li-preflight
Skill1 starsChanged 5 days agoMITView on GitHub
Run every check in the pack on one LinkedIn draft - length and the "see more" fold, links, hashtags, bait, walls of text, 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, comment, invite note, headline or about section goes out, or when the user says "check this", "is this ready", "preflight", or "can I post this".
In this repository16 other files it gives its agents.
- li-auditSkill
- li-carouselSkill
- li-commentSkill
- li-dmSkill
- li-engageSkill
- li-humanSkill
- li-inboxSkill
- li-jobsearchSkill
- li-newsletterSkill
- li-planSkill
- li-postSkill
- li-profileSkill
- li-publishSkill
- li-replySkill
- li-repurposeSkill
- li-voiceSkill
The file
Files
li-preflight
The pack has a counter, a humanizer panel and a voice check, and the one that gets skipped is the one that would have caught it. This runs all three on the same text and gives one answer.
python3 preflight.py draft.txt # a post
python3 preflight.py comment.txt --kind comment
python3 preflight.py note.txt --kind invite
python3 preflight.py headline.txt --kind headline| stage | tool | fails when |
| COUNT | ../li-post/count.py | over the limit for that surface |
| HUMAN | ../li-human/detect.py | the five-check panel says FLAGGED |
| VOICE | ../li-voice/voice.py | the draft drifted from the user's measured voice (only when ~/.claude/linkedin/voice.json exists) |
Warnings do not block. They are listed under the verdict in the order to fix them.
Order of operations
- Draft with the right skill (
/li-post,/li-comment,/li-dm,/li-profile). humanize.pyfrom/li-human, then rewrite the flagged lines by hand.preflight.pyon the result.- FIX FIRST: fix item 1, run it again. READY: show the user the text, then the pre-flight table. Never the table alone.
What READY does not mean
It means nothing mechanical is wrong. It does not mean the post is good, and it is not a prediction of reach. A READY post with nothing true in it is still a post with nothing true in it.
Nothing is posted by this skill. The user pastes the text into LinkedIn.
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.

