inbox
Skill3 starsChanged 34 days agoMITView on GitHub
Read DM conversations, draft replies in your voice, send after approval; respects the 24-hour window and pending-approval drafts.
25 other projects use a version of this.
Adopted by
Most recently taken up by
- nmamano/isomuxtheir own version, first seen Nov 8, 2026
- tandregbg/core-claude-skillstheir own version, first seen Nov 4, 2026
- buildomator/buildomatortheir own version, first seen Nov 4, 2026
- le4ker/mneme-templatetheir own version, first seen Nov 1, 2026
- shakhruz/mila-coretheir own version, first seen Nov 1, 2026
- Anglesite/anglesite-skillstheir own version, first seen Oct 27, 2026
Used with
Projects with it also use tailor, task and 6 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
ledqSkilltailor
Tailor the resume to one job posting. Give it a URL, paste the posting (or refer to one pasted earlier in this chat), or point at a saved application folder; it resolves the JD and runs the tailor-pipeline workflow end to end.
Also in 3 projects that use this
endlessblinkSkilltask
Create a new task in MASTER_PLAN.md with auto-generated sequential IDs. Supports TASK, BUG, FEATURE, and INQUIRY types. Triggers on "/task", "add task", "new task", "create task", "track this".
Also in 3 projects that use this
genomewalkerSkilltasks
Browse and resume tasks, threads, and background jobs across sessions
Also in 3 projects that use this
AnthropicSkillonboarding
Generate an onboarding checklist and first-week plan for a new hire. Use when someone has a start date coming up, building the pre-start task list (accounts, equipment, buddy), scheduling Day 1 and Week 1, or setting 30/60/90-day goals for a new team member.
Also in 3 projects that use this
AnthropicSkillstatus
Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.
Also in 3 projects that use this
genomewalkerSkilllearn
Learn from web sources, generate SKILL.md, and store key patterns in soul memory. Trigger keywords: learn, skill-gen, web-learn, documentation, tutorial.
Also in 3 projects that use this
Other versions25 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 25
- me2resh/apexyard★ 542same name
- m13v/fazm★ 340same name
- mediar-ai/fazm★ 340same name
- kv0906/pm-kit★ 138same name
- minorun365/html-share★ 117same name
- buildomator/buildomator★ 102same name
- nmamano/isomux★ 43same name
- alxyrgin/health-os★ 38same name
- Anglesite/anglesite-skills★ 15same name
- aibtcdev/skills★ 11same name
15 more not listed
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.
In this repository50 other files it gives its agents.
- automationsSkill
- commentsSkill
- hooksSkill
- ig-auditSkill
- ig-captionSkill
- ig-carouselSkill
- ig-dmSkill
- ig-humanSkill
- ig-profileSkill
- ig-reelSkill
- ig-storySkill
- ig-viralSkill
- linkedin-comment-drafterSkill
- linkedin-content-plannerSkill
- linkedin-employee-advocacySkill
- linkedin-engager-analyticsSkill
- linkedin-hook-extractorSkill
- linkedin-humanizerSkill
- linkedin-interviewerSkill
- linkedin-post-writerSkill
- linkedin-profile-optimizerSkill
- linkedin-reply-handlerSkill
- linkedin-repurposerSkill
- linkedin-thread-monitorSkill
- naver-ai-citeSkill
- naver-draftsSkill
- naver-engageSkill
- naver-keywordsSkill
- naver-postSkill
- performance-reviewSkill
- publishSkill
- repurposeSkill
- schedule-weekSkill
- setupSkill
- threadsSkill
- troubleshootSkill
- voice-profileSkill
- yt-auditSkill
- yt-benchmarkSkill
- yt-chaptersSkill
- yt-commentSkill
- yt-editSkill
- yt-packageSkill
- yt-planSkill
- yt-retentionSkill
- yt-scriptSkill
- yt-seoSkill
- yt-shortsSkill
- yt-uploadSkill
- yt-viralSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 20 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Read ~/.uplika/<workspace-slug>/voice.md first if it exists.
- Distinctive: line 23
Never invent prices, stock, dates, links or promises.
- Very specific: line 24
Leave contacts who opted out alone: the contact shows it, and sending is refused with opted_out.
- Distinctive: line 41
When an AI automation wrote a reply while the window was closed, Uplika kept it as a draft waiting for approval instead of sending it.
“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Inbox
Use this for "check my DMs", "answer my messages", "what is in my inbox". It reads the conversations Uplika receives (direct messages, and public threads such as mentions on Threads), drafts replies in the person's voice, and sends only what the person approves. Below, "the contact" is whoever wrote to the account.
1. Read
- Start with
list_accountsto see which accounts are connected; never assume one is. With nothing connected that receives messages, there is nothing to read: send the person to https://uplika.com/dashboard/connections. If a call answersworkspace_required, show the workspaces it lists, ask which one, and passworkspaceId. list_conversationslists open conversations by default. Narrow it withstate(closedfor closed ones),unread,kind(dmormention),accountId, orsearch(a name or words from the last message). Each item says whether the messaging window is open and how much of it is left.- Show the list with the conversations whose window closes soonest first, then mentions, then those whose window is closed.
read_conversationopens one: the recent messages and the contact (name, whether they follow the account on Instagram, tags, opt-out). AI drafts waiting for approval appear there with statusdraft.get_contactwhen you need more about the contact: username, follow status in both directions (Instagram, and only for people who have messaged), follower count, tags, opt-out, and when their window closes. Passrefresh: trueto re-read the profile from the channel.
2. Draft
Read ~/.uplika/<workspace-slug>/voice.md first if it exists. If not, ask three questions (tone, how messages end, words to avoid) and offer to save the answers with the voice-profile skill.
- Answer what the contact asked, in the language they wrote in. Keep it short: one message unless the question needs more.
- Never invent prices, stock, dates, links or promises. When the answer needs something only the account owner knows, ask the person.
- Leave contacts who opted out alone: the contact shows it, and sending is refused with
opted_out.
3. Show and get approval
Show each draft with the contact, the channel, and whether the window is open. The person approves, edits or drops each one. Nothing is sent before they approve it.
4. Send
send_dmwith the conversation id and the approved text.- An AI draft the person approves:
send_dmwith itsdraftId. To send it edited, pass the editedtexttogether with thedraftId. Dropping an AI draft is done in the dashboard inbox (https://uplika.com/dashboard/inbox); no tool does it. - A conversation whose window has
modepublic_reply(a mention thread on Threads, or a comment thread) has no messaging window:send_dmthere posts a public reply, not a private message. Say so when you show the draft. Threads has no direct messages (faq:threads-no-dm). - Sending as the person pauses the account's automations in that conversation for a while (the
send_dmdescription says how long). Tell the person if an automation was answering there.
The messaging window
Meta lets the account message a contact only inside the messaging window that opens when the contact writes (faq:dm-24h-window). Outside it send_dm is refused with window_closed, and nothing can be sent until the contact writes again. Say that plainly, keep the approved draft for when they do, and do not suggest a way around it.
When an AI automation wrote a reply while the window was closed, Uplika kept it as a draft waiting for approval instead of sending it. Sending that draft is still a message, so it also needs the window to be open again.
Held replies on Threads
If the person uses Threads reply approval, replies to their Threads posts wait in a queue until approved. approve_reply with the account id and no reply id lists the queue. With a reply id it approves that reply, which makes it public, or ignores it with approve: false. Show each held reply and act only on the person's decision. Working through the replies under posts in general is the comments skill.
Errors
reconsent_required: the account was connected without the messaging permissions, or (on a mention list, as anotice) without the mentions permission. Reconnecting the account adds it; thetroubleshootskill walks the person through it (faq:dm-reconnect).feature_in_review: the permission is still in the platform's review and reconnecting does not help yet. Thetroubleshootskill explains.account_disconnected: thetroubleshootskill.- Anything else: call
get_helpwith the code and pass its answer and url on.
Tools
list_accounts: which accounts are connected, before reading the inboxlist_conversations: the inbox list, with the window state of each conversationread_conversation: one conversation, its contact and any AI drafts waiting for approvalget_contact: one contact's details and when their window closessend_dm: send an approved message, or an approved AI draft with draftIdapprove_reply: Threads only: list held replies, then approve or ignore one after the person decidesget_help: the answer for an error code
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.

