tweet-post SKILL.md skillA
tweet-post from ibrahimsobh/aiskills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ibrahimsobh/aiskills/tweet-post@git:20261012.1337ffePins git:20261012.1337ffe in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ibrahimsobh/aiskills
- Path
tweet-post/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261012.1337ffe, committed Oct 12, 2026
- First version recorded
- Oct 8, 2026
- Size
- 14,663 bytes
- Repository stars
- 7
- License
- MIT
Write a tweet / X post about any kind of technical content — something the user built (a skill, tool, CLI, project), a research paper or finding, a technical insight, or a project update. Use whenever the user asks for a "tweet", "tweet-like post", "X post", or to "post this on Twitter/X," in English or Arabic — even if the user gives a different word/character limit. Also trigger when the user pastes a SKILL.md, README, paper abstract, or technical write-up and asks to "tweet about it" or…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Tweet Post ## Overview The user wants tweet-length technical posts written as a personal engineering narrative compressed to X-post size, not marketing copy and not a generic listy summary. This applies whatever the subject is — something the user built, a research paper or finding, a technical insight — the compression discipline and narrative arc are the same regardless of content type; only the voice changes (see Voice, below). The single biggest failure mode is treating "tweet-like" as *only* a brevity instruction and losing the narrative arc in the process — a tweet under this skill still has a hook, a turn, and a close that echoes it; it's just all of that packed into ~110 words instead of a paragraph each. The whole point of this skill is to hit that density without collapsing into a bare feature list. This skill is scoped to X/Twitter only. If the user asks for a LinkedIn post or something longer, that's a different pacing and structure (more room per beat, no hashtag convention) — don't force this skill's word cap or hashtags onto it; ask what length/platform the user actually wants. ## The structure Every post follows this shape, in order: …
Read the whole file at its exact version.
How to install
mdr add ibrahimsobh/aiskills/tweet-post@sha256:49eb7a8edb2d53eaThe line at the top of this page pins the label git:20261012.1337ffe, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_qejdgqla42pg7c52)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Oct 8, 2026 and Oct 12, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261012.1337ffe latest | 2026-10-12 | 1337ffe | 14,663 B | A | view · diff |
| git:20261008.e92b91a | 2026-10-08 | e92b91a | 14,550 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (14663 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
ibrahimsobh/aiskills · 7 stars · license MIT · pushed 2026-10-12 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_qejdgqla42pg7c52 GET https://markdownregistry.com/api/v1/resolve?ref=ibrahimsobh/aiskills/tweet-post GET https://markdownregistry.com/api/v1/blob/49eb7a8edb2d53eae10c6cf8bad890a9ad6e47315a9a53d6e6af6914c969b529
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.