x-preflight
Skill1 starsChanged 5 days agoMITView on GitHub
Run every check in the pack on one X draft - X's weighted character count, links, hashtags and bait, the hook score on line 1, the five-check humanizer panel, and drift from the user's measured voice - and return one READY or FIX FIRST verdict with the fixes in order. Use before any post or reply goes out, or when the user says "check this", "is this ready", "preflight", "can I post this".
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 39
Never the table alone.
≈ “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
x-preflight
Four tools, one answer. The check that gets skipped is the one that would have caught it, so this runs all of them on the same text.
python3 preflight.py draft.txt
python3 preflight.py draft.txt --premium # long post: 25,000, fold at 280
python3 preflight.py reply.txt --kind reply # no hook stage| stage | tool | fails when |
| COUNT | ../x-post/count.py | over the weighted limit |
| HOOK | ../x-post/hookscore.py | line 1 scores under 50 (posts only) |
| HUMAN | ../x-human/detect.py | the panel says FLAGGED |
| VOICE | ../x-voice/voice.py | the draft drifted from the measured voice (only when ~/.claude/x/voice.json exists) |
Warnings do not block; they are listed in the order to fix them.
Order of operations
- Draft with
/x-post,/x-thread(run each post),/x-commentor/x-reply. humanize.pyfrom/x-human, then rewrite the flagged lines by hand.preflight.pyon the result.- FIX FIRST: fix item 1, run it again. READY: show the text, then the table. Never the table alone.
What READY does not mean
Nothing mechanical is wrong. It is not a reach prediction: hookscore.py
is a lint, and the README says what it can and cannot separate. A READY post
with nothing true in it is still empty.
Nothing is posted by this skill.
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.

