Skip to main content
PromptMetricsPromptMetrics
Book a free call
← All open source
PluginFork

Production-grade blog content, gated before you ever see it.

pm-blog is a Claude Code skill suite that writes, optimizes, and audits blog content at scale. Every article is dual-optimized for Google rankings (E-E-A-T) and AI citation platforms (ChatGPT, Perplexity, AI Overviews). A v1.9.0 5-gate delivery contract scores every draft against a 100-point rubric and blocks anything below 90 from reaching you.

PythonMITCowork · Claude Codegithub.com/promptmetrics/pm-blog
View on GitHubOpen an issue
Forked from AgriciDaniel/claude-blog by Daniel Agrici, MIT license. All credit for the engine goes to the upstream project. Star it there.
Install

Claude Code

Prefer the upstream public repo for the canonical release; our fork carries PromptMetrics-specific adjustments.

claude
# upstream (canonical, MIT)
> /plugin marketplace add AgriciDaniel/claude-blog
> /plugin install claude-blog@agricidaniel-claude-blog
# or our fork
> /plugin marketplace add promptmetrics/pm-blog
What you get
  • 30 sub-skills, 5 agents, 12 templates: research, outline, draft, schema, internal linking, fact-checking, and repurposing behind a single /blog surface.
  • 5-gate delivery contract: Capability, Format, Visual, Content Review, and Asset Integrity gates block drafts below 90/100; the writer iterates up to 3 times before escalating.
  • Dual optimization: Google E-E-A-T and JSON-LD schema on one side; answer-first formatting and citation capsules for AI platforms on the other.
  • Fact-checking pipeline: /blog factcheck fetches every cited source and scores claim confidence.
  • Broad platform support: Next.js MDX, Astro, Hugo, Jekyll, WordPress, Ghost, 11ty, Gatsby, and static HTML.
How it works

One orchestrator routes /blog commands through sub-skills, agents, and gates.

  1. 01

    Route

    /blog write, rewrite, analyze, brief, cluster: the orchestrator picks the sub-skills.

  2. 02

    Draft

    Research with sourced statistics, outline approval, then the full draft with schema and internal links.

  3. 03

    Gate

    Five gates run on every draft; the content review is blocking at 90/100 with zero P0 issues.

  4. 04

    Deliver

    Eight artifacts per post: .md, .html, .pdf, hero image, three viewport screenshots, review scorecard, preflight report.

Try it
/blog write <topic>Full article; the 5-gate contract runs automatically.
/blog analyze <file>Quality audit with a 0-100 score.
/blog factcheck <file>Verify every statistic against its cited source.
/blog multilingual <topic> --languages en,de,frWrite, translate, localize, and emit hreflang in one command.

Questions or issues? Open one on GitHub, or browse the rest of the catalog.

All open source