indranilbanerjee/digital-marketing-pro · skills/eval-suite/SKILL.md

eval-suite skillA

eval-suite is agent-read markdown (skill) from indranilbanerjee/digital-marketing-pro: Batch-evaluate a whole set of content pieces — files, a directory, or pasted blocks — in one run, producing a ranked portfolio quality report: grade distribution, per-dimension averages, systemic issues, a prioritized revision list, and auto-rejects below threshold. Triggers on "/digital-marketing-pro:eval-suite", "score our whole content library", "quality-check all campaign assets before launch", "evaluate these 5 drafts together", "which deliverables are weakest". Runs eval-runner.py per item.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add indranilbanerjee/digital-marketing-pro/eval-suite@git:20260812.b624042
Exact content
mdr add indranilbanerjee/digital-marketing-pro/eval-suite@sha256:396cef45e9b1d918

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_nuabz3aj3est3cew.svg)](https://markdownregistry.com/a/art_nuabz3aj3est3cew)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260812.b624042 latest2026-08-12 b624042 9,137 BA view · diff
git:20260709.294ff622026-07-09 294ff62 8,611 BA view · diff
git:20260508.d4086892026-05-08 d408689 8,320 BA view · diff
git:20260330.6a584192026-03-30 6a58419 8,282 BA view · diff
git:20260224.b1de39f2026-02-24 b1de39f 8,373 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (9137 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

indranilbanerjee/digital-marketing-pro · 823 stars · license MIT · pushed 2026-09-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_nuabz3aj3est3cew
GET https://markdownregistry.com/api/v1/resolve?ref=indranilbanerjee/digital-marketing-pro/eval-suite
GET https://markdownregistry.com/api/v1/blob/396cef45e9b1d918d2ca0706fd979c9caffc945b48f74813eb3a322f757d109d

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.