fb-reply
Skill1 starsChanged 16 days agoMITView on GitHub
Handle the comments under the user's own Facebook post - sort them into keyword / lead / substance / question / support / complaint / noise, then write replies in that order. Use when the user pastes their comments, says "help me reply to these", "how do I answer this comment", or has a post taking off.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- tonydzi/second-brain-starter-kittheir own version, first seen Sep 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- tonydzi/second-brain-starter-kit★ 6same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Ask for the comments (pasted or a screenshot).
- Distinctive: line 45
Use their first name. Vary every reply.
- Distinctive: line 47
Never invent a policy, discount or promise the user hasn't confirmed.
≈ “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
fb-reply
The thread under a post is part of the post. Replies keep it alive and turn commenters into conversations.
Sort first
Ask for the comments (pasted or a screenshot). Sort every one:
| bucket | what it is | priority |
| KEYWORD | they typed the word the post asked for | 1 - send what was promised |
| LEAD | price question, "do you deliver to...", "how do I book" | 1 |
| COMPLAINT | a problem with the product or service | 1 - publicly, calmly |
| QUESTION | about the content | 2 |
| SUBSTANCE | adds a point or a story | 2 |
| SUPPORT | "love this", tags, emoji | 3 - short reply or a reaction |
| NOISE / SPAM | scams, links, bots, abuse | hide or delete; never argue |
Write replies in that order
- KEYWORD / LEAD: short public reply ("Sent you a message, Sita!") then the
private message via
/fb-dm. On Pages, Meta's "comment to message" automations can do the keyword part through Business Suite. Never put prices that change daily in a public comment if they belong in a message. - COMPLAINT: acknowledge, own what's yours, move details to Messenger, come back and say it's resolved. Never delete a fair complaint.
- QUESTION: answer it fully in the reply. Others will read it.
- SUBSTANCE: respond to their point specifically; a question back keeps the thread going.
- SUPPORT: a few words using their name, or just a reaction. Don't paste the same "Thank you so much! ❤️" 40 times.
Rules
- Use their first name. Vary every reply; identical replies read as a bot.
- 1-2 sentences, in the user's voice. Run through
/fb-human. - Never invent a policy, discount or promise the user hasn't confirmed.
- The user posts the replies.
Output
A table: commenter, bucket, reply. Then a one-line summary of leads to follow up in Messenger.
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.