Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Callyourcode

ASecurity

Talk to the user through the CallYourCode app. Use when messages arrive prefixed "VOICE:" or "TEXT:", when the callyourcode MCP (speak/chat/show) is connected, or when the user asks to see something "in the app".

2 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgo

Works with

terminalclimcp

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add CallYourCode/CallYourCode --skill callyourcode --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Callyourcode?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Callyourcode
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/callyourcode-callyourcode/badge)](https://www.skillsdirectory.com/skills/callyourcode-callyourcode)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: callyourcode
description: Talk to the user through the CallYourCode app. Use when messages arrive prefixed "VOICE:" or "TEXT:", when the callyourcode MCP (speak/chat/show) is connected, or when the user asks to see something "in the app".
---

# CallYourCode

The user is talking to you from the CallYourCode app on their phone,
tablet or laptop. They cannot see your terminal; the app's tools are the
only channel back: `speak` is heard, `chat` is read, `show` is seen.

## Messages, in and out

From them: every message arrives prefixed `VOICE:` (spoken) or `TEXT:`
(typed), and ends with a note saying how they want the reply: speech,
text, or both. Follow the note. Files they send you (photos, voice notes)
arrive as file paths you can open.
From you: a turn that ends without a speak, chat or show call reached
nobody. Speech leads with the answer, stays short and conversational, and
never reads markdown, code or paths aloud; they can interrupt you
mid-sentence. Text is a chat message, light markdown. Anything better
looked at than heard goes through `show` (lists, code, diffs, logs,
images, interactive pages that can question the user and send answers
back); copy a working page from `engine/mcp/examples/`, details in PAGES.md.

## Acting in the app

The engine at 127.0.0.1:10101 holds your conversation's state. Your own
agent id comes from this server's `info` tool; every `cyc` command takes
an agent id explicitly. You can, and should when asked:

- Name and photo: give this conversation a recognizable identity.
- Reminders and crons: schedule one-off or repeating messages the app
  delivers back to you.
- Other agents: list who is running on this machine, and message any of
  them: hand off work, ask status, wake one.
  Every command for these, ready to run: CLI.md, as the `cyc` command.

## Extending the app

Every toolbar button, card and composer control the user sees is a plugin:
one file the engine serves and the app renders. The built-ins (usage card,
crons, search, model, persona) are the reference set. Reading what this
machine declares, or writing a new plugin: PLUGINS.md.

## Setup

If the app's tools are missing from this session, the `callyourcode`
server is registered per project in `.mcp.json` and needs the engine
running: SETUP.md.

Attribution

CallYourCodeCallYourCode
View sourceMore from CallYourCode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →