content-voice-revision SKILL.md skillA

content-voice-revision from sean-m-cooper/ai_tools is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add sean-m-cooper/ai_tools/content-voice-revision@git:20260729.31ea116

Pins git:20260729.31ea116 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
sean-m-cooper/ai_tools
Path
skills/content-voice-revision/SKILL.md
Versions recorded
1
Latest version
git:20260729.31ea116, committed Jul 29, 2026
Size
4,694 bytes
Repository stars
11
License
a license file GitHub does not identify

Revise selected blog posts, newsletters, and thought-leadership content using findings from a content audit. Use when asked to fix named essays, improve the lowest-scoring content, reduce AI-sounding cadence, add evidence or receipts, or strengthen an argument without changing the author's voice. Work conversationally with the author to solicit missing evidence, nuance, and lived experience before substantive rewrites.

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

# Content Voice Revision

Improve selected content through an editor-author conversation. Use an existing content audit as input when one is available. Do not widen the scope beyond the pieces the user named.

## Before Editing

1. Read the target repository's writing instructions, brand guidance, and anonymization rules. Then read `author-style-guide.md` from the repository root when it exists. Apply this precedence: repository rules, the author guide, the source piece's established conventions, then `references/default-content-guidelines.md`.
2. Read each complete target piece and its audit findings before editing.
3. Identify the real issue. A low score can be a false positive, and a strong line may deserve to remain isolated.
4. Separate expression problems from substance problems:
   - **Expression:** cadence, paragraph shape, repetition, structure, clarity, or phrasing. These can be revised directly.
   - **Substance:** a missing anecdote, measurement, counterargument, decision rationale, consequence, or source. These require author input.
5. Never invent a receipt, anecdote, number, outcome, source claim, or emotional motive.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add sean-m-cooper/ai_tools/content-voice-revision@sha256:672d12d7011d7589

The line at the top of this page pins the label git:20260729.31ea116, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_skn6jtv42petcjpw.svg)](https://markdownregistry.com/a/art_skn6jtv42petcjpw)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jul 29, 2026.

versioncommittedcommitsizeaudit
git:20260729.31ea116 latest2026-07-29 31ea116 4,694 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the 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 (4694 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

sean-m-cooper/ai_tools · 11 stars · license a license file GitHub does not identify · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_skn6jtv42petcjpw
GET https://markdownregistry.com/api/v1/resolve?ref=sean-m-cooper/ai_tools/content-voice-revision
GET https://markdownregistry.com/api/v1/blob/672d12d7011d7589943057a27cacefe6557eba25e36f916ef7ca35a756f05301

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.

More from sean-m-cooper/ai_tools

audit-writing-architecture SKILL.md skill
sean-m-cooper/ai_tools · skills/audit-writing-architecture/SKILL.md · Audit technical and professional nonfiction with SOLID, DRY, YAGNI, paragraph contracts, and refactoring practices. Use…
git:20260812.29fd01e · audit A · 11 stars
author-style-guide SKILL.md skill
sean-m-cooper/ai_tools · skills/author-style-guide/SKILL.md · Analyze an author's real writing samples, interview them about observed patterns and intended positioning, and create…
git:20260729.31ea116 · audit A · 11 stars
code-map SKILL.md skill
sean-m-cooper/ai_tools · skills/code-map/SKILL.md · Generate an AI-optimized YAML code map (.codemap.yaml) at the repository root. The map captures project structure, API…
git:20260402.7705868 · audit A · 11 stars
cold-start-audit SKILL.md skill
sean-m-cooper/ai_tools · skills/cold-start-audit/SKILL.md · Audit a standalone artifact for context its intended reader, operator, or AI collaborator needs but was never given…
git:20260816.8fcb5e8 · audit A · 11 stars
content-voice-audit SKILL.md skill
sean-m-cooper/ai_tools · skills/content-voice-audit/SKILL.md · Run a read-only heuristic audit of Markdown blog posts, newsletters, essays, and thought-leadership content for…
git:20260821.ec66e3a · audit A · 11 stars
feature-writer SKILL.md skill
sean-m-cooper/ai_tools · skills/feature-writer/SKILL.md · Guide a product owner through defining a feature — UI, backend, or full-stack. Conducts a structured interview that…
git:20260524.ed40828 · audit A · 11 stars
root-cause SKILL.md skill
sean-m-cooper/ai_tools · skills/root-cause/SKILL.md · Systematically analyze bugs, failures, or unexpected behavior to identify root causes. Examines code, data…
git:20260407.7b9ec8a · audit A · 11 stars
security-audit SKILL.md skill
sean-m-cooper/ai_tools · skills/security-audit/SKILL.md · Use this skill when performing a security review of a codebase, app, or system design. Triggers include pre-launch…
git:20260422.8727f12 · audit A · 11 stars
story-prefinement SKILL.md skill
sean-m-cooper/ai_tools · skills/story-prefinement/SKILL.md · Use when asked to evaluate, review, or score a story or bug for quality, readiness, or completeness - especially when a…
git:20260524.e7c16fb · audit A · 11 stars
story-splitter SKILL.md skill
sean-m-cooper/ai_tools · skills/story-splitter/SKILL.md · Break a Feature into individual stories — one per user action, CRUD operation, or backend operation — and create each…
git:20260524.ed40828 · audit A · 11 stars
story-writer SKILL.md skill
sean-m-cooper/ai_tools · skills/story-writer/SKILL.md · Use when a product manager or product owner wants to create a new story, bug, or task - guides them interactively…
git:20260524.e7c16fb · audit A · 11 stars

Every file in sean-m-cooper/ai_tools

Browse by kind, by grade A, or by owner.