Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Send messages to Discord channels via the Discord API. Use this skill when the user wants to send text messages, notifications, or formatted content to a Discord channel.
.claude/skills/evolution-foundation-discord-send-message/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 94% | 0% |
| case-06 | ✓→✗ | ▼ Worse | 37% | 0% |
| case-07 | ✓→✓ | = Same ✓ | 58% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 91% | 0% |
| case-08 | ✓→✓ | = Same ✓ | 33% | 0% |
Send messages to Discord channels using the Discord API v10. This skill supports plain text messages, formatted markdown content, and embeds.
Use this skill when the user wants to:
DISCORD_BOT_TOKEN environment variable must be setWhen the user requests to send a Discord message:
DISCORD_BOT_TOKEN is set in environmentUse the following curl command structure:
bash curl -X POST "https://discord.com/api/v10/channels/{CHANNEL_ID}/messages" \ -H "Authorization: Bot ${DISCORD_BOT_TOKEN}" \ -H "Content-Type: application/json" \ -d '{"content": "Your message here"}'
Replace:
{CHANNEL_ID} with the actual channel ID"Your message here" with the actual message contentjson{ "content": "Hello from Claude Code!" }
json{ "content": "**Bold text** *Italic text* `code` [Link](https://example.com)" }
json{ "embeds": [{ "title": "Notification", "description": "This is an embed message", "color": 3447003, "fields": [ { "name": "Field Name", "value": "Field Value", "inline": false } ] }] }
json{ "content": "Check out this embed:", "embeds": [{ "title": "Title", "description": "Description" }] }
Before sending:
401 Unauthorized
DISCORD_BOT_TOKEN is set correctly403 Forbidden
404 Not Found
400 Bad Request
See examples.md for detailed usage scenarios.
POST /channels/{channel.id}/messages| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-07 | pass→pass | 9,699 | 14,175 | +46% | 1 | 1 | 0% | 1,813 | 2,860 | +58% | 0 | 0 | — |
case-01 | fail→fail | 9,831 | 7,809 | -21% | 1 | 1 | 0% | 1,985 | 1,458 | -27% | 0 | 0 | — |
case-02 | fail→fail | 3,674 | 6,988 | +90% | 1 | 1 | 0% | 655 | 1,485 | +127% | 0 | 0 | — |
case-03 | fail→fail | 5,084 | 8,770 | +73% | 1 | 1 | 0% | 919 | 1,524 | +66% | 0 | 0 | — |
case-04 | fail→fail | 4,882 | 7,911 | +62% | 1 | 1 | 0% | 946 | 1,648 | +74% | 0 | 0 | — |
case-05 | pass→pass | 7,663 | 8,539 | +11% | 1 | 1 | 0% | 1,379 | 2,636 | +91% | 0 | 0 | — |
case-06 | pass→fail | 5,669 | 6,911 | +22% | 1 | 1 | 0% | 1,052 | 1,441 | +37% | 0 | 0 | — |
case-08 | pass→pass | 9,057 | 5,659 | -38% | 1 | 1 | 0% | 1,578 | 2,096 | +33% | 0 | 0 | — |
case-09 | pass→pass | 7,482 | 3,788 | -49% | 1 | 1 | 0% | 1,497 | 1,827 | +22% | 0 | 0 | — |
case-10 | pass→pass | 5,504 | 3,743 | -32% | 1 | 1 | 0% | 978 | 1,715 | +75% | 0 | 0 | — |
case-11 | fail→pass | 4,817 | 3,398 | -29% | 1 | 1 | 0% | 808 | 1,570 | +94% | 0 | 0 | — |
case-12 | pass→pass | 10,216 | 4,392 | -57% | 1 | 1 | 0% | 1,843 | 1,812 | -2% | 0 | 0 | — |
case-13 | pass→pass | 12,756 | 7,032 | -45% | 1 | 1 | 0% | 2,062 | 2,189 | +6% | 0 | 0 | — |
case-14 | pass→pass | 12,190 | 6,303 | -48% | 1 | 1 | 0% | 2,119 | 2,110 | -0% | 0 | 0 | — |
case-15 | pass→pass | 12,637 | 7,317 | -42% | 1 | 1 | 0% | 2,269 | 2,443 | +8% | 0 | 0 | — |
case-16 | pass→pass | 4,103 | 2,441 | -41% | 1 | 1 | 0% | 602 | 1,476 | +145% | 0 | 0 | — |
case-17 | pass→pass | 12,599 | 5,938 | -53% | 1 | 1 | 0% | 2,106 | 1,997 | -5% | 0 | 0 | — |
case-18 | pass→pass | 4,126 | 3,925 | -5% | 1 | 1 | 0% | 727 | 1,708 | +135% | 0 | 0 | — |
case-19 | pass→pass | 8,095 | 4,439 | -45% | 1 | 1 | 0% | 1,538 | 1,948 | +27% | 0 | 0 | — |
case-20 | pass→pass | 4,023 | 1,429 | -64% | 1 | 1 | 0% | 583 | 1,233 | +111% | 0 | 0 | — |
case-21 | pass→pass | 5,242 | 3,739 | -29% | 1 | 1 | 0% | 945 | 1,691 | +79% | 0 | 0 | — |
case-22 | pass→pass | 3,769 | 2,837 | -25% | 1 | 1 | 0% | 669 | 1,543 | +131% | 0 | 0 | — |
case-23 | pass→pass | 10,562 | 3,924 | -63% | 1 | 1 | 0% | 1,697 | 1,609 | -5% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 18 counted toward the lift figure. The other 5 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of 0 percentage points is the difference between those two pass rates over the 18 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.