Claude Skills by agentprojectcontext

ALWAYS activate when the project has a .apc/ directory or AGENTS.md file. Do not wait to be asked. Read .apc/ before making any assumption about agents, memory, or project structure. Activate on: .apc/, AGENTS.md, 'which agents', 'list agents', 'agent context', 'who are the agents', any question about agents or memory in this project. IMPORTANT: if .apc/migrate.md exists, open the conversation with a migration offer before answering anything else. If the user declines, delete .apc/migrate.md ...

Registers, lists, runs, debugs, and scopes MCP servers in APX — the MCP entry point for agents (shared/runtime/global scopes). In an .apc project, prefer APX-managed MCPs over a built-in client. Triggers: 'add MCP', 'apx mcp', 'list MCPs', 'run an MCP tool', 'MCP failing'.

Orchestrates agents, sessions, routines, and channels through the APX CLI and local daemon — run the super-agent locally or delegate a task to another coding CLI (Claude Code, Codex, OpenCode, Aider, Cursor, Gemini, Qwen). Triggers: 'apx', 'apx exec', 'apx run', 'apx daemon', 'apx routine', 'delegate to a runtime'.

Reusable agent templates from the vault — "una plantilla de agente", "agentes reutilizables", dev, marketing, ops, qa and support archetypes. Spawn a specialist, list, import into a project, create, or hide/restore a bundled default. Triggers: 'spawn agent', 'use Cody/Rocky/Tessa', 'list agents', 'agent vault', 'import agent', 'new agent'.

Create, configure, use project agents in APX — including writing an agent's SYSTEM PROMPT (the body of its definition file, required for the agent to do anything) and its identity (typology, area, role, avatar blob). Load when user wants to add an agent, write or change an agent's prompt/instructions/persona, set an agent's type/area/role/avatar, import from vault, set a per-agent model, or write agent memory. Triggers: 'add agent', 'new agent', 'create agent', 'agent prompt', 'agent instruct...

Install the APX Android app on the owner's phone over USB — "instalá la app en mi celular", "install the app on my phone", "pasame APX al teléfono", "apx android install", the APK, the download link, pairing a phone by cable. Load when asked to put APX on a phone, when an install fails, or when someone asks where to download the app.

A promise you made to a named person and still owe them — "me comprometí a", "quedé en", "le dije a", "avisarle a", "compromisos pendientes" — with the counterparty, the date you gave them and the channel you said it on. Sibling of apx-task, deliberately NOT the same thing. Load whenever someone else is waiting on something. Triggers: 'I told X I would…', 'le dije a X que…', 'I promised…', 'quedé en…', 'me comprometí a…', 'what do I owe X', 'qué le debo a X', 'overdue promises', 'mark it kept...

Generate an image from a text prompt — "generá una imagen", "creá un logo", "dibujame", "hacé una ilustración" — routed to a local, LAN or cloud engine. Load when asked to draw, render, illustrate, or make a picture, logo sketch, thumbnail, or cover; to pick between image engines; to set image size, steps, guidance, seed, or a negative prompt; or when an image engine is unreachable or ignoring options.

APX connectors and integrations — "integraciones", "conectores", "conectá", "no ves mi calendario" — Asana, Google Calendar, GitHub, Obsidian, WhatsApp. Load when a connector tool says "not connected" / "read-only" / "not authorized", or the user wants to connect/configure/check a plugin. NOT the same as MCP servers (apx-mcp) or the Telegram channel (apx-telegram). Triggers: 'connect Asana/Calendar/GitHub', 'why can't you see my calendar', 'integration not connected', 'plugins tab', 'read-onl...

Author a new MCP (Model Context Protocol) server and register it in APX. Covers JSON-RPC stdio protocol, FastMCP (Python) / TypeScript SDK shapes, tool design, secrets, debugging. Load when building a new MCP / exposing a new tool surface. To add an existing MCP, load `apx-mcp` instead.

Register, list, debug, scope MCP servers in APX. Load BEFORE adding any MCP — three scopes (shared/runtime/global) with different commit and secrecy semantics. Triggers: 'add MCP', 'apx mcp', 'MCP scope', 'MCP failing', 'list MCPs'.

Agent profiles: installable lines of work — "el perfil", "perfiles disponibles", "instalá un perfil" — secretary, project manager and others. Load when the user wants to install, activate, configure, diagnose or remove one, or asks why the agent behaves the way it does. Triggers: 'install a profile', 'apx profile', 'what profiles are there', 'activate the secretary', 'go back to vanilla', 'change my agent's schedule', 'why does it message me'.

Register, list, configure, manage APX projects. Load BEFORE asking "which project?" — registered projects are listable; per-project config set via dotted-key PATCH. Triggers: 'register project', 'apx project', 'project config', 'list projects', 'what projects are registered'.

Scheduled recurring automation — a routine, "una rutina", "rutinas", "todos los días", "cada mañana", "tarea programada": create, edit, run and debug APX routines. Load BEFORE `apx routine add` — schedule grammar, kind selection, pre/post hooks, double-reply gotcha.

Hand a job to an external coding CLI — "delegá", "corré esto con", "usá claude code", "usá codex", "usá opencode" — claude-code, codex, opencode, aider. The APX agent is optional — pass-through runs the CLI as itself, `-a <agent>` wraps it in that agent's system prompt. Load when delegating to another AI tool, or when confused about the agent argument.

Coding session operations across engines (apx, claude, codex, opencode, antigravity) — a session, "una sesión", "las sesiones", "retomá la sesión", "seguir donde quedamos": find by title, list, get transcript, summarize, ask, resume, continue. Triggers: 'apx session find/ask/summary/resume/get', 'find/resume/summarize session', 'get session transcript', 'continue session in apx'. Not for `apx run` orchestration (use apx skill).

Write a new APX skill — "creá una skill", "una skill nueva", "cómo se escribe una skill" — file location, frontmatter and body style. Load when creating or adding a skill to APX.

Per-project to-do list — a task, "una tarea", "tareas pendientes", "tareas abiertas", "anotá", "marcá como terminada" — with subtasks, comments and a board. Event-sourced, project-scoped, addressable by short id prefix. Load when user wants to note, remind, list, read, EDIT, reassign, complete, split or comment on a task. Triggers: 'add a task', 'remind me to…', 'what's pending', 'mark as done', 'open tasks', 'what does that task say', 'change the due date', 'cambiale la fecha', 'movelo al vi...

APX Telegram plugin — channels, project pinning, master agents, media. Load BEFORE configuring a new bot or routing — channels[] is the only place credentials live.

Turn recorded audio or video into text — "transcribí", "pasá a texto", "la grabación", "este audio", "este video" — with `apx transcribe`. Load when asked to transcribe a voice note, an audio clip, or a video's speech, to batch-transcribe a folder, to pipe transcription into a script, or when choosing between the local, cloud, or a networked custom STT engine.

Text-to-speech: make APX speak out loud — "la voz", "que me hable", "en voz alta", "motor de voz", "leelo" — Piper local, ElevenLabs, OpenAI or Gemini. Load when configuring a voice engine, adding a custom TTS server, enabling emotion tags, or fixing silent output.

APX WhatsApp channel — one paired account, an allowlist roster, and a sealed turn for everyone who is not the owner. Load BEFORE adding a contact, changing who gets answered, sending a message, or explaining why somebody was not replied to.

APX CLI umbrella — routes operations to sub-skills (sessions, MCPs, routines, tasks, commitments, telegram, projects, agents, agent vault, profiles, runtimes). Activate on `apx`, the APX daemon, or coordinating/running/delegating agents. Not for `.apc/` alone (use apc-context). Triggers: 'apx', 'apx run', 'apx daemon', 'coordinate agents'.

Activate ONLY when the user explicitly mentions Claude Code, Claude CLI, claude command, Anthropic Claude Code, installing Claude Code, using Claude Code, or APX runtime claude-code. Do not activate for generic Claude model discussion.

Activate ONLY when the user explicitly mentions Codex CLI, OpenAI Codex, @openai/codex, codex command, codex exec, installing Codex, using Codex, ~/.codex, or APX runtime codex.

Activate ONLY when the user explicitly mentions OpenCode, opencode command, installing OpenCode, using OpenCode, OpenCode provider setup, or APX runtime opencode.

Activate ONLY when the user explicitly mentions OpenRouter, OPENROUTER_API_KEY, OpenRouter models, installing OpenRouter provider config, or using OpenRouter with APX, OpenCode, LiteLLM, or an OpenAI-compatible client.

APX Discord channel — a bot on a community server, an allowlist of rooms with a mode each (always / mention / read), and a sealed turn for everyone. Load BEFORE adding or changing a Discord room, setting the bot up, posting to Discord, or explaining why the bot did or did not answer.