Docker Container Analyzer skill for Claude and Codex
Assesses a container image before it ships: base image risk, known vulnerabilities to check, layer and size findings, and runtime hardening steps, in a short…
Install it once and Claude or Codex runs it for you. When your request matches, your AI loads the skill, asks for anything it is missing, and works through the template itself. Prefer to fill it in by hand? See the full prompt template.
Download the skill (.zip) · View SKILL.md
When it is used
Use when a container image needs a security and size assessment before deployment, with base image risk, CVEs to check, and runtime hardening. Do not use for troubleshooting a container that is already failing, or rewriting a Dockerfile to shrink the image. Related topics: coding, docker.
What it will ask you for
- Image name (free text, e.g. "nginx or ghcr.io/acme/api")
- Tag (free text, e.g. "1.27.2 or latest")
- Base OS (choose one: Alpine, Debian, Ubuntu, CentOS, Distroless, Scratch, Unknown)
- Analysis depth (choose one: Quick, Moderate, Deep)
- CVE lookup (choose one: Enable, Disable)
- Size limit (MB) (number from 0 to 2000)
- Image history or Dockerfile (longer free text)
- Additional notes (longer free text)
How it works
- Read the supplied layer history or Dockerfile for packages, secrets, and copied files, or state that findings rest on name, tag, and base OS and give the commands to confirm.
- Judge the base image on tag pinning, end-of-life status, and package surface, and record each finding as a bullet.
- List CVE IDs when lookup is enabled, each labelled known or to be confirmed by a scanner.
- Compare the image size to the limit and attribute any excess to specific layers.
- Write the hardening recommendations in priority order and open the report with a one-line verdict.
What you get
A Markdown report with sections Summary (one-line verdict), Security Findings, Size Overview, and Recommendations, all in bullet points, with CVE IDs when lookup is enabled.
What it watches out for
- Presenting remembered CVEs as scan results; label what a scanner must confirm so nobody signs off on a guess.
- Passing an image tagged latest, which makes every finding unreproducible the next time the tag moves.
- Burying the verdict under findings; the reviewer needs the ship or do not ship line first.
How to install
Claude.ai and the Claude desktop app
- Download the skill .zip.
- Open Settings, then Capabilities, and find Skills.
- Choose Upload skill and select the .zip.
- Ask Claude for help with the task. It loads the skill when your request matches.
Claude Code
- Download the skill .zip.
- Unzip it into ~/.claude/skills/ (or .claude/skills/ inside a project).
- Start a new session. Claude Code loads the skill when your request matches.
Codex
- Download the skill .zip.
- Unzip it into ~/.agents/skills/ (or .agents/skills/ inside a project).
- Codex picks it up on its own. Type $ and the skill name to use it, or just ask for the task.
Cursor
- Download the Cursor rule (.mdc).
- Save it in .cursor/rules/ inside your project.
- Cursor's agent applies the rule when your request matches its description.
AGENTS.md (Codex, Cursor, and other coding agents)
- Copy the AGENTS.md section.
- Paste it into AGENTS.md at the root of your repository, creating the file if needed.
- Coding agents that read AGENTS.md follow it when your request fits.