paper-to-social
Skill36 starsChanged 2 months agoMITView on GitHub
Creates Telegram, X, or Habr posts from a research paper using verified figures and the user's writing style. Use when the user asks to write a post about a paper, announce a publication, promote a result on Telegram or Twitter, or draft a Habr article.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Vepricov/claude-brainlabword for word, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 1
- Vepricov/claude-brainlab★ 35100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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 repository68 other files it gives its agents.
- rules/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- academic-plottingSkill
- agent-identifierSkill
- architecture-designSkill
- astar-paper-reviewSkill
- bug-detectiveSkill
- call-notesSkill
- cavemanSkill
- citation-verificationSkill
- code-ingestSkill
- code-librarySkill
- code-review-excellenceSkill
- command-developmentSkill
- create-projectSkill
- daily-codingSkill
- defuddleSkill
- diagnoseSkill
- doc-coauthoringSkill
- experiment-runsSkill
- frontend-designSkill
- git-guardrails-claude-codeSkill
- git-workflowSkill
- google-workspace-mcpSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- handoff-to-jarvisSkill
- hook-developmentSkill
- improve-codebase-architectureSkill
- json-canvasSkill
- kaggle-learnerSkill
- lab-knowledgeSkill
- latex-conference-template-organizerSkill
- mcp-integrationSkill
- ml-paper-writingSkill
- obsidian-basesSkill
- obsidian-cliSkill
- obsidian-experiment-logSkill
- obsidian-markdownSkill
- operon-obsidian-setupSkill
- paper-ingestSkill
- paper-searchSkill
- paper-venue-formattingSkill
- pdf-readerSkill
- planning-with-filesSkill
- plugin-structureSkill
- presentationSkill
- presenter-modeSkill
- prototypeSkill
- research-cycleSkill
- research-ideationSkill
- restore-sessionSkill
- results-analysisSkill
- results-reportSkill
- reverse-outline-flow-checkSkill
- review-responseSkill
- setup-pre-commitSkill
- skill-developmentSkill
- tddSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Read references/voice-and-anti-ai.md in full before writing anything.
- Very specific: line 15
Never look like AI: Always run the writing-anti-ai skill over every post before finishing.
- Distinctive: line 47
Do not overclaim beyond the paper.
≈ “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.
Files
Paper → social posts (Telegram · Twitter/X · Habr)
Turn a paper into promo posts that real researchers want to read and share. One job, three active target platforms. The user may ask for one platform or all of them. Default output: one Obsidian markdown note per requested platform in the project's folder, copy-paste-ready, with figures, in the user's voice.
LinkedIn is paused (user request, 2026-06-26). Do not generate LinkedIn posts unless the user explicitly asks again. The
references/linkedin.mdplaybook andexamples/linkedin-template.mdare kept for when it is re-enabled.
Hard rules (the user has said these many times — never make them repeat)
Read references/voice-and-anti-ai.md in full before writing anything. The non-negotiables:
- Never look like AI. Always run the
writing-anti-aiskill over every post before finishing. No em dashes, no semicolons in the prose, no hype vocabulary, no "In this work we…", no negative parallelism, no empty windups. - Accessible but precise. A smart reader should understand what the paper does and want to keep reading. Plain words first, then the name. Concrete exact numbers over adjectives.
- Never invent results, arXiv links, GitHub links, conference acceptances, or @handles. Verify each; leave a clear placeholder if you cannot.
- Never invent personal content. Professional feelings, what worked / what didn't, who to tag, behind-the-scenes story: if you don't know it, ASK the user, do not make it up. (This is a standing rule the user stated explicitly.) Documented process notes the user points you to (e.g. an "how we did it" note) are fair to summarize faithfully.
- Use the BRAIn Lab brand for all visuals — palette and logo in
references/brand.md(berry/apricot/cream/blue + the real graph-node logo). Never the old purple/lavender scheme, never a placeholder logo. - Figures come from the arXiv/published version, extracted cleanly. See
references/images.md. - Route output into the work itself:
${OBSIDIAN_VAULT}/<направление>/<тема>/<работа>/socials/. The path is visible from the path; there is no mapping file any more.
Workflow
- Get the paper.
git pullthe Overleaf/local source if present and readmain.tex(abstract, intro/contributions, method, experiments/tables, conclusion). Prefer.texover PDF. Also note the arXiv id, code URL, and conference acceptance if any. - Extract the core once (reused across platforms): the one-sentence idea, the problem it fixes, the mechanism, the headline numbers (exact), the theory in one breath, the "free to adopt" angle, and the live debate it plugs into.
- Pull figures from the arXiv version into
<направление>/<тема>/<работа>/socials/<platform>-assets/(or a sharedsocials/social-assets/). Seereferences/images.md. View every render before describing it. - Write each requested platform using its reference file. Match the user's voice from the examples, not a generic template.
- Telegram →
references/telegram.md(examples:telegram-wlora.md,telegram-kawasaki.md,telegram-markovian.md) - Twitter/X →
references/twitter.md(example:twitter-softsign-thread.md) - Habr →
references/habr.md(example:habr-template.md) - LinkedIn → paused. Skip unless explicitly asked. (
references/linkedin.md,examples/linkedin-template.md)
- Telegram →
- Run
writing-anti-aiover the result and fix every flagged pattern. - Verify mechanics: tweet char counts ≤280, every handle resolves, every image marker maps to a real file, links present (or placeholdered).
- Report the file path(s) and flag every placeholder the user must fill (arXiv link, coauthor handles, unconfirmed handles).
What changes per platform (one-line map)
- Telegram — conversational Russian, emoji section headers, concrete numbers, a closing insight, "Принято в
<venue>", 🔗 Статья / 💻 Код. Always ship a "Карточки" carousel. Theory-heavy paper: theorem screenshots go in the comments (one-line caption each), referenced from the body. - Twitter/X — English thread, dense tweets near 280, theory gets 2–3 tweets, marquee method in tweet 1, tags only in a separate shout-out post, an image on most tweets.
- LinkedIn — paused (user request). When re-enabled: the Telegram post's substance as professional English prose, roughly TG length (4–6 short paragraphs), light on emoji, 3–5 hashtags, always with a visual (one figure or a carousel/document built from the TG cards).
- Habr — a real connected-prose article in Russian (not bullets), sections, formulas in LaTeX (Habr renders them), the place to expand the theory in depth, several figures, practical framing, the longest version.
Boundaries
- This skill drafts. The user posts. Do not post anything.
- Do not overclaim beyond the paper. Keep numbers exact (no rounding away, no "≈").
- One post per platform per request unless asked for variants.
Resources
references/voice-and-anti-ai.md— shared voice + the full anti-AI checklist + accumulated user preferences. Read first.references/telegram.md,references/twitter.md,references/linkedin.md,references/habr.md— per-platform playbooks.references/images.md— pulling clean figures/cover/theorem images from the arXiv PDF and the arXiv abstract page, plus the carousel/document build recipe.references/brand.md— BRAIn Lab palette + logo (assets/), for all carousels and visuals.examples/— real posts (gold standard): three Telegram, one Twitter thread, plus LinkedIn and Habr templates.
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.

