tune-anchors SKILL.md skillA

This file is byte-identical to the first copy the registry indexed, one of 5 indexed copies. Same content hash, so the same checks give both the same grade.

tune-anchors from petar-djukic/writing-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add petar-djukic/writing-skills/tune-anchors@git:20260812.fc1b88f

Pins git:20260812.fc1b88f in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
petar-djukic/writing-skills
Path
.agents/skills/tune-anchors/SKILL.md
Versions recorded
1
Latest version
git:20260812.fc1b88f, committed Aug 12, 2026
Size
7,353 bytes
Repository stars
5
License
MIT

Sweep anchor selections over a writing-voice corpus and report which tag query produces the best register outcome. Runs match-voice then tighten-style over (article × arm) combinations, ranks arms on the four-axis register composite, and optionally verifies the top candidates with an external detector. Triggers: tune anchors, sweep anchors, which anchors should I use, calibrate writing-voice, onboard corpus.

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

# tune-anchors

## The objective

Given a `writing-voice/` corpus and one or more target articles, answer:
**which anchor-selection rule produces rewrites closest to the author's own
register?**

A rule is an *arm* — a set of filters over the manifest: `role=venue-voice`,
`tags~clipped`, `pre_ai=true`. Different arms produce different anchor sets,
and the model copies the register of whatever it sees. The right arm is the
one whose anchors give the model a register worth copying.

## The pipeline

Each full trial runs two model passes before measurement:

1. **match-voice** (`drive.py`) — voice rewrite using the arm's anchors
2. **tighten-style** (`tighten.py`) — remove AI-register artifacts (passive
   stacks, nominalizations, filler) using the same model family shown
   transformation pairs, not rules
3. **measure** — register markers on the tightened output

The ranking reflects the final output quality, not the raw voice draft.
Tightening is what removes the AI sound; ranking without it would penalize
arms whose raw drafts carry fixable markers and reward arms whose markers
survive tightening unchanged.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add petar-djukic/writing-skills/tune-anchors@sha256:fe9180e2aba47457

The line at the top of this page pins the label git:20260812.fc1b88f, 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_l5vgjb4qqk5itrgi.svg)](https://markdownregistry.com/a/art_l5vgjb4qqk5itrgi)

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

Versions

The registry has recorded 1 version of this file, committed on Aug 12, 2026.

versioncommittedcommitsizeaudit
git:20260812.fc1b88f latest2026-08-12 fc1b88f 7,353 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 (7353 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

petar-djukic/writing-skills · 5 stars · license MIT · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_l5vgjb4qqk5itrgi
GET https://markdownregistry.com/api/v1/resolve?ref=petar-djukic/writing-skills/tune-anchors
GET https://markdownregistry.com/api/v1/blob/fe9180e2aba474573530c6d90f16817c3c9b376871ca1abbd3710dc904dbcf9f

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 petar-djukic/writing-skills

accent-dial SKILL.md skill
petar-djukic/writing-skills · .agents/skills/accent-dial/SKILL.md
git:20260901.e5cdb32 · audit C · 5 stars
audit-references SKILL.md skill
petar-djukic/writing-skills · .agents/skills/audit-references/SKILL.md · Verify citations in a paper or document. Reads a markdown document, extracts every [@citation-id] pandoc citation…
git:20260812.fc1b88f · audit A · 5 stars
bake-off SKILL.md skill
petar-djukic/writing-skills · .agents/skills/bake-off/SKILL.md
git:20260901.7dd2836 · audit C · 5 stars
cold-review SKILL.md skill
petar-djukic/writing-skills · .agents/skills/cold-review/SKILL.md
git:20260901.4f43034 · audit C · 5 stars
critic-apply SKILL.md skill
petar-djukic/writing-skills · .agents/skills/critic-apply/SKILL.md
git:20260901.f04b48c · audit C · 5 stars
critic-panel SKILL.md skill
petar-djukic/writing-skills · .agents/skills/critic-panel/SKILL.md
git:20261106.4b31e38 · audit C · 5 stars
filter-tells SKILL.md skill
petar-djukic/writing-skills · .agents/skills/filter-tells/SKILL.md · Detect and fix AI writing patterns recursively. Use when: reviewing text for AI tells, cleaning AI-generated drafts…
git:20260901.b53aa12 · audit A · 5 stars
humanize SKILL.md skill
petar-djukic/writing-skills · .agents/skills/humanize/SKILL.md · The laundering chain: one generative pass that moves AI-drafted prose toward human-passing on Pangram. Stages in order…
git:20260902.07c0a34 · audit A · 5 stars
inject-vernacular SKILL.md skill
petar-djukic/writing-skills · .agents/skills/inject-vernacular/SKILL.md
git:20260901.e5cdb32 · audit C · 5 stars
match-outline SKILL.md skill
petar-djukic/writing-skills · .agents/skills/match-outline/SKILL.md · Whole-document voice analysis: compare a draft against a corpus profile, extract voice persona blueprints from exemplar…
git:20260901.e5cdb32 · audit A · 5 stars
match-structure SKILL.md skill
petar-djukic/writing-skills · .agents/skills/match-structure/SKILL.md · Paragraph and sentence-level style metrics for a research corpus. Computes quantitative profiles (sentence/paragraph…
git:20260829.5edff40 · audit A · 5 stars
match-voice SKILL.md skill
petar-djukic/writing-skills · .agents/skills/match-voice/SKILL.md · Rewrite paragraphs of a draft in the author's voice using a second model family served by Ollama, with a verification…
git:20260904.2ed6e9f · audit A · 5 stars

Every file in petar-djukic/writing-skills

Other files named tune-anchors

tune-anchors SKILL.md skill
petar-djukic/writing-skills · .github/skills/tune-anchors/SKILL.md · Sweep anchor selections over a writing-voice corpus and report which tag query produces the best register outcome. Runs…
git:20260812.fc1b88f · audit A · 5 stars
tune-anchors SKILL.md skill
petar-djukic/writing-skills · .opencode/skills/tune-anchors/SKILL.md · Sweep anchor selections over a writing-voice corpus and report which tag query produces the best register outcome. Runs…
git:20260812.fc1b88f · audit A · 5 stars
tune-anchors SKILL.md skill
petar-djukic/writing-skills · .cursor/skills/tune-anchors/SKILL.md · Sweep anchor selections over a writing-voice corpus and report which tag query produces the best register outcome. Runs…
git:20260812.fc1b88f · audit A · 5 stars
tune-anchors SKILL.md skill
petar-djukic/writing-skills · .claude/skills/tune-anchors/SKILL.md · Sweep anchor selections over a writing-voice corpus and report which tag query produces the best register outcome. Runs…
git:20260729.a439653 · audit A · 5 stars

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