agentleFS
Sign inStart free
OutThisLifeOutThisLife/brooklyn-skills/skills/draft-tweet/SKILL.md

draft-tweet

Skill207 starsChanged 4 months agoMITView on GitHub

Draft X/Twitter posts about shipped work. Never post unless asked. Use when the user wants tweet options or "what should I tweet".

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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
  1. Distinctive:

    Write tweet options. Do not post unless they explicitly say to.

    line 10
  2. Very specific:

    If xurl is installed and already authenticated, use it read-only to sample the user's recent original posts before drafting:

    line 14
  3. Very specific:

    If that version does not have xurl posts, use the user ID from xurl whoami:

    line 22
  4. Very specific:

    If xurl is missing or unauthenticated, draft from examples already in the conversation.

    line 32
  5. Very specific:

    Call xurl post, reply, quote, DM, or any other write API unless asked

    line 48
  6. Distinctive:

    Default to a thread — offer one only if they want depth

    line 50

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Draft Tweet

Write tweet options. Do not post unless they explicitly say to.

Match their voice

If xurl is installed and already authenticated, use it read-only to sample the user's recent original posts before drafting:

xurl whoami
xurl posts @handle -n 30

If that version does not have xurl posts, use the user ID from xurl whoami:

xurl '/2/users/<id>/tweets?max_results=30&exclude=retweets,replies'

Infer their usual capitalization, punctuation, sentence length, vocabulary, link use, and emoji use. Match the patterns, not the subject matter. Do not quote old posts or mention that style sampling happened.

If xurl is missing or unauthenticated, draft from examples already in the conversation. Do not block the task or ask them to configure X unless they specifically request stronger style matching.

Output

2–4 options, each roughly ≤240 chars:

  • Concrete claim or user benefit — no empty hype. For visual tools, lead with the visible effect or a playful, accurate description rather than a feature inventory.
  • When asked for an example image, look for prior PR/MR artifacts first. Inspect the actual image; a normal screenshot is not overlay evidence. If constructing a demo from it, visibly label deliberate offsets/edits and preserve source provenance. Never present the reconstruction as historical QA.
  • Little/no emoji; no engagement bait
  • One link max if useful
  • Run through no-tropes

Don't

  • Call xurl post, reply, quote, DM, or any other write API unless asked
  • Invent performance numbers they didn't bless
  • Default to a thread — offer one only if they want depth

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.

Check your setup, free