All skills

Turn one long asset - a YouTube video, podcast, newsletter, blog post, transcript or client call - into a week of LinkedIn posts. Use when the user says "repurpose this", "turn this into posts", "I have a video/newsletter/ transcript", or pastes a long piece of content and wants it on LinkedIn.

Use this Skill: https://skilld.dev/gh/jakeschincariol/linkedin-agent-skill/li-repurpose

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈77 tokens for metadata: the name and description. ≈593 when used: this file.

Description uses 3.9% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈310 characters, or 3.9%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

li-repurpose

One good long asset contains four to six posts. Most people extract one and throw the rest away.

Input

A transcript, an article, a newsletter, a script, a call summary. If the user gives a YouTube URL and there is a transcript tool available in the session, use it; otherwise ask them to paste the text. Read the whole thing before extracting anything.

Extract, do not summarise

A summary of a video is not a post. Nobody wants the summary. Go through the asset and pull out the things that stand alone:

pull what it is
Claims every sentence that would start an argument
Numbers every figure, cost, duration, percentage
Stories every moment with a person, a scene and a cost
Mechanisms every "the way this works is..." explanation
Mistakes every admission of something that went wrong
Lines every sentence that is already quotable as-is

List what you found, with counts, before writing anything. If the asset yields fewer than four items, it is thin, and four posts squeezed out of it will be thin too. Say that.

Then build the week

Each extract becomes one post, and each post has to stand completely on its own - the reader has not seen the video and never will. Never write "as I mentioned in my latest video". The post is the thing.

Assign a hook formula from li-post/hooks.json to each, and vary them: five posts from one source with the same hook shape reads as a content mill.

Order them across the week so the strongest claim goes first, the story goes midweek, and the mechanism post goes last, when people who liked the earlier ones are watching for it.

Output

SOURCE: "Why we killed discovery calls" (18 min, 3,400 words)

FOUND  4 claims, 6 numbers, 2 stories, 3 mechanisms, 1 mistake, 5 quotable lines

WEEK
TUE  #1  Contrarian    Discovery calls are a tax you pay for a bad website
WED  #17 Time Anchor   We got 6 hours a week back by deleting one calendar link
THU  #9  Cold Open     "Can we just hop on a quick call?"
FRI  #21 Direct Value  The 4-question form that replaced the call. Steal it.

Say "write Tuesday" and I will draft it.

Then draft on request, one at a time, each through /li-post and /li-human. Do not dump four finished posts at once - they will all sound the same, and the user will edit none of them.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts29d3 checks · Risk SAFE
  • Gen Agent Trust Hub29d

    This skill is used for repurposing long-form content into LinkedIn posts. It is functionally safe, though it processes external content which presents a minor risk of indirect prompt injection if the source material contains malicious instructions.

  • Socket29d

    No alerts

  • Snyk29d

    Risk: LOW · No issues

Signed by skilld at add2c23. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 44 minutes ago.

Activeupdated last month

README badge

README badge for jakeschincariol/linkedin-agent-skill/li-repurpose