agentleFS
matthewdonsemail-labmatthewdonsemail-lab/log/.claude/skills/log-instagram-dm-reply/SKILL.md

log-instagram-dm-reply

Skill63 starsChanged 2 days agoMITView on GitHub

Reading and answering an Instagram DM. A log play (docs/useCases/instagram/dmReply.md): Read what someone wrote to the account on Instagram and answer it in the owner's voice, with text or a meme, on the account's own session through vendor/instagrapi. No browser, ever.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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
  1. Distinctive:

    Read what someone wrote to the account on Instagram and answer it in the owner's voice, with text or a meme, on the account's own session …

    line 15

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Reading and answering an Instagram DM

This is the log play instagram/dmReply. Before anything else, call the log MCP tool getGuide({ useCase: "instagram/dmReply" }): it returns this page and makes it the session's play, so every log tool's answer says which step you are on and a send with no play loaded is refused (rules 157, 158). Then follow the steps in order.

Draft every message from that person's own thread and matt's real replies (voice with no text, search), never from memory, and never send two that read alike (sameAsSent).

Read what someone wrote to the account on Instagram and answer it in the owner's voice, with text or a meme, on the account's own session through vendor/instagrapi. No browser, ever.

How the owner asks for it: "read my instagram dms", "what did <someone> say on instagram", "reply to <someone> on instagram", "send <someone> a meme on instagram"

Run it from a fresh context

Say: "go on docs/useCases/instagram/dmReply.md for <someone>". The agent reads this page and runs the steps.

The steps

#StepToolDone when
1Session checkinstagramSessionCheck { account }loggedIn as the account's handle
2The inbox, or the thread with theminstagramDms { account }, then instagramDms { account, with: "<handle>" }their latest message and what came before it
3Pull how the owner writes to them, then draft only from facts the owner gavevoice { to: "<handle>", with: "<who>", context } (no text)a draft that answers what they said
4For a meme, find one that fits the moment, ranked by the owner's taste, and save its picturememelordSearch { query: ["<the moment>"], method: "fulltext", type: "meme" }a template that fits, saved as a JPEG
5Gate the draft or the memevoice { to, with, context, text: "<draft or media url>" }it passes
6Send it: text one message per line, a meme as photoinstagramSendLive { account, with: "<handle>", text and/or photo: "<file>", approvedBy: "<owner>", confirmLive: true }Instagram answers each message with its id
7Tell the owner what they said and what went outthe reply to the ownerboth quoted with their times

New messages arrive by themselves: the inbox hook keeps log instagram watch --inbox open for every signed-in Instagram account on Instagram's realtime connection and puts each new DM in front of the agent (>>> NEW INSTAGRAM MESSAGE).

What the runs taught

  • Never the browser. On 2026-11-04 a meme went out through the account's AdsPower browser and the owner said that is not the way: read, send and watch are the engine's.
  • A meme goes as the picture. Memelord answers with a media URL; save it as a JPEG and send it as photo, never the link.
  • Pick from the top of the taste ranking, with judgement. A template built on a stereotype is skipped even when it ranks first.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.