Martha Judge — Content & Marketing agent for Claude Code
Strict, independent evaluator for Martha's sales copy.
How to install Martha Judge
Installs to ~/.claude/agents/calebsamuel1026-blip-martha-martha-judge.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/calebsamuel1026-blip/martha/HEAD/agents/martha-judge.md -o ~/.claude/agents/calebsamuel1026-blip-martha-martha-judge.md Restart Claude Code, or start a new session, for it to be picked up.
What Martha Judge does
name: martha-judge description: Strict, independent evaluator for Martha's sales copy. Use only inside Martha's improvement cycle (IMPROVE.md) to score a blind judge pack. Scores with RUBRIC.md, applies the hard-rule auto-fails, and returns JSON only. Never writes, rewrites or suggests sales copy. tools: Read, Glob, Grep
You are martha-judge, a strict and independent grader. You do not write sales copy. You never rewrite a message or offer a better version. You score it, quote your evide
Alternatives in Content & Marketing
- Solopreneur — Solopreneur persona reviewer (32yo, freelancer/consultant) 587 ★
- Gate Judge — Parity-gate judge — a blind lane that assigns confidence tiers or verdicts from a fixture copy of pages, under 94 ★
- Content SEO — Produces public SEO content briefings, drafts, reviews, and promotion checks with hard decision/check gates 50 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Content Improvement Agent
Use this agent when you need to improve the quality, readability, and usability of content files such as docum
Mops Retro
The learning loop for a client marketing-operations account — the agent that makes the programme advance inste
Paid Traffic TikTok Ads
Use for any work inside TikTok Ads - structuring campaigns, Smart+, Spark Ads, TikTok Shop/GMV Max, native pla
Demo Validator Check
Runs the mechanical gates for the live-demo and workbench builds inside the worktree named in its prompt — the
Resume Evaluate
Independently scores the tailored resume content ( /.run/resume.json) against the quality rubric (.claude/skil
Content Saturation Simulator
Use this agent to simulate content saturation for a target audience, map what they're drowning in, score satur
Related Skills
Skill Review
Skill rubric: strict-improvement review of a candidate skill edit
Rubric Evaluator
Evaluate Claude Code and Codex skill directories with deterministic rubric checks and graded, fixable reports.
Evaluator Library
Dispatch a fresh-context evaluator against a domain rubric. Bundled domains: code-quality, ui-design, prose, s