evaluate-ghostwriter SKILL.md skillA
evaluate-ghostwriter from mblode/ghostwriter is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add mblode/ghostwriter/evaluate-ghostwriter@git:20260723.3a778baPins git:20260723.3a778ba in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- mblode/ghostwriter
- Path
skills/evaluate-ghostwriter/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260723.3a778ba, committed Jul 23, 2026
- First version recorded
- Jul 23, 2026
- Size
- 7,729 bytes
- Repository stars
- 7
- License
- MIT
Runs blind, human-labeled baseline-versus-profile evaluations through a locally authenticated Codex or Claude Code CLI. Measures whether the exact ghostwriter skill and private platform profiles improve resemblance to held-out writing. Use when asked to "evaluate my voice", "test my voice profile", compare writing with and without the ghostwriter skill, review blind A/B candidates, or report voice evaluation results. Use train-ghostwriter to create the profiles and held-out cases this measures.
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
# Evaluate ghostwriter Measure a fixed runtime skill and fixed private profiles against real held-out writing. - **IS:** clean candidate generation, deterministic blinding, human review, and descriptive reporting. - **IS NOT:** training profiles, modifying corpora, grading with another model, or exposing the treatment before a human choice. Use `train-ghostwriter` to create profiles and held-out cases. The scripts execute the deterministic parts of this workflow. Do not reproduce their logic manually. `scripts/run-eval.ts` generates candidates without opening references. `scripts/review-eval.ts` joins references only after generation and records human choices. The scripts use [assets/candidate-output.schema.json](assets/candidate-output.schema.json) for structured runner output; do not edit it per run. Both branches of a pair get the same CLI, model, case bytes, and output contract in fresh non-persistent sessions. The treatment alone also receives the complete runtime `SKILL.md` and platform profile, encoded losslessly as JSON strings. Never summarize or selectively copy either file; `manifest.json` pins hashes of their original bytes. …
Read the whole file at its exact version.
How to install
mdr add mblode/ghostwriter/evaluate-ghostwriter@sha256:1c8b0cfb0c81bff7The line at the top of this page pins the label git:20260723.3a778ba, 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.
[](https://markdownregistry.com/a/art_kenss3qpitybftfj)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, all committed on Jul 23, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260723.3a778ba latest | 2026-07-23 | 3a778ba | 7,729 B | A | view · diff |
| git:20260723.c849372 | 2026-07-23 | c849372 | 7,453 B | A | view · diff |
| git:20260723.808ce8a | 2026-07-23 | 808ce8a | 6,896 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7729 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
mblode/ghostwriter · 7 stars · license MIT · pushed 2026-09-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_kenss3qpitybftfj GET https://markdownregistry.com/api/v1/resolve?ref=mblode/ghostwriter/evaluate-ghostwriter GET https://markdownregistry.com/api/v1/blob/1c8b0cfb0c81bff7397357f6ae5e2cbd684617d8b70152cd47c46019955cec51
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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.