You are helping create a **Cursor Agent Skill** for this repository (or the user’s personal skills if they say so).
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →You are helping create a **Cursor Agent Skill** for this repository (or the user’s personal skills if they say so).
Technical project management for coordinated Backlog.md delivery in this repo. Use only when the user explicitly asks Codex to coordinate one or more existing Backlog tasks, manage dependencies, or delegate implementation across multiple agents or worktrees.
**Category:** Engineering Team
Use when the user wants to analyze competitors or research the competitive landscape. Produces battle cards, pricing landscape, feature matrix, and strategic recommendations. Triggers: who are my competitors, competitive analysis, battle cards, market positioning. Works standalone; uses /fh:startup-design output if available. Does NOT handle code planning or development. (Codex adapter)
Implement — Use when the user asks to create a demo video, product walkthrough, feature showcase, animated presentation, marketing video, or GIF from screenshots or scene descriptions. Orchest
You are running the **factor-based trading loop** — a systematic, quantitative approach to stock selection and trading. Factor scoring is deterministic Python; your role is orchestration, earnings int
Aggregates all check results into a final scored readiness report
**Purpose:** Check if an existing skill follows the canonical structure with proper TitleCase naming.
This directory contains operational automation. Changes here can affect deploys, CI, backups, Telegram flows, and GitOps checks.
- **Skill ID:** M-059
Workspace: `business-os/operations/`
This file coordinates multi-agent swarm mode for ProjectStats.
workflow-team
CLI command patterns for the autopilot CLI using Command, CLI, and argparse. Use when adding commands, subcommands, or modifying global flags.
Create isolated git worktree for parallel development in monorepos.
Roll back a bad release to the previous known-good version (Marcus workflow)
Deploy a service or static site publicly via CasaOS + VPS reverse proxy. Covers DNS, SSL, nginx config, Docker containers, and static files.
Execute development work from a pool of GitHub issues. Take one at a time, implement via act-dev, close the issue when done. Use when architect/PM has produced a backlog of issues to implement in parallel.
Добавить встроенную справку к объекту 1С (обработка, отчёт, справочник, документ и др.)
BrewMind × Cici: route business facts through evidence → prepared context → proposals → governed state (owner-approved). Triggers: brewmind steward, governed state steward, BrewMind gate, Cici proposal, promote BrewMind fact.
Follow the instructions in ./workflow.md.
autosort ledger.jsonl의 무결성/정책 위반을 감사(audit)한다. before/after, decision, confidence, reason, timestamp, run_id 필드 누락/위반 탐지에 사용.
Re-ask the voice and beneficiary questions and update .bodega.md. Useful when the user's preference changes or the store is being handed off to someone new.
>-
Full autonomous engineering workflow
Issue tracking with Beads (bd CLI). Use when commands need to create, query, update, or close issues, or manage dependencies.
Sync workflows for Workbench CLI. Use when aligning local work items with GitHub issues, creating branches, or reconciling doc backlinks.
'[DEPRECATED] Use /ce:compound instead — renamed for clarity.'
Business logic, order lifecycle, workflow states, quality gates, and pricing rules. Use when implementing order features or understanding business workflows.
'Stage, commit, and push changes with conventional branch prefixes and safety checks. Use when the user asks to commit, push, save, or publish local changes to GitHub, or wants a standard commit workflow in this project.'
Gather phase context through adaptive questioning before planning. Use --auto to skip interactive questions (the agent picks recommended defaults).
Full autonomous engineering workflow using swarm mode for parallel execution
Orchestrate the release team: coordinates release-manager, qa-lead, devops-engineer, and producer to execute a release from candidate to deployment.
Announce: "I'm using the /do skill to orchestrate feature development with lifecycle tracking."
Use when the user wants Compass BMAD automation wrappers, Beads-aware orchestration, approval gates, or resume/retry behavior instead of a single manual workflow.
Use this skill for mission/sector/upgrade balancing and authored data changes.
在发版前执行发布门禁检查，并输出“可发布/带条件可发布/不可发布”结论与阻断项。适用于部署前、打 tag 前、发布分支合并前。
Workspace-first GrepAI search workflow for programming agents (v0.34+): project-scoped semantic search, token-efficient output, and reliable fallbacks.
name: smoke
Write and maintain self-contained ExecPlans (execution plans) that a novice can follow end-to-end; use when planning or implementing non-trivial repo changes.
Manage your Simplenote notes conversationally.
Use the Hello World skill to respond to the user when they enter the phrase "hello world".
Index and search code repositories, documentation, research papers, HuggingFace datasets, local folders, Slack workspaces, Google Drive, and packages with Nia AI. Includes auth bootstrapping, Oracle autonomous research, GitHub live search, dependency analysis, context sharing, and code advisor.
Realizar un análisis técnico y funcional profundo de un requerimiento, repositorio, módulo, script o conjunto de cambios para entender su propósito, flujo, dependencias, riesgos, deuda técnica y oport
Research a topic across gopher-cli sources, read relevant documents, and save a structured summary to the vault
Close the loop on a completed plan by writing SUMMARY.md and updating state
Citation verifier — checks that in-text citations accurately represent what the cited source actually says
Release a new version. Bumps version in Cargo.toml and flake.nix, commits, tags, publishes to crates.io, and pushes. Usage: /release 0.2.2
Weekly experiment tracking loop for MD Home Care. Scans content changes, measures traffic impact via PostHog and GSC, and makes keep/iterate/revert decisions with lag-adjusted attribution.
>