Agent skill

discord-get-messages

Retrieve messages from Discord channels via the Discord API. Use this skill when the user wants to read, search, or analyze messages from a Discord channel.

Stars 211
Forks 54

Install this agent skill to your Project

npx add-skill https://github.com/EvolutionAPI/evo-nexus/tree/main/.claude/skills/discord-get-messages

SKILL.md

Discord Get Messages

Retrieve messages from Discord channels using the Discord API v10. This skill supports pagination, filtering by message count, and retrieving message history.

When to Use This Skill

Use this skill when the user wants to:

  • Read recent messages from a Discord channel
  • Get message history for analysis
  • Search for specific messages in a channel
  • Retrieve messages before or after a specific message ID
  • Export channel conversation history

Prerequisites

  • DISCORD_BOT_TOKEN environment variable must be set
  • Bot must be a member of the target server
  • Bot must have "Read Message History" permission in the target channel
  • Valid Discord channel ID (18-19 digit snowflake ID)

Instructions

When the user requests to retrieve Discord messages:

  1. Validate Requirements

    • Confirm DISCORD_BOT_TOKEN is set in environment
    • Verify channel ID is provided (18-19 digit number)
    • Validate limit parameter (1-100 messages)
  2. Prepare Query Parameters

    • limit: Number of messages to retrieve (default: 50, max: 100)
    • before: Get messages before this message ID (for pagination)
    • after: Get messages after this message ID
    • around: Get messages around this message ID
  3. Make the API Request Use the following curl command structure:

    bash
    curl -X GET "https://discord.com/api/v10/channels/{CHANNEL_ID}/messages?limit=50" \
      -H "Authorization: Bot ${DISCORD_BOT_TOKEN}"
    

    Replace:

    • {CHANNEL_ID} with the actual channel ID
    • limit=50 with desired message count (1-100)
  4. Process Response

    • Messages are returned in reverse chronological order (newest first)
    • Each message contains: id, content, author, timestamp, attachments, embeds
    • Filter or format messages as requested by user
  5. Handle Response Codes

    • 200 Success: Messages retrieved successfully
    • 401 Unauthorized: Invalid bot token
    • 403 Forbidden: Missing "Read Message History" permission
    • 404 Not Found: Channel doesn't exist or bot can't see it
  6. Present Results

    • Format messages in a readable way
    • Show author, timestamp, and content
    • Include attachment URLs if present
    • Summarize if many messages retrieved

Query Parameters

Limit

bash
?limit=10  # Get 10 most recent messages (default: 50, max: 100)

Before (Pagination)

bash
?before=1234567890123456789&limit=50  # Get 50 messages before this message ID

After

bash
?after=1234567890123456789&limit=50  # Get 50 messages after this message ID

Around

bash
?around=1234567890123456789&limit=50  # Get 50 messages around this message ID

Message Object Structure

Each message returned contains:

json
{
  "id": "1234567890123456789",
  "channel_id": "123456789012345678",
  "author": {
    "id": "987654321098765432",
    "username": "Username",
    "discriminator": "0000",
    "avatar": "avatar_hash"
  },
  "content": "Message text content",
  "timestamp": "2025-10-20T12:00:00.000000+00:00",
  "edited_timestamp": null,
  "tts": false,
  "mention_everyone": false,
  "mentions": [],
  "mention_roles": [],
  "attachments": [],
  "embeds": [],
  "reactions": [],
  "pinned": false,
  "type": 0
}

Formatting Output

Simple Format

[2025-10-20 12:00] Username: Message content here
[2025-10-20 11:55] OtherUser: Another message

Detailed Format

Message ID: 1234567890123456789
Author: Username#0000 (987654321098765432)
Timestamp: 2025-10-20T12:00:00.000000+00:00
Content: Message text content here
Attachments: image.png (https://cdn.discordapp.com/...)

Filtering and Processing

Filter by Author

After retrieving messages, filter by author ID or username:

bash
# Get messages then filter in output
curl ... | jq '.[] | select(.author.username == "TargetUser")'

Filter by Content

Search for specific keywords in message content:

bash
# Get messages then search content
curl ... | jq '.[] | select(.content | contains("keyword"))'

Get Only Text Messages

Exclude system messages and embeds:

bash
# Filter message type 0 (default text messages)
curl ... | jq '.[] | select(.type == 0)'

Pagination Strategy

To retrieve more than 100 messages:

  1. Get first batch: ?limit=100
  2. Get oldest message ID from response
  3. Get next batch: ?before={oldest_id}&limit=100
  4. Repeat until all messages retrieved or desired count reached

Example:

bash
# First batch
curl "https://discord.com/api/v10/channels/{CHANNEL_ID}/messages?limit=100" \
  -H "Authorization: Bot ${DISCORD_BOT_TOKEN}"

# Get oldest message ID from response (e.g., 1234567890123456789)

# Next batch
curl "https://discord.com/api/v10/channels/{CHANNEL_ID}/messages?before=1234567890123456789&limit=100" \
  -H "Authorization: Bot ${DISCORD_BOT_TOKEN}"

Error Handling

Common Errors

401 Unauthorized

  • Check that DISCORD_BOT_TOKEN is set correctly
  • Verify token hasn't expired

403 Forbidden

  • Bot needs "Read Message History" permission
  • Bot needs "View Channel" permission
  • Check channel permission overrides

404 Not Found

  • Channel ID is incorrect
  • Channel was deleted
  • Bot doesn't have access to channel

400 Bad Request

  • Invalid limit parameter (must be 1-100)
  • Invalid message ID format for before/after/around

Rate Limiting

  • Discord allows 5 requests per 5 seconds per channel
  • Implement delays between requests when paginating
  • Wait 1 second between pagination requests

Security Notes

  • Never expose the bot token in messages or logs
  • Respect user privacy when handling message content
  • Don't store messages longer than necessary
  • Follow Discord's Terms of Service regarding data retention

Performance Tips

  • Use limit parameter to reduce response size
  • Retrieve only the messages you need
  • Cache results if querying the same channel multiple times
  • Use pagination for large history retrieval

Examples

See examples.md for detailed usage scenarios.

API Reference

Expand your agent's capabilities with these related and highly-rated skills.

EvolutionAPI/evo-nexus

data-create-viz

Cria visualizações de dados de qualidade profissional com Python no tema Evolution (fundo escuro, acento

211 54
Explore
EvolutionAPI/evo-nexus

cs-customer-escalation

Empacota uma escalação para Devs, Produto ou Davidson com contexto completo. Use quando um bug precisa de atenção além do suporte normal, vários clientes reportam o mesmo problema, um cliente está ameaçando cancelar, ou um problema ficou sem resolução além do SLA. / Package an escalation for engineering, product, or leadership with full context. Use when a bug needs engineering attention beyond normal support, multiple customers report the same issue, a customer is threatening to churn, or an issue has sat unresolved past its SLA.

211 54
Explore
EvolutionAPI/evo-nexus

mkt-draft-content

Draft blog posts, social media, email newsletters, landing pages, press releases, and case studies with channel-specific formatting and SEO recommendations. Use when writing any marketing content, when you need headline or subject line options, or when adapting a message for a specific platform, audience, and brand voice.

211 54
Explore
EvolutionAPI/evo-nexus

gog-tasks

Create, manage, and prioritize tasks and todo items. Convert emails to tasks, set priorities (P0-P3) and categories (Work/Personal/Errands/Admin), review daily priorities, track blocked and overdue tasks. Use when user mentions tasks, todos, action items, or wants to convert emails to tasks. Requires confirmation before creating or deleting tasks.

211 54
Explore
EvolutionAPI/evo-nexus

cs-customer-research

Pesquisa multi-fonte sobre pergunta ou tópico de cliente com atribuição de fontes. Use quando um cliente pergunta algo que precisa ser verificado, investigando se um bug foi reportado antes, verificando o que foi dito anteriormente a uma conta específica, ou coletando contexto antes de redigir uma resposta. / Multi-source research on a customer question or topic with source attribution. Use when a customer asks something you need to look up, investigating whether a bug has been reported before, checking what was previously told to a specific account, or gathering background before drafting a response.

211 54
Explore
EvolutionAPI/evo-nexus

int-omie

Omie ERP integration via API. Manage clients, products, orders, invoices (NF-e), financials (accounts receivable/payable), and stock. Use when users ask about ERP data, financials, orders, invoices, stock, or clients from Omie. Also handles webhooks for real-time events.

211 54
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results