>

- Ensure the PR is conflict-free with main.

1. Verify git status is clean or commit/stash changes before merging.

Triage recent Slack activity into a priority queue or task list for the user.

Draft Slack replies from available context. Use when the user wants help finding messages that likely need a response and preparing reply drafts.

Draft Microsoft Teams replies from available context. Use when the user wants help finding messages that likely need a response and preparing reply drafts.

Summarize activity from one Microsoft Teams channel or one scoped Teams conversation and return a concise recap or post-ready follow-up.

Handle Outlook Calendar workflows, including delegated/shared calendar writes. Use when the user asks for schedule understanding, availability checks, meeting scheduling, intelligent rescheduling, meeting prep, reminder updates, RSVP responses, recurring maintenance, travel coordination, deadline planning, or safe create, update, reschedule, respond, attach, delete, or cancel changes with timezone-aware event times and attendee validation.

website-to-hyperframes

Submit compact Genebass gene burden requests for one Ensembl gene ID and one burden set. Use when a user wants concise Genebass PheWAS summaries

Summarize activity from one Slack channel and return a concise recap, post-ready update, or summary doc.

Use this skill when the target is a local skill directory or `SKILL.md` file.

kOps is a command-line tool for creating, destroying, upgrading, and maintaining production-grade, highly available Kubernetes clusters. It is written in Go and supports multiple cloud providers, incl

**IMPORTANT**: This project uses **trx** for ALL issue tracking. Do NOT use markdown TODOs, task lists, or other tracking methods.

An AI agent is a system that uses a language model as its reasoning engine to decide what actions to take, execute those actions, observe the results, and iterate until a task is complete. While a sta

Before doing any work on the user's behalf, you MUST follow this workflow:

Bug fix designer — diagnoses root causes and writes fix plans for workers to execute

>These rules define how the agent should communicate, act, and collaborate with the user during development and automation tasks.The objective is to maintain clarity, reliability, and discipline while

<!-- gitnexus:start -->

**Research Date**: 2026-01-21

**Note**: This project uses [bd (beads)](https://github.com/steveyegge/beads) for issue tracking. Use `bd` commands instead of markdown TODOs. See the **Issue Tracking with bd (beads)** section below

[Engineering at Anthropic](/engineering)

Delegate code tasks and analysis to Codex CLI agents

To create or edit subagents, use the **agent-kit:claude-agent-development** skill.

**Purpose**: Coordinate multiple agents running in parallel to maximize efficiency and avoid conflicts.

Documentation for GreenLang AI Agent Workforce Deployment

Demo the SubagentStop hook by spawning 3 agents and viewing the activity log

Agents support the "small steps, verify often" principle from `.claude/docs/APPROACH.md`.

> Claude Code: read this at the start of every session alongside CLAUDE.md.

**Search Demand:** VERY HIGH (launched yesterday, April 8, 2026)

> Every logical service in EOM is described here: its responsibility boundary,

> Last synced: 2026-04-21

**Objetivo Primordial:** Este documento y **todos los demás archivos `.md` que contienen reglas, directrices o conocimientos operativos** deben ser actualizados proactivamente por el Agente de IA. La

- Funciones propósito único, preferiblemente <20 líneas

Use small, explicit roles. Do not delegate understanding or product truth.

Этот файл описывает, **как мы используем AI внутри проекта**. Он превращает

Agentic Workflow — persistent AI development workflows with quality gates when you need them.

No two agents may edit the same file concurrently. Ownership during a workflow:

This document defines agent roles, responsibilities, and safe collaboration rules.

Localizados em `~/COMBINED/workspace-config/claude/agents/`:

**Responsibilities:**

The following agents ship with this harness (under `~/.claude/agents/` for global install, `./.claude/agents/` for project install). Do not reference agents that are not in this list.

**Launches multiple parallel agents for grunt work - same task, different inputs.**

The fundamental challenge in any complex problem is combinatorial explosion. The Hubble Space Telescope scheduling problem involves tens of thousands of observation requests, six scientific instrument

> **Contract alignment**: These docs align to ntask CLI Contract v1.0.0.

Voice agents turn the same agent concepts into spoken, low-latency interactions. The key design choice is deciding whether the model should work directly with live audio or whether your application sh

Use these agent definitions when the request is large, parallelizable, or needs tighter role separation.

Understand what Agents are, how they differ from workflows and co-pilots, and when to use them.

<!-- AGENT_INSTRUCTION_START -->

Reconciles data sources using stable identifiers (Pay Number, driving licence, driver card, and driver qualification card numbers), producing exception reports and “no silent failure” checks. Use when you need weekly matching with explicit reasons for non-joins and mismatches.