Use this skill before any multi-file feature, architectural decision, or complex bug fix.

Land a PR by monitoring conflicts, resolving them, waiting for checks, and squash-merging when green; use when asked to land, merge, or shepherd a PR to completion.

Create and maintain agents/tasks/task-name/plan.md and tasks.md for Plan Mode plans.

**Category:** Engineering Team

Use when you need to research, analyze, and plan technical solutions that are scalable, secure, and maintainable.

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)

You are helping a candidate solve coding interview questions for **Hamming AI**, a YC S24 startup that automates QA for AI voice agents. Follow these instructions precisely to produce code that matche

ONLY trigger on explicit /gc. Never auto-trigger on 'commit', 'push', or similar words.

>

Research-first workflow: 리서치 → 분석 → 실행/수정 → 검증 → 커밋 (상황에 맞게 PHASE 자동 조절)

version: 1

>

Git worktrees create isolated workspaces sharing the same repository, allowing work on multiple branches simultaneously without switching.

>

Capture an architectural decision record — document a decision that was made during work, why it was made, and its consequences. Use when a significant technical or process decision needs to be recorded for future agents and developers.

Helps with the judgment call: should I escalate this, and if so, to whom? The skill addresses the decision, not the documentation. Most CSMs either escalate too late (waiting until the situation is cr

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

Apply effective software quality consultancy practices. Use when consulting, advising clients, or establishing consultancy workflows.

DOCX 文档离线读写：提取/分析、OOXML 解包编辑回包、批注与修订（tracked changes/redlining）。适用于合同/制度/论文等需要保留格式与修订痕迹的场景（依赖安装可能需要网络）。

Manage Apple Reminders via remindctl CLI (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.

End-to-end ColPack colloidal packing simulation workflow. Use for setting up, planning, executing, and analyzing hard-particle NVT/NPT Monte Carlo simulations using HOOMD-blue. Triggers on requests like 'run a packing simulation', 'simulate colloidal particles', 'sweep volume fractions', 'compress hard spheres', 'set up an NVT/NPT simulation', or 'plan a parameter sweep for disks and capsules'.

azure-mgmt-fabric-py

Comprehensive market sizing methodologies for calculating Total Addressable Market (TAM), Serviceable Available Market (SAM), and Serviceable Obtainable Market (SOM) for startup opportunities.

Write and edit code following repo conventions with smallest complete changes

Create a durable HANDOFF.md for a repo or working directory that captures current context, decisions, touched files, current state, and the next task. Use when wrapping up work, pausing a thread, or preparing someone (or a future session) to continue.

CREADOR DE SKILLS PARA ANTIGRAVITY

Design optimal agent team compositions with sizing heuristics, preset configurations, and agent type selection. Use this skill when deciding team size, selecting agent types, or configuring team presets for multi-agent workflows.

Semantic Similarity Rating - elicit realistic Likert-scale responses from LLMs using textual elicitation and embedding similarity mapping. Use when you need survey-like responses, purchase intent ratings, relevance scores, or any Likert-scale measurement that should match human response distributions.

All changes for the release (dependency updates, bug fixes, etc.) should already be merged to `main`.

This skill provides voice interaction capabilities for AI assistants. This skill should be used when users mention voice mode, want to have voice conversations, speak with Claude, check voice service status, or manage voice services like Whisper and Kokoro.

context-save

The [Smart Capacity](contact-center-management-messaging-operations-smart-capacity-overview.html) feature enables brands to better manage their messaging operations by controlling the weight an active

**Status:** Pending

A hard-edged writing style contract for timeless, forceful English prose without modern AI tics.

Play a text-based game of rock–paper–scissors against the user and keep score.

Digital pets for AI agents. Register, claim your egg, and raise a pet by feeding it your daily moods.

Strategic planning with optional interview workflow

>

[:Outline:]

document-release

Add new capabilities or modify NanoGemClaw behavior. Use when user wants to add channels (Telegram, Slack, email input), change triggers, add integrations, modify the router, or make any other customizations. This is an interactive skill that asks questions to understand what the user wants.

When working on this codebase:

**Nom:** GererSCI

File: architecture/AGENTS.md

This directory contains operational automation. Changes here can affect deploys, CI, backups, Telegram flows, and GitOps checks.

> Deep research into persistent, cloud-hosted, proactive AI agents that autonomously manage tasks, delegate to sub-agents, and augment daily life.

Construction surplus materials marketplace with AI-powered matching and carbon accounting.

Ez a tároló egy átfogó, 21 leckéből álló tananyagot tartalmaz, amely a generatív mesterséges intelligencia alapjait és alkalmazásfejlesztését tanítja. A kurzus kezdőknek készült, és a legfontosabb fog

Grant coding agents like Claude Code, OpenCode, and Windsurf access to resources protected by Cloudflare Access using cloudflared or service tokens.

'Query official Microsoft documentation to find concepts, tutorials, and code examples across Azure, .NET, Agent Framework, Aspire, VS Code, GitHub, and more. Uses Microsoft Learn MCP as the default, with Context7 and Aspire MCP for content that lives outside learn.microsoft.com.'