- 📁 assets/
- 📁 references/
- 📄 SKILL.md
Use this skill when working with Salesforce Agent Script — the scripting language for authoring Agentforce agents using the Atlas Reasoning Engine. Triggers include: creating, modifying, or comprehending Agent Script agents; working with AiAuthoringBundle files or .agent files; designing topic graphs or flow control; producing or updating an Agent Spec; validating Agent Script or diagnosing compilation errors; previewing agents or debugging behavioral issues; deploying, publishing, activating, or deactivating agents; deleting or renaming agents; authoring AiEvaluationDefinition test specs or running agent tests. This skill teaches Agent Script from scratch — AI models have zero prior training data on this language. Do NOT use for Apex development, Flow building, Prompt Template authoring, Experience Cloud configuration, or general Salesforce CLI tasks unrelated to Agent Script.
- 📁 agents/
- 📁 casting/
- 📁 identity/
- 📄 casting-history.json
- 📄 casting-policy.json
- 📄 casting-registry.json
{what this skill teaches agents}
- 📁 skills/
- 📁 workflows/
- 📄 casting-history.json
- 📄 casting-policy.json
- 📄 casting-registry.json
{what this skill teaches agents}
Comprehensive guide for developing Letta agents, including architecture selection, memory design, model selection, and tool configuration. Use when building or troubleshooting Letta agents.
- 📁 src/
- 📄 AGENTS.md
- 📄 package-lock.json
- 📄 package.json
Communicate with remote agents via A2A protocol, discover available agents, and ask the human owner for clarification via the A2A Hub. Use when asked to send messages to other agents, discover what agents are available, or when you need human input to proceed. **Triggers — use this skill when:** - You need human input to proceed (approval, decision, clarification) - User asks to "send a message to another agent" - User asks to "discover agents" or "what agents are available" - You're stuck and need to escalate to the owner - A long-running task needs human approval before continuing --- # A2A — Agent-to-Agent Communication & Human-in-the-Loop ## Tools | Tool | Purpose | |------|---------| | `a2a_discover` | Find remote agents on the hub or static registry | | `a2a_send` | Send a message to a remote agent by name, ID, or URL | | `ask_owner` | Ask the human owner a question (non-blocking) | --- ## ask_owner — Human-in-the-Loop Use `ask_owner` when you **genuinely cannot proceed** without human input. The tool submits your question to the hub and **returns immediately** — it does NOT block your session. When the owner responds, a **fresh pi subprocess** is automatically spawned with your handoff context + the owner's answer to continue the work. ### How It Works 1. You call `ask_owner` with a question + handoff context 2. The question is submitted to the A2A Hub — you get an immediate confirmation 3. You continue with other work or end your session 4. The owner answers through the hub's web UI (could be minutes or hours later) 5. A background poller detects the response 6. A fresh `pi` subprocess is spawned with a self-contained prompt containing: - The original question - The owner's response - Your full handoff context (done, remaining, decisions, etc.) 7. The new session picks up where you left off — no prior conversation context needed ### When to Use - **Approval needed** — destructive operations, merging PRs, deploying - **Ambiguous requirements** — multiple vali
Manage Bernstein agents — list active agents, inspect their output, kill stalled agents, or stream live logs. Use when the user asks about agents, wants to see what an agent is doing, or needs to kill one. --- # Bernstein Agent Management Inspect, monitor, and control active Bernstein agents. ## When to Use - User asks "what agents are running?" or "show me the agents" - User wants to see what a specific agent is working on - User says "kill that agent" or "stop the backend agent" - User asks "why is that agent stuck?" or wants to inspect agent output - User wants to see agent logs ## Instructions ### List agents 1. Run `scripts/agents.sh list` to get all active agents. 2. Present them clearly: ``` ## Active Agents (3) | Agent | Role | Model | Status | Task | Runtime | Cost | |-------|------|-------|--------|------|---------|------| | ses-a1b2 | backend | claude-sonnet-4 | alive | TASK-042: Fix auth | 4m 12s | $0.32 | | ses-c3d4 | qa | gpt-4.1 | alive | TASK-043: Write tests | 2m 45s | $0.18 | | ses-e5f6 | frontend | claude-sonnet-4 | stalled | TASK-044: Update UI | 8m 03s | $0.51 | ``` ### Inspect agent 3. To see what an agent is doing: `scripts/agents.sh logs <session_id>` 4. Show the last ~20 lines of output. ### Kill agent 5. To kill a stalled or misbehaving agent: `scripts/agents.sh kill <session_id>` 6. Confirm: "Agent ses-e5f6 terminated. Task TASK-044 returned to open queue." ### Stall detection 7. If any agent shows `stalled` status, proactively suggest killing it. 8. An agent is stalled if it hasn't sent a heartbeat in >60 seconds.
Author, edit, review, or refactor meridian agent profiles — the markdown files with YAML frontmatter that live in an `agents/` directory and define reusable spawn configurations (model, system prompt, tools, permissions, skills). Load this skill whenever you're writing an agent from scratch, tweaking an existing profile, splitting one agent into several, reviewing an agent for quality, or deciding whether something should be an agent at all. Phrases that should trigger this skill: "write an agent", "create a profile", "edit this agent", "add a reviewer agent", "refactor the coder agent", "this agent's prompt needs work", "add tools to this profile", "tighten up this agent's description". --- # agent-creator A guide for writing meridian agent profiles that are reusable, caller-agnostic, and age well as models and workflows evolve. Load this skill before touching any file under a `meridian-base/`, `meridian-dev-workflow/`, or similar source submodule's `agents/` directory. ## Hard rule: edit source, never `.agents/` `.agents/` is generated output from `meridian mars sync`. Anything you edit there is overwritten the next time someone runs sync, so the edit is invisible to everyone else and disappears on the next pull. Edit the source submodule instead — `meridian-base/agents/<name>.md`, `meridian-dev-workflow/agents/<name>.md`, or whichever repo owns the profile.
Multi-dimensional analysis via CSV wave pipeline. Diamond topology — CLI exploration agents (Wave 1), 6-dimension scoring agents (Wave 2), decision synthesis agent (Wave 3). Supports dual depth with -q quick mode. Replaces maestro-analyze command.
Guides architectural decisions for Deep Agents applications. Use when deciding between Deep Agents vs alternatives, choosing backend strategies, designing subagent systems, or selecting middleware approaches.
Building LLM agents with mlld — tool agents (MCP tools), event-driven agents (routers and dispatchers), and workflow agents (stateless jobs). Use when creating agents, exposing tools, or building event-driven systems.
- 📁 .codex/
- 📁 docs/
- 📁 providers/
- 📄 SKILL.md
Employee agent lifecycle management system. Use when working with agents/ directory employee agents - starting, stopping, monitoring, or assigning tasks to Dev/QA agents running in tmux sessions. Completely independent of CAO, uses only tmux + Python.
- 📁 cmd/
- 📁 docker/
- 📁 docs/
- 📄 .gitignore
- 📄 CHANGELOG.md
- 📄 go.mod
Manage AI agent teams with agencycli — a CLI tool for organising AI agents (Claude Code, Codex, Gemini, Cursor, etc.) into hierarchical teams (Agency → Team → Role → Project → Agent). Key capabilities: create agencies and teams, hire agents with merged context layers, assign and run tasks with priority queues, manage autonomous playbooks (wakeup.md), send async inbox messages between human and agents, configure heartbeat schedules and cron jobs, run agents inside Docker sandboxes, forward/confirm tasks via inbox, manage templates, and more. Use this skill whenever you need to: create or manage an agencycli workspace, hire/fire/sync agents, add/run/cancel tasks, check inbox confirmations, send messages, configure heartbeats or crons, start the scheduler, or work with agency templates.
