mcpField
L
linkedin-content-validation

linkedin-content-validation

github.com/arthurzakirovMarketing & growth0166 installsUpdated 4w ago
Repository

About linkedin-content-validation

linkedin-content-validation is a skill for checking and repairing drafted LinkedIn text and visual specifications. It applies formatting and asset rules, then guides revisions from machine-readable validation errors.

Key features

  1. 01Format LinkedIn Markdown
  2. 02Validate LinkedIn assets
  3. 03Enforce section frontmatter
  4. 04Repair drafts from errors

Use cases

  1. 01Check a drafted LinkedIn post
  2. 02Validate profile copy and image specs

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/arthurzakirov/proofstack --skill linkedin-content-validation

After installing, type/linkedin-content-validationin Claude Code to confirm it loaded.

Details

From the project README

LinkedIn Content Validation

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

Workflow

  1. Save generated text under content/ as Markdown with YAML frontmatter.
  2. Save generated image specs under content/ or assets/ as YAML.
  3. Run the formatter.
  4. Run the validator.
  5. If validation fails, repair the draft using the exact machine-readable error.
  6. 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:

  1. quantified hook
  2. reader benefit
  3. proof metrics
  4. mechanism/framework
  5. CTA

Remove first:

  1. filler words
  2. repeated qualifiers
  3. duplicated concepts
  4. excessive internal details
  5. weak adjectives
  6. 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.

Comments

Markdown supported