openclaw-agent-management

Name: Openclaw Agent Management
Author: delorenj

// This skill codifies the standards and workflows for this machine's openclaw agent gateway configuration. Use this skill when provisioning new agents or managing existing ones. Trigger phrases are "add a new agent", "update [agent's name] identity"

Exécuter dans Manus

$ git log --oneline --stat

stars:9

forks:1

updated:30 mars 2026 à 17:03

Explorateur de fichiers

2 fichiers

SKILL.md

readonly

name	openclaw-agent-management
description	This skill codifies the standards and workflows for this machine's openclaw agent gateway configuration. Use this skill when provisioning new agents or managing existing ones. Trigger phrases are "add a new agent", "update [agent's name] identity"

openclaw-agent-management

This skill helps define standards for the agents that live in this OpenClaw gateway instance.

![!IMPORTANT] MANDATORY RULE ONLY READ THE MINIMUM REQUIRED OF THIS SKILL IN ORDER TO SATISFY THE CURRENT TASK

Main Router

Are you here to:

Provision a new agent? see Provisioning

Agents

Each agent is a one-to-one mapping with an existing Triumph team member. i.e. Gershon Herczeg (team lead) --> GershonBot (main agent)
An agent is one of two possible roles:
1. Manager: Can delegate to other agents. Does not modify code
2. Developer: Implements tickets and requests from managers by modifying code or spawning ephemeral subagents. Cannot delegate tasks to other team members/agents

related-skills.json

même dépôt

33god.md

from "delorenj/skills"

Unified 33GOD master skill and router. Use for any 33GOD request: architecture context, project creation, task execution, coding workflow, service development, workflow generation, and platform-level orchestration. This skill routes to focused references/workflows/scripts for incremental discovery.

2026-03-309

ecosystem-patterns.md

from "delorenj/skills"

Use this when creating new projects, generating documentation, cleaning/organizing a repo, suggesting architecture, deploying containers and services, naming files/folders, or when the user references 'ecosystem', 'patterns', or 'containers'. This skill outlines naming conventions, stack preferences, project organization (iMi worktrees), Docker patterns, and PRD structures from past conversations.

2026-03-309

mise-tasks.md

from "delorenj/skills"

Orchestrate multi-step project workflows using mise task definitions with dependency management and argument handling. Use whenever the user wants to create, edit, or debug mise tasks, wire up task dependencies with depends/depends_post, or run workflows via 'mise run'. Also use when setting up task runners or automating build pipelines through mise. Do NOT use for mise environment variable configuration (use mise-configuration instead) or for general shell scripting unrelated to mise.

2026-03-309

obsidian-vault-management.md

from "delorenj/skills"

Codifies the standards and conventions for the creation, organization, categorization, and aggregation of data in the DeLoDocs obsidian vault. Use this skill when asked to add something 'to my vault' or 'in my vault', when creating any reports, instructions, updates, or any markdown documents that are intended to be viewed, and are NOT part of a project or repository.

2026-03-309

bub-email-triage.md

from "delorenj/skills"

Bub's canonical workflow for inbox/calendar triage escalation filtering (known contacts, money/security risk, high-signal AI changes).

2026-03-259

context-self-heal.md

from "delorenj/skills"

Agent-local context guard and deterministic compaction workflow (GOD-13). Use when context usage is high, when wiring auto-compaction/restart timers, or when deploying standardized context-monitor hooks across agents.

2026-03-259

package.json