Works with the AI Agents you already use
Bilingual Content Gate
A pre-publish gate for blog and news HTML in one or two languages: headings, FAQ, links, banned phrases and TR/EN parity, checked by a script that never edits your content.
$9
Bilingual Content Gate
Example session with this skill installed
Run a pre-publish check on the folder ./content/batch-42 using the news profile to ensure TR and EN parity.
- Read your context and instructions
- Compiled the bilingual content gate
- Generated the document
The bilingual content gate has completed the audit of the ./content/batch-42 folder. Two errors were identified in the English version that prevent publishing.
Audit Report: batch-42
| Locale | File | Profile | Score | Status | Issues Found |
|---|---|---|---|---|---|
| TR | tr.html | News | 96 | Warning | 1 Warning: Missing keyword in first paragraph |
| EN | en.html | News | 70 | FAIL | 2 Errors: Missing sourceUrl, H1 detected in body |
Error Details
- Error (EN):
sourceUrlis mandatory for the news profile but was null or empty innotes.json. - Error (EN): Body HTML contains an
<h1>tag. Titles must be handled by the page template. - Warning (TR): Primary keyword "ekonomi" not found in the first 100 words.
- Parity Check: FAILED. EN version has 3 images; TR version has 2 images.
Next steps
- Remove the
<h1>tag fromen.htmland verify the title is set innotes.json. - Add the missing
sourceUrlto the English entry innotes.json. - Sync the image count between
tr.htmlanden.htmlto ensure visual parity.
tr.html
PDF · document
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop publishing broken posts
Most quality problems are boring and repeatable: a missing FAQ block, a stray <h1> in the body, a link to the wrong language, a banned phrase that slipped in, a Turkish post whose English twin drifted. Bilingual Content Gate catches them before anything goes live.
It is a zero-dependency Node script. Point it at a folder of HTML files, get a pass/fail report and an exit code (1 on errors) you can wire into any publish step. It never edits your content and never talks to a database.
What it checks
- Structure: title and meta length, valid slug, no
<h1>inside the body, heading order, FAQ section on blog posts - Links: internal links stay in the post's language, external links carry
rel="noopener", no "click here" link text, primary source linked on news notes - Style: bold abuse, banned phrases, relative dates ("yesterday") on news, paragraph length, word count per profile
- Safety: no
<script>,<iframe>or inline event handlers; every image has alt text - Parity: heading, link and FAQ counts and length compared between the two language versions, so translation drift shows up
How it works
- Put your HTML files and a small
notes.json(file, locale, slug, title, meta, keyword) in a folder - Run the check, read the report, fix, re-run
- Publish only when it exits 0
Rules and limits live in plain config (references/config.md) with two built-in profiles, blog and news, that you can adjust.
Good for
Agencies and in-house teams running a bilingual blog, news notes with mandatory sources, solo marketers who publish daily, and anyone who wants a deterministic last step before a CMS or database write.
Requirements: Node 18+. Works with Claude Code and any agent that follows the SKILL.md standard.
Requires Node.js environment. Only audits HTML/JSON files. Does not perform auto-corrections or translations. Only supports TR and EN locale validation.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 15 days ago
Requires