remove-ai-marks SKILL.md skillB

The newest version of a file that held these bytes earlier

remove-ai-marks in guillaumemeyer/watermarks-remover is at git:20261002.43107e4 (Oct 2, 2026), graded B.

mdr add guillaumemeyer/watermarks-remover/remove-ai-marks@git:20261002.43107e4

This copy is 1 version behind it. See what changed · install this older copy instead

This line moves to the next version by itself within about an hour of that file saving one. A copy already installed stays as it is until you update it.

remove-ai-marks from kulykivska/claude-plugins is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
kulykivska/claude-plugins
Path
content/skills/remove-ai-marks/SKILL.md
Versions recorded
1
Latest version
git:20260916.804d5bd, committed Sep 16, 2026
Size
19,113 bytes
Repository stars
6
License
MIT

Remove multi-vendor AI provenance marks: invisible Unicode (Layer A), statistical text watermarks via rewrite (Layer B, always offer), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD/TEX. Covers Claude, Gemini/SynthID-class, OpenAI provenance, and open-LLM sampling marks. Use when the user asks to strip watermarks, remove C2PA/Content Credentials, clean AI metadata, remove invisible Unicode, anti-detect clean AI output, or runs /remove-ai-marks…

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

# Remove AI marks

Multi-vendor anti-detection hygiene for **text** (Unicode + statistical rewrite) and **files** (C2PA / AI metadata across common containers).

Read if needed:

- `references/mark-classes.md` — Unicode / sampling / C2PA / containers
- `references/vendor-notes.md` — Claude, Gemini/SynthID, OpenAI, open-LLM
- `references/removal-matrix.md` — which layer when
- `references/ethics.md` — intended use
- `references/how-claude-marks.md` — Anthropic-specific detail
- `references/markdiffusion.md` — optional MarkDiffusion image harness (schemes, honesty caveats)

This skill is a **thin client**. All deterministic cleaning machinery runs in a
separate HTTP service (this repo's `service/`), so the agent host needs no
Python, venvs, or cleaning tools. Call the service with `curl`; never run
cleaning scripts directly.

## Service access

Base URL comes from `WATERMARKS_SERVICE_URL`, default `http://127.0.0.1:8765`:

```bash
WM="${WATERMARKS_SERVICE_URL:-http://127.0.0.1:8765}"
```

The service is started either by the operator (`docker compose up -d`, or a
published GHCR image) or locally (`make serve`). **Always check it first**, and
…

Read the whole file at its exact version.

How to install

This older copy, pinned
mdr add kulykivska/claude-plugins/remove-ai-marks@git:20260916.804d5bd

Pins git:20260916.804d5bd in mdr.lock, 1 version behind the newest at the top of this page.

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_njkea5t63r3frd5u/bef308cdeffc8bcaf91be5a3e7b72ff9a79544b72010a73d483210a9ba020f08.json

Then /plugin install remove-ai-marks@markdownregistry-njkea5t63r3frd5u in Claude Code. It installs git:20260916.804d5bd, the one graded B here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add kulykivska/claude-plugins/remove-ai-marks@sha256:bef308cdeffc8bca

The older copy line above pins the label git:20260916.804d5bd, 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_njkea5t63r3frd5u.svg)](https://markdownregistry.com/a/art_njkea5t63r3frd5u)

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

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: get me the newest guillaumemeyer/watermarks-remover/remove-ai-marks, and what changed since bef308c? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of remove-ai-marks from somewhere else? Ask it: where did my remove-ai-marks come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Sep 16, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260916.804d5bd latest2026-09-16 804d5bd 19,113 BB view

Copies

The newest version, then this copy

Newest: git:20261002.43107e4 of remove-ai-marks in guillaumemeyer/watermarks-remover (skills/remove-ai-marks/SKILL.md), graded B.

This copy: byte for byte that file's version git:20260909.e2a699b, which it committed on Sep 9, 2026, before this repository did; graded B, 1 version behind.

See what changed since these bytes · ask your agent

Matched on the exact bytes and the commit dates, nothing else. It does not say who wrote the file or where this repository got it.

Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No link to a raw IP address (matched: http://127.0.0.1:8765)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (19113 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 script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

kulykivska/claude-plugins · 6 stars · license MIT · pushed 2026-11-13 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_njkea5t63r3frd5u
GET https://markdownregistry.com/api/v1/resolve?ref=kulykivska/claude-plugins/remove-ai-marks
GET https://markdownregistry.com/api/v1/blob/bef308cdeffc8bcaf91be5a3e7b72ff9a79544b72010a73d483210a9ba020f08

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 kulykivska/claude-plugins

app-factory SKILL.md skill
kulykivska/claude-plugins · app-factory/skills/app-factory/SKILL.md · Take an app idea from one spoken sentence to a submitted App Store build. Runs the whole pipeline with subagents…
git:20261104.4063c88 · audit A · 6 stars
humanizer SKILL.md skill
kulykivska/claude-plugins · content/skills/humanizer/SKILL.md · Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and…
v2.8.2 · audit A · 6 stars
linkedin-post-writer SKILL.md skill
kulykivska/claude-plugins · content/skills/linkedin-post-writer/SKILL.md · Use this skill whenever the user wants to write, draft, or improve a LinkedIn post — especially when the goal is…
git:20260922.a4bd47b · audit A · 6 stars
social-post SKILL.md skill
kulykivska/claude-plugins · content/skills/social-post/SKILL.md · Create posts for one or several social networks from an idea or recent work. Trigger on "write a post", "make a post…
git:20260922.a4bd47b · audit A · 6 stars
evening SKILL.md skill
kulykivska/claude-plugins · daily/skills/evening/SKILL.md · Evening wind-down, the pair of /morning. On "evening" (or "/evening", "that is enough for today", "how should I end the…
git:20260922.a4bd47b · audit A · 6 stars
morning SKILL.md skill
kulykivska/claude-plugins · daily/skills/morning/SKILL.md · Morning standup / daily kickoff. On "morning" (or "/morning", "good morning", "what did we do yesterday", "where do I…
git:20261104.b33b2e0 · audit A · 6 stars
deploy SKILL.md skill
kulykivska/claude-plugins · fly-ops/skills/deploy/SKILL.md · Deploy a Fly.io-hosted app safely and verify the rollout. Trigger on "deploy", "ship it to prod", or after merging work…
git:20260922.a4bd47b · audit A · 6 stars
fly-logs SKILL.md skill
kulykivska/claude-plugins · fly-ops/skills/fly-logs/SKILL.md · Fetch and filter production logs from Fly.io apps. Trigger on "show me the logs", "check prod logs", "what is in the…
git:20260922.a4bd47b · audit A · 6 stars
incident SKILL.md skill
kulykivska/claude-plugins · fly-ops/skills/incident/SKILL.md · Production incident triage for Fly-hosted apps: site down, 500s, empty data, broken predictions. Trigger on "prod is…
git:20260922.a4bd47b · audit A · 6 stars
local-secrets SKILL.md skill
kulykivska/claude-plugins · guardrails/skills/local-secrets/SKILL.md · The rule and the mechanism for values that must never be written into a repository — passwords, API keys, tokens…
git:20260922.4db1bd6 · audit A · 6 stars
feature-change SKILL.md skill
kulykivska/claude-plugins · ml/skills/feature-change/SKILL.md · Add, remove or rename a model feature without breaking serving. Trigger on "add a model feature", "new feature in the…
git:20260922.a4bd47b · audit A · 6 stars
model-eval SKILL.md skill
kulykivska/claude-plugins · ml/skills/model-eval/SKILL.md · Prove a model change is real before shipping it. Trigger on "did it get better?", "check the model", "evaluate this…
git:20260922.a4bd47b · audit A · 6 stars

Every file in kulykivska/claude-plugins

Other files named remove-ai-marks

remove-ai-marks SKILL.md skill
guillaumemeyer/watermarks-remover · skills/remove-ai-marks/SKILL.md · Remove multi-vendor AI provenance marks: invisible Unicode (Layer A), statistical text watermarks via rewrite (Layer B…
git:20261002.43107e4 · audit B · 27,686 stars
remove-ai-marks SKILL.md skill
badmuriss/my-llm-kit · skills/remove-ai-marks/SKILL.md · Inspect and remove requested metadata or invisible marks from user-owned files. Use when provenance cleanup is…
git:20261001.2d71fc1 · audit B · 3 stars

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