threads
Skill3 starsChanged 33 days agoMITView on GitHub
Write Threads posts and chains in your voice, add a topic tag, reply to comments, and learn from your real insights what works.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- matthull/my-skillstheir own version, first seen Oct 20, 2026
- enkr1/claude-code-skillstheir own version, first seen Oct 20, 2026
- obra/muse-skillstheir own version, first seen Oct 13, 2026
- shabash-dev/shabash-pluginstheir own version, first seen Oct 13, 2026
- AceDataCloud/Skillstheir own version, first seen Oct 6, 2026
- thenavidm/threads-mcp-clitheir own version, first seen Oct 5, 2026
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- obra/muse-skills★ 20same name
- AceDataCloud/Skills★ 17same name
- jacobwell/muse-skills★ 8same name
- thenavidm/threads-mcp-cli★ 4same name
- retrodigio/claude-channel-slack★ 2same name
- andrmaz/spec-driven-architecture★ 1same name
- enkr1/claude-code-skills★ 1same name
- Dimks777/aiclub★ 0same name
- matthull/my-skills★ 0same name
- shabash-dev/shabash-plugins★ 0same 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.
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
- inboxSkill
- 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
- 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
5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Read ~/.uplika/<workspace-slug>/voice.md if it exists.
- Very specific: line 14
Read the limits from select_channels or list_platforms.
- Very specific: line 21
Topic tag: only when the person wants one: options.threads.topicTag, one topic, no periods or ampersands.
- Distinctive: line 22
Check for machine-sounding text: before showing a draft, and rewrite when you find: the same bullet shape repeated, a summary sentence …
- Very specific: line 30
Read with list_replies on the post (or open_post from a link).
“Common” is measured: kept by at least 6 in 10 of the 9 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
Threads
Short posts and chains on Threads, written hook first, sent after approval, and improved from the account's own numbers.
Before writing
- Read
~/.uplika/<workspace-slug>/voice.mdif it exists. If not, ask three questions (tone, how posts end, words to avoid) and offer to save them with thevoice-profileskill. - Find the Threads account with
select_channels(scopethreads). If it answersworkspace_required, ask which workspace and passworkspaceId. - Read the limits from
select_channelsorlist_platforms. Count characters the waycharCountsays.
Writing
- Hook first. The first line is all most people see. Lead with the most specific thing: a number, a claim, a question, or the moment in a story. The
hooksskill has formulas and Korean patterns. - One idea per post. A second idea is a second post or the next piece of a chain.
- Chains for anything longer than one post: put the pieces in
threadItemsonpublish(the first item is the root, the rest are replies under it in order). Each piece should stand on its own when someone lands on it. - Topic tag only when the person wants one:
options.threads.topicTag, one topic, no periods or ampersands. It goes on the first piece. - Check for machine-sounding text before showing a draft, and rewrite when you find: the same bullet shape repeated, a summary sentence closing every paragraph, symmetrical "not X, but Y" contrasts, a philosophical closing line, and stacked connectors ("Moreover", "Additionally", "In addition").
Sending
Show the full text (every chain piece), the account and the time. Publish only after the person approves: publish with accountIds, threadItems or content, wait: true; for later, scheduledAt. Then give them the permalink.
Replies
- Read with
list_replieson the post (oropen_postfrom a link). Draft replies in the same voice, show them, send approved ones withreply. - Mentions of the account come from
list_mentionswhen the account holds that permission; if itsnoticesaysreconsent_required, the account was connected without it and one reconnect adds it (thetroubleshootskill explains). - Threads has no direct messages (
faq:threads-no-dm). Liking and mentions depend on permissions shown in the features table oflist_platforms; read it rather than promising.
Weekly review
Call list_channel_posts for the account and get_insights per post. Compare each post to the account's own median, never to other channels. Name the patterns behind the top posts (hook type, length, chain or single, posting time) and suggest the next three posts from them. Nulls are not zeros.
Tools
select_channels: the Threads account and its limitslist_platforms: rules and the features tablepublish: send or schedule a post or chain after approvallist_replies: replies under a postopen_post: a post from a link with replies and metricsreply: send an approved replylist_mentions: posts that mention the accountlist_channel_posts: the account's posts for the weekly reviewget_insights: per-post metrics
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.

