests, mock setup, and coverage requirements. Use when writing tests or setting up test infrastructure.
Project patterns including functional options, must pattern, caching decorator, error handling, configuration, and HTTP clients. Use when implementing common patterns in the codebase.
Tracing with OpenTelemetry and structured logging with slog. Use when adding observability to services, handlers, or debugging production issues.
Autonomous homelab operations using OODA loop (Observe, Orient, Decide, Act) - use when reviewing system state, planning autonomous actions, or investigating operational issues
Automated service deployment with validation, templating, and verification - use when deploying new services, updating existing deployments, or troubleshooting deployment issues
Coordinate with other AI agents running in tmux panes. Use this skill when you need to delegate tasks, request reviews, or collaborate with agents like Codex, Gemini, or other Claude instances.
Communicate with other AI agents in tmux panes. Use when you need to talk to codex, claude, gemini, or other agents.
SOP for creating new Claude Code skills. Use when adding a new skill to any project or globally.
Orchestration overview for the autonomous bug fixing system. References the component skills (dispatcher, handler) and per-project skills (bug-intake, qa-submission).
Google Drive CLI access via rclone. Use when needing to read, write, list, or manage files on Google Drive without browser automation. Prefer this over browser for Drive operations.
Google Sheets browser automation pitfalls and PA-specific additions. Use when automating Sheets via browser.
Send Slack messages via API (channels, DMs, notifications). Use when needing to post to Slack channels or send DMs programmatically.
基于 cleanddd-requirements-analysis 结果输出 CleanDDD 建模蓝图,并在 only-danmuku 的 iterate/feature 目录交付 *_gen.json 建模元素与 *_update.sql DDL 变更脚本;用于将已拆解需求落为可生成代码的模型与数据库变更清...
需求澄清与拆解,识别干系人并将需求条目标注所属对象与业务实体;仅产出结构化需求描述,不做建模定义,可作为后续建模输入
在 only-danmuku 的 CleanDDD Kotlin 项目中编写或修改聚合/命令/查询/API 端点/事件/防腐层 Client/仓储/配置/测试时使用;遵循 代码实现规约.md 与 design/_gen + genDesign 的生成流程。
High-performance CLI for working with SQL dump files: split/merge by table, analyze contents, validate integrity, convert between MySQL/PostgreSQL/SQLite/MSSQL, create FK-safe samples, shard multi-tenant dumps,...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.