Linkedin content validation

Skill ArthurZakirov/ProofStack/skills/linkedin_content_validation

Use when drafting, saving, formatting, validating, or repairing LinkedIn profile and content assets in this repository, including headlines, About sections, Experience descriptions, project copy, posts, articles, and LinkedIn image specs.From its SKILL.md

Install

npx -y skills add ArthurZakirov/ProofStack --skill linkedin_content_validation

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.7 KB, 339 tokens by cl100k_base, as published. Nobody here has run it

LinkedIn Content Validation

Use this skill after any LinkedIn/profile-content drafting skill produces copy or visual specs.

Workflow

Save generated text under content/ as Markdown with YAML frontmatter.
Save generated image specs under content/ or assets/ as YAML.
Run the formatter.
Run the validator.
If validation fails, repair the draft using the exact machine-readable error.
Repeat until validation passes.

Markdown Contract

Every LinkedIn Markdown file must use frontmatter:

---
platform: linkedin
section: about
---

Text body here.

Supported section values:

profile_headline
about
experience_description
project_title
project_description
post
comment
article_title
article_body

Commands

python3 scripts/format_linkedin_text.py --write content
python3 scripts/format_linkedin_text.py --check content
python3 scripts/validate_linkedin_assets.py content
python3 scripts/validate_linkedin_assets.py content --config config/linkedin_limits.yaml

Repair Priorities

Preserve:

quantified hook
reader benefit
proof metrics
mechanism/framework
CTA

Remove first:

filler words
repeated qualifiers
duplicated concepts
excessive internal details
weak adjectives
redundant setup

Do not remove blank lines just to fit a character limit. If count_mode is non_newline_unicode_codepoints, shorten actual words instead.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.