agentic-image-loop SKILL.md skillA

agentic-image-loop from cowork-os/cowork-os is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add cowork-os/cowork-os/agentic-image-loop@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
cowork-os/cowork-os
Path
resources/skills/agentic-image-loop/SKILL.md
Versions recorded
3
Latest version
v1.0.0, committed Sep 19, 2026
First version recorded
Feb 28, 2026
Size
1,705 bytes
Repository stars
535
License
MIT

Generate -> annotate -> refine -> repeat using generate_image + Visual Annotator (Live Canvas).

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

# Agentic Image Loop

## Purpose

Generate -> annotate -> refine -> repeat using generate_image + Visual Annotator (Live Canvas).

## Routing

- Use when: Use when the user asks to generate -> annotate -> refine -> repeat using generate_image + Visual Annotator Live Canvas.
- Do not use when: Do not use when the request is asking for planning documents, high-level strategy, or non-executable discussion; use the relevant planning or design workflow instead.
- Outputs: Outcome from Agentic Image Loop: task-specific result plus concrete action notes.
- Success criteria: Returns concrete actions and decisions matching the requested task, with no fabricated tool-side behavior.

## Trigger Examples

### Positive

- Use the agentic-image-loop skill for this request.
- Help me with agentic image loop.
- Use when the user asks to generate -> annotate -> refine -> repeat using generate_image + Visual Annotator Live Canvas.
- Agentic Image Loop: provide an actionable result.

### Negative

- Do not use when the request is asking for planning documents, high-level strategy, or non-executable discussion; use the relevant planning or design workflow instead.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add cowork-os/cowork-os/agentic-image-loop@sha256:a7ed7aa47022d7a3

The line at the top of this page pins the label v1.0.0, 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_tr7qj57fwanc7vcl.svg)](https://markdownregistry.com/a/art_tr7qj57fwanc7vcl)

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

Versions

The registry has recorded 3 versions of this file, between Feb 28, 2026 and Sep 19, 2026, about one every 102 days.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-09-19 33f99b3 1,705 BA view · diff
v1.0.02026-08-20 1b357d9 1,706 BA view · diff
git:20260228.04a98092026-02-28 04a9809 1,623 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 (1705 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

cowork-os/cowork-os · 535 stars · license MIT · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_tr7qj57fwanc7vcl
GET https://markdownregistry.com/api/v1/resolve?ref=cowork-os/cowork-os/agentic-image-loop
GET https://markdownregistry.com/api/v1/blob/a7ed7aa47022d7a3e6d7c25bbdc94e3b36158977a18441fce8cf95af90c582b1

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 cowork-os/cowork-os

attack-path-analysis SKILL.md skill
cowork-os/cowork-os · resources/plugin-packs/codex-security/skills/attack-path-analysis/SKILL.md · Use when Codex is already in the attack-path-analysis phase of a security scan or the user explicitly asks to trace a…
git:20260919.4f2a470 · audit A · 535 stars
deep-security-scan SKILL.md skill
cowork-os/cowork-os · resources/plugin-packs/codex-security/skills/deep-security-scan/SKILL.md · Use when the user asks for a deep, exhaustive, multi-pass, or variance-reducing repository-wide Codex Security scan…
git:20260606.a4decec · audit A · 535 stars
finding-discovery SKILL.md skill
cowork-os/cowork-os · resources/plugin-packs/codex-security/skills/finding-discovery/SKILL.md · Use when Codex is already in the finding-discovery phase of a security scan or the user explicitly asks to discover…
git:20260919.ad0495b · audit A · 535 stars
fix-finding SKILL.md skill
cowork-os/cowork-os · resources/plugin-packs/codex-security/skills/fix-finding/SKILL.md · Use when the user explicitly asks to fix and verify a validated or plausible security finding. Do not use as the…
git:20260606.a4decec · audit A · 535 stars
security-diff-scan SKILL.md skill
cowork-os/cowork-os · resources/plugin-packs/codex-security/skills/security-diff-scan/SKILL.md · Use when the user asks for a security review of a pull request, commit, branch diff, working-tree patch, or other…
git:20260919.c03e78b · audit A · 535 stars
security-scan SKILL.md skill
cowork-os/cowork-os · resources/plugin-packs/codex-security/skills/security-scan/SKILL.md · Use when the user asks for a repository-wide or scoped-path security scan.
git:20260919.7b075ca · audit A · 535 stars
threat-model SKILL.md skill
cowork-os/cowork-os · resources/plugin-packs/codex-security/skills/threat-model/SKILL.md · Use when Codex is already in the threat-modeling phase of a security scan, the user explicitly invokes $threat-model…
git:20260606.a4decec · audit A · 535 stars
validation SKILL.md skill
cowork-os/cowork-os · resources/plugin-packs/codex-security/skills/validation/SKILL.md · Use when Codex is already in the validation phase of a security scan or the user explicitly asks to determine whether…
git:20260606.a4decec · audit A · 535 stars
1password SKILL.md skill
cowork-os/cowork-os · resources/skills/1password/SKILL.md · Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or…
v1.0.0 · audit A · 535 stars
add-documentation SKILL.md skill
cowork-os/cowork-os · resources/skills/add-documentation/SKILL.md · Generate JSDoc/docstrings for functions
v1.0.0 · audit A · 535 stars
analyze-csv SKILL.md skill
cowork-os/cowork-os · resources/skills/analyze-csv/SKILL.md · Load a CSV and provide insights
v1.0.0 · audit A · 535 stars
android-development SKILL.md skill
cowork-os/cowork-os · resources/skills/android-development/SKILL.md · Android/Kotlin development: Jetpack Compose, Room database, Gradle builds, emulator management, and Play Store…
v1.0.0 · audit A · 535 stars

Every file in cowork-os/cowork-os

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