agentleFS
matthewdonsemail-labmatthewdonsemail-lab/log/.claude/skills/log-inbox-reactions/SKILL.md

log-inbox-reactions

Skill63 starsChanged 2 days agoMITView on GitHub

Reacting to a message. A log play (docs/useCases/inbox/reactions.md): React to someone's message with an emoji on X, Discord, Slack or Instagram, the way a person answers a moment without typing: a laugh at a joke, a fire on a win, a heart on good news. It goes through the platform's own engine and the account's one session, never the browser, and counts as a write (rule 8).

The file

Files
SKILL.md

Reacting to a message

This is the log play inbox/reactions. Before anything else, call the log MCP tool getGuide({ useCase: "inbox/reactions" }): 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).

React to someone's message with an emoji on X, Discord, Slack or Instagram, the way a person answers a moment without typing: a laugh at a joke, a fire on a win, a heart on good news. It goes through the platform's own engine and the account's one session, never the browser, and counts as a write (rule 8).

How the owner asks for it: "react to that", "heart his message", "put a 😂 on what she said", "send a reaction to <person>"

Run it from a fresh context

Say: "go on docs/useCases/inbox/reactions.md for <person or chat>". The agent reads this page and runs the steps.

The steps

#StepToolDone when
1Read the chat and find the message to react to, with its idtwitterDms { with }, discordRead { channel }, slackRead { chat } or instagramDms { with }, with jsonone message named with its author, time and id (a Slack message's id is its ts)
2Pick the emoji: the one the owner named, or the one a person would put on that momentthe agent, from the chatone emoji
3Dry run itmessagesReact { account, chat, message, emoji }: the platform is the account's (or twitterReact, discordReact, slackReact, instagramReact)the dry run names the chat and the message
4ReactmessagesReactLive { account, chat, message, emoji, approvedBy: "<owner>", confirmLive: true } (or twitterReactLive, discordReactLive, slackReactLive, instagramReactLive)the platform answers sent
5Tell the owner what was reacted tothe reply to the ownerthe message quoted with the emoji

On Discord the chat flag is channel and on Instagram thread. remove takes the account's own reaction off. A refusal stops it, and nothing is tried again until the owner says so (rule 94).

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.