- 📁 references/
- 📄 evals.json
- 📄 README.md
- 📄 SKILL.md
Use this skill when working with the A2A (Agent-to-Agent) protocol - agent interoperability, multi-agent communication, agent discovery, agent cards, task lifecycle, streaming, and push notifications. Triggers on any A2A-related task including implementing A2A servers/clients, building agent cards, sending messages between agents, managing tasks, and configuring push notification webhooks.
This skill should be used when sending images, files, or notifications back to the user via messaging platforms (Discord, Feishu, Telegram, etc.) through cc-connect. TRIGGER when agent generates a plot/chart/screenshot and wants to show the user; agent creates a report/PDF/file the user should receive; agent needs to proactively notify the user (e.g. task completed, alert, reminder); user asks to "send image", "show me the chart", "notify me", "send the file", "send to Telegram", "show plot in Discord".
- 📁 references/
- 📄 schemas
- 📄 SKILL.md
Creates structured agent definitions using the 7-component format grounded in persona science (PRISM), vocabulary routing, and failure mode taxonomy (MAST). Produces agents with real-world job titles, expert domain vocabulary payloads (15-30 terms), explicit deliverables, decision boundaries, imperative SOPs, and named anti-pattern watchlists. Use this skill when the user wants to create an agent, define a role, build a persona, or needs a specialized AI assistant for a specific domain. Also triggers when Mission Planner delegates agent creation for team roles. Works for any domain — software, marketing, security, operations, design, writing, research, and more. Do NOT use for creating skills (use Skill Creator) or team composition (use Mission Planner). --- # Agent Creator Creates structured agent definitions following the 7-component format. Every agent produced by this skill is grounded in persona science research, vocabulary routing mechanics, and the MAST failure taxonomy. --- ## Expert Vocabulary Payload **Agent Design:** role identity, domain vocabulary payload, deliverables, decision authority, standard operating procedure, anti-pattern watchlist, interaction model, handoff artifact, quality gate **Organizational Structure:** RACI matrix, task-relevant maturity (Andy Grove), blast radius, reporting lines, escalation path, out-of-scope boundary **Security & Risk:** STRIDE threat model, OWASP Top 10, attack surface, threat modeling (Shostack) **Persona Science:** persona alignment, persona-accuracy tradeoff, PRISM framework, role-task alignment rule, flattery degradation, token budget **Vocabulary Mechanics:** vocabulary routing, embedding space, knowledge cluster, distribution center, 15-year practitioner test, sub-domain clustering, attribution amplification --- ## Anti-Pattern Watchlist ### Flattery Persona - **Detection:** Superlatives and absolutes in role identity — "world-class," "best," "always," "never," "unparalleled," "leading expert." - **Why it fa
- 📄 __init__.py
- 📄 manifest.json
- 📄 SKILL.md
Cognithor - Agent OS: Local-first autonomous agent operating system. 16 LLM providers, 17 channels, 112+ MCP tools, 5-tier memory, A2A protocol, knowledge vault, voice, browser automation, Computer-use, self-healing, self-improving. Python 3.12+, Apache 2.0.
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.
Expert at selecting and configuring AgenticFORGE agents. Generates correct FunctionCallAgent, ReActAgent, PlanSolveAgent, ReflectionAgent, SimpleAgent, SkillAgent, and WorkflowAgent code with proper configuration. Use when the user wants to build an agent, choose between agent types, configure agent options, or understand agent behavior.
Creates structured Taskplane task packets (PROMPT.md, STATUS.md) for autonomous agent execution via the task-orchestrator extension (/orch). Use when asked to "create a task", "create a taskplane task", "stage a task", "prepare a task for execution", "write a PROMPT.md", "set up work for the agent", "queue a task", or whenever the user wants to define work that will be executed autonomously by another agent instance.
Delegate coding tasks to Blackbox AI CLI agent. Multi-model agent with built-in judge that runs tasks through multiple LLMs and picks the best result. Requires the blackbox CLI and a Blackbox AI API key.
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.
- 📁 references/
- 📁 scripts/
- 📄 SKILL.md
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code, Cursor, or similar agent internals (5) want to build agents for business, research, creative, or operational tasks
End-to-end workflow to create a coded Business Central agent using the Agent SDK. Follows the official Agent Template project structure. Generates all required objects with correct interface signatures. Use when creating a new BC agent.
End-to-end workflow to create a coded Business Central agent using the Agent SDK. Follows the official Agent Template project structure. Generates all required objects with correct interface signatures. Use when creating a new BC agent.
