Run the scored pre-publish gate via eval-runner.py: claims, brand voice, compliance, AI tells. "check this before we publish".
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# /digital-marketing-pro:check — Unified Pre-Publish Quality Gate
> **Script location.** If your host does not set `${CLAUDE_PLUGIN_ROOT}`, the scripts are in this plugin's `scripts/` folder, next to `skills/`. Run them with Python 3.10 or newer: `python`, or `python3` where `python` is not found (macOS, many Linux systems).
This skill is the canonical pre-publish gate for marketing content. It wraps the evaluation suite (`scripts/eval-runner.py`) and produces a single pass/fail decision with actionable issues.
## Context efficiency
Heavy skill. **Grep before Read** any referenced file, then `Read` only matched ranges with `offset` + `limit`. List the brand's workspace at `~/.claude-marketing/brands/{slug}/` (or `$CLAUDE_PLUGIN_DATA/digital-marketing-pro/brands/{slug}/` when that env var is set) before opening files. On re-invocation mid-session, skip files already in context.
Use this skill **before publishing any marketing content** — blog posts, ad copy, emails, social posts, landing pages, press releases, or any branded copy.
## Why this skill exists
…
The line at the top of this page pins the label git:20261011.1a0c374, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_ey7y72cgbbhlv2yo
GET https://markdownregistry.com/api/v1/resolve?ref=indranilbanerjee/neels-plugins/check
GET https://markdownregistry.com/api/v1/blob/756a77512430e28e0d2e38f6689cda56cdf890948963bfe044e48bd8b72737c3
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
indranilbanerjee/neels-plugins · hermes/digital-marketing-pro/content/skills/batch-process/SKILL.md · Batch-produce many content pieces as one resumable queue, highest priority first. "write these 15 posts"
indranilbanerjee/neels-plugins · hermes/digital-marketing-pro/content/skills/cf-add-integration/SKILL.md · Add a custom MCP connector for any external API or service. "hook up our internal CMS"
indranilbanerjee/neels-plugins · hermes/digital-marketing-pro/content/skills/cf-aeo-check/SKILL.md · Re-check a published piece's AEO: cited in AI Overviews and AI answers, tracked over time. "did AI cite our article"
indranilbanerjee/neels-plugins · hermes/digital-marketing-pro/content/skills/cf-analytics/SKILL.md · Show content analytics: quality-score trends, slowest pipeline phase and alerts over 7-90 days. "how is production…
indranilbanerjee/neels-plugins · hermes/digital-marketing-pro/content/skills/cf-audit/SKILL.md · Audit a content library for stale posts and topic gaps; ranks what to refresh or retire. "which posts need refreshing"
indranilbanerjee/neels-plugins · hermes/digital-marketing-pro/content/skills/cf-brief/SKILL.md · Write a research-backed content brief from a keyword or topic: intent, competitors, outline. "brief me on this topic"
indranilbanerjee/neels-plugins · hermes/digital-marketing-pro/content/skills/cf-calendar/SKILL.md · Build a 30/60/90-day content calendar with production windows, owners and conflicts. "plan next quarter's content"
indranilbanerjee/neels-plugins · hermes/digital-marketing-pro/content/skills/cf-cowork-setup/SKILL.md · One-time setup for team use in Cowork: shared Drive folders and routing. "set up ContentForge for our team"
indranilbanerjee/neels-plugins · hermes/digital-marketing-pro/content/skills/cf-environment/SKILL.md · Detect the runtime environment (Cowork or local) and what works there: connectors, file locations, limits. "am I…
indranilbanerjee/neels-plugins · hermes/digital-marketing-pro/content/skills/cf-help/SKILL.md · Show help for ContentForge: live version, skills, examples and troubleshooting. "how do I use ContentForge"
indranilbanerjee/neels-plugins · hermes/digital-marketing-pro/content/skills/cf-integrations/SKILL.md · Show which MCP integrations are connected versus available, with quick wins. "what integrations are connected"
davepoon/buildwithclaude · plugins/ciagent/skills/check/SKILL.md · Run CIAgent regression checks after changing an AI agent's code, prompts, or knowledge base in a repo that has…
vibiumdev/vibium · skills/check/SKILL.md · Independently check application acceptance criteria in a live browser or saved recording with the Vibium CLI. Use for a…
indranilbanerjee/digital-marketing-pro · skills/check/SKILL.md · Run the unified pre-publish quality gate on marketing content — wraps scripts/eval-runner.py to score hallucination…
escoffier-labs/brigade · registry/skills/check/SKILL.md · Use when about to claim anything works, is fixed, is complete, or passes - before committing, replying to the user, or…
junjiezhou1122/ideascientist-claude-code · skills/check/SKILL.md · Run the standalone offline validator for a native IdeaScientist run's artifacts, evidence receipts and stage…
camoa/claude-skills · claude-plugin-checks/skills/check/SKILL.md · Run every available check against a Claude Code plugin — the first-party validator, plugin-dev's linters, and three…