discordembed
Skill1 starsChanged 4 months agoMITView on GitHub
Compose the current answer / chat context as a rich Discord EMBED-style writeup (the ~6000-char embed budget, bold headers, emojis, masked links, custom emoji tokens) and copy it to the clipboard, ready to paste — does NOT auto-post. Use when the user says "/discordembed", "embed this", "make a discord embed", "long discord post", "6k embed post".
In this repository9 other files it gives its agents.
- commitpushSkill
- discordmsgSkill
- endSkill
- handoffSkill
- prettyhtmlSkill
- prettymsgSkill
- startSkill
- wrapupSkill
- wtfSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 40
Don't pad. A tight, scannable writeup beats a wall.
- Very specific: line 57
Only if it genuinely needs more → split into two blocks, separated by a clear --- (part 2) --- marker, keeping the total ≤ 6000.
- Very specific: line 59
If important *attachment-style* detail (full logs, raw numbers, code) overflows even 6000 → that isn't embed material.
- Very specific: line 65
Write the raw text (no surrounding fence) to a temp file, e.g.
- Very specific: line 100
if a .txt overflow file was written, its absolute path + a one-line note on what's in it.
- Very specific: line 114
Write the raw text to a temp file — ${TMPDIR:-/tmp}/discord-embed.txt.
- Distinctive: line 119
Do not send anything anywhere and do not commit — this skill only formats and copies.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/discordembed — compose a rich Discord EMBED-style writeup, copied to your clipboard
Take what was just figured out / produced in this chat and package it in Discord embed style —
then put it on the clipboard, ready to paste yourself. Like /discordmsg, but using the embed
formatting rules (bigger budget, bold headers, masked links, custom emoji tokens) instead of the
plain-message rules. This skill never sends anything anywhere — no webhook, no auto-post. It only
formats and copies.
Why embed style (vs a plain /discordmsg message):
- Embed formatting affords a bigger combined budget —
description ≤ 4096, whole payload≤ 6000— good for a longer writeup than a normal Discord message allows. ##/###headers do not render inside an actual Discord embed → use**bold**section headers instead, regardless of where this text ends up.- Masked
[text](url)links and full-token custom emoji (<:name:id>/ animated<a:name:id>) are written the same way whether this lands in an embed or gets pasted as-is.
Embeds are typically produced by a bot or webhook payload (a
content-plus-embedsJSON post). This skill gives you the ready-to-drop-in text; how you turn it into an actual embed (a bot, a webhook tool, or a site that builds the payload) is up to you.
The embed format (rules of the output)
##/###headers do NOT render inside an embed → use**bold**for every header/section label instead. (The #1 embed gotcha.)- Lead with a one-line TL;DR, then bold-headed sections with
-bullets. Overview first, detail second — written for a reader who was NOT in the chat. - Emojis where they slap — one per section header + the odd inline accent (✅ done, 🐛 bug,
🔧 fix, ⚠️ caveat, 🚀 shipped, 📊 numbers, 🎯 goal). Plain unicode renders fine; relevant, not
confetti. Custom server emoji must carry the full token
<:name:id>(animated<a:name:id>) — the:name:shorthand does not expand outside the Discord client. - Masked links work in embeds —
[text](url)renders, so you may use them. Raw URLs work too. - A title is optional — put it as a single bold line at the top of the text if used.
- Don't pad. A tight, scannable writeup beats a wall. Length serves clarity.
Audience note
Tailor the content to where it's going. If the destination is a shared team / work channel, keep it to status & progress — what's done / in flight / next — and don't assign work to others or air open problems as things needing attention. For a personal or casual channel, anything goes. (When in doubt, write a clean progress overview, not a task list.)
Character budget
DESC_CAP = 4096 # one embed's worth of text
TOTAL_CAP = 6000 # if it must span two embeds worth (rare)- Compose the overview to fit one block ≤ 4096. That covers almost every writeup.
- Only if it genuinely needs more → split into two blocks, separated by a clear
--- (part 2) ---marker, keeping the total ≤ 6000. - If important attachment-style detail (full logs, raw numbers, code) overflows even 6000 → that
isn't embed material; mention it in one line and spill it to a
.txtinstead (same overflow convention as/discordmsg).
Copy to clipboard (always)
- Write the raw text (no surrounding fence) to a temp file, e.g.
${TMPDIR:-/tmp}/discord-embed.txt. Writing to a file (not a shell var) avoids emoji/quote escaping bugs. - Copy that file to the clipboard with whatever's available on this OS — try in order and use the
first that exists:
F="${TMPDIR:-/tmp}/discord-embed.txt" if command -v pbcopy >/dev/null; then pbcopy < "$F" # macOS elif command -v wl-copy >/dev/null; then wl-copy < "$F" # Linux / Wayland elif command -v xclip >/dev/null; then xclip -selection clipboard -i "$F" # Linux / X11 elif command -v xsel >/dev/null; then xsel -b -i < "$F" # Linux / X11 (alt) elif command -v clip.exe >/dev/null; then clip.exe < "$F" # Windows / WSL else echo "no clipboard tool found — use the copy block below"; fi - ⚠️ Remote/SSH caveat — say this when it applies. If
SSH_CONNECTIONis set, the clipboard command writes to the remote machine's clipboard, which usually does not reach the user's local machine over plain SSH. In that case the copy-friendly fenced block (below) is their fallback — always print it too.
How to deliver it back to the user
Present the text inside a copy-friendly fenced block (belt-and-suspenders: the fallback when the clipboard can't cross SSH) so one select grabs the raw markdown:
````
**Title (optional)**
**🎯 TL;DR**
... the embed-style writeup ...
````Then, below the block, in your normal reply (NOT inside the copy block):
- a line confirming the text is on the clipboard (+ the SSH caveat if it applies);
- one line confirming char count vs the budget (e.g.
1,694 / 4096 chars ✅); - if a
.txtoverflow file was written, its absolute path + a one-line note on what's in it.
$ARGUMENTS
- Focus string (e.g.
/discordembed the release notes) → summarize that, aimed at that audience/angle. A tone/length request ("short", "very detailed") overrides defaults (caps hold). - No focus → summarize the most recent substantive result in the chat, as a general share.
Execution steps
- Parse
$ARGUMENTS→ subject + audience/tone. - Draft the writeup in embed-style markdown using bold headers (NOT
##), TL;DR → bold-headed sections → bullets, emojis where they slap, outsider-readable, audience-appropriate. Fit it to ≤ 4096; only split into a second block if it truly needs the 6k budget. - Write the raw text to a temp file —
${TMPDIR:-/tmp}/discord-embed.txt. - Copy it to the clipboard (write to file → clipboard command → confirm), per the Copy to
clipboard section. Flag the SSH caveat if
SSH_CONNECTIONis set. - Output the text in a copy-friendly fence; below it confirm it's on the clipboard, report the char
count vs budget, and give any
.txtoverflow path. - Do not send anything anywhere and do not commit — this skill only formats and copies.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

