cc-connect
Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Slack, Telegram, Discord). Use when: controlling AI agents from team chat, sending coding tasks via Slack/Telegram, building team-accessible AI workflows.
What this skill does
# CC-Connect
## Overview
CC-Connect bridges AI coding agents running on your local machine to the messaging platforms your team already uses. Code review, research, automation, data analysis — anything an AI agent can do, now accessible from your phone, tablet, or any device with a chat app.
**Architecture:** Your local AI agent <-> CC-Connect bridge <-> Messaging platform (Slack/Telegram/Discord/etc.)
Send a message in Slack, CC-Connect routes it to your local Claude Code instance, the agent does the work, and the response comes back to your chat.
## Instructions
### Installation
```bash
npm install -g cc-connect
```
### Configuration
Create a `cc-connect.yaml` in your project:
```yaml
agent:
type: claude-code # or: codex, gemini, cursor
workdir: /path/to/your/project
platform:
type: telegram # or: slack, discord, feishu, dingtalk
token: "your-bot-token"
```
### Platform Setup
**Telegram:** Create a bot via @BotFather, get the bot token, and add it to your config.
**Slack:** Create a Slack App at api.slack.com/apps, enable Socket Mode and Event Subscriptions, add Bot Token Scopes (`chat:write`, `app_mentions:read`, `messages.im`), and install to your workspace.
**Discord:** Create an application at discord.com/developers, create a bot, enable Message Content Intent, and invite the bot to your server.
### Starting the Bridge
```bash
cc-connect init # Interactive wizard for platform credentials
cc-connect start # Start routing messages
```
### Session Management
```yaml
session:
timeout: 30m
max_concurrent: 3
continue: true
auto_compress: true
```
### Multi-Agent Routing
Route different commands to different agents:
```yaml
agents:
code-review:
type: claude-code
workdir: /path/to/project
trigger: "!review"
research:
type: gemini
trigger: "!research"
```
### Access Control
```yaml
access:
allowed_users: ["U123", "U456"]
allowed_channels: ["C789"]
admin_users: ["U123"]
```
## Examples
### Example 1: Team Code Review via Slack
A team sets up CC-Connect to allow engineers to request code reviews from Slack:
```yaml
# cc-connect.yaml
agent:
type: claude-code
workdir: /home/dev/acme-api
platform:
type: slack
app_token: "xapp-1-A07QX4R..."
bot_token: "xoxb-8234567890-..."
channels: ["#code-review"]
session:
timeout: 10m
auto_compress: true
access:
allowed_channels: ["#code-review"]
allowed_users: ["U0381KDLS", "U0492JFMA"]
```
In Slack `#code-review`, an engineer types: `@agent Review the auth module for SQL injection risks`. Claude Code analyzes the code and responds in the thread with findings.
### Example 2: Scheduled Daily Reports via Telegram
A solo developer configures CC-Connect with cron jobs for automated daily standup reports:
```yaml
agent:
type: claude-code
workdir: /home/dev/saas-app
platform:
type: telegram
token: "7284619035:AAF-kLm9xPqR..."
allowed_users: ["198274563"]
cron:
- schedule: "0 9 * * 1-5"
command: "Summarize yesterday's git commits and open PRs, highlight blockers"
platform: telegram
timeout: 5m
fresh_session: true
```
Every weekday at 9am, the agent generates a summary of recent activity and sends it to the developer's Telegram chat.
## Guidelines
- Start with one messaging platform and get it working before expanding to others
- Always set `allowed_users` in production to restrict access
- Use threads in Slack/Discord to keep conversations organized
- Set `session.timeout` to prevent runaway agent sessions consuming resources
- Enable `auto_compress` for long conversations to prevent context overflow
- Use `fresh_session: true` for cron jobs to avoid inherited context from previous runs
- Verify your setup with `cc-connect status` if messages are not routing
- See the [GitHub Repository](https://github.com/chenhg5/cc-connect) for full documentation
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.