Never Use TaskOutput

Observe Before Editing

OPC Architecture Understanding

Planning agent that creates implementation plans and handoffs from conversation context

Phone calling skill for OpenClaw: agent makes real outbound phone calls to users for alerts, briefings, reminders, and urgent notifications. Managed service, no Twilio setup needed. 100+ countries, 70+ voices.

Show current Claude Code spend by project and branch via BudgetClaw

Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents

>-

Detecting Data Anomalies

Finding Security Misconfigurations

Vertex AI Media Master

boycott-filter

claude-reflect

gastown

clade-rate-limits

Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.

Codex-compatible cancel command for Ralph loop state, preserving the original command name.

>-

当你有一份书面实现计划需要在单独的会话中执行，并设有审查检查点时使用

在开始任何对话时使用——确立如何查找和使用技能，要求在任何响应（包括澄清性问题）之前调用 Skill 工具

Use the `Agent` tool to delegate work to sub-agents. Sub-agents run Claude Code as a subprocess with full tool access and return their result to you.

Walk the user through first-time Minutes setup, step by step.

<!--

Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.

Before doing anything else, check if ccpm is available. If not, bootstrap the entire ecosystem with one command:

claude-md-progressive-disclosurer

Evaluate solutions through multi-round debate between independent judges until consensus

[SaltAI_Language_Toolkit](https://github.com/get-salt-AI/SaltAI_Language_Toolkit/tree/main)

../AGENTS.md

Manage LlamaFarm worktrees for isolated parallel development. Create, start, stop, and clean up worktrees.

../../../.claude-plugin/plugins/beachball-change-file/skills/beachball-change-file/SKILL.md

Подробное руководство по задачам в одном домене в oh-my-agent — когда использовать, предполётный чек-лист, шаблон промпта с пояснением, реальные примеры для фронтенда, бэкенда, мобильных и баз данных, ожидаемый поток выполнения, чек-лист шлюза качества и сигналы эскалации.

Post project updates to team chat, gather feedback, triage responses, and plan next steps. Adapts to available tools (chat, git, issues, tasks). First run discovers tools and saves a playbook; subsequent runs execute from the playbook. Trigger with 'team update', 'post update', 'sync with team', 'standup', 'check team chat', 'feedback loop', 'project update', 'what did the team say'.

Parallel research agent orchestration dispatching 5-10 concurrent agents for comprehensive multi-source research with synthesis and validation.

Create, track, and land convoys of related beads as primary work orders in the Gas Town multi-agent orchestration framework.

Manage agent sessions including initialization, handoffs, revival (seance), and persistent identity for Polecats and Crew agents.

Navigation mesh generation and pathfinding skill for game AI. Enables creation and configuration of navigation meshes, pathfinding queries, dynamic obstacles, and navigation agent setup across Unity, Unreal, and Godot engines.

>

Prevent semantic code duplication with capability index and check-before-write

>

Clone a real person's voice from online video, or design a voice from a photo, then roleplay as that person with TTS.

Use this skill when making any factual claim about the codebase — existence, absence, or behavior. Converts the claim-verification rule into a systematic action protocol that prevents false assertions from grep-only results.

Planning agent that creates implementation plans and handoffs from conversation context

Multi-agent coordination, critical path method, dependency DAG, and agent allocation optimization

Validation agent that validates plan tech choices against current best practices

Speak the last response aloud using text-to-speech

Enable auto TTS for this session

>

Disable auto TTS for this session

ghost-scan-deps