Docker Development

What it does

When your agent uses it

• Asks to analyze a Dockerfile
• Optimize Docker layers
• Validate docker-compose
• Check container best practices

Example prompts

• “analyze a Dockerfile”
• “optimize Docker layers”
• “validate docker-compose”
• “/docker-development”

Requirements

• Python 3
• Docker

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Analyze - Run dockerfile_analyzer.py against the target Dockerfile
2. 2Review findings - Address critical security issues first (root user, secrets)
3. 3Optimize layers - Combine RUN statements, reorder for cache efficiency
4. 4Validate base images - Switch to minimal base images where possible
5. 5Re-analyze - Confirm improvements and verify no regressions

What it can do on your machine

Read from SKILL.md and the folder at commit 4a698e8. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 2 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python
  • apt-get

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Docker Development loads about 1.5k tokens when it runs, and up to ~2.2k if it reads all its reference files. Until then it costs about 53 tokens; SKILL.md has 509 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~53

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:140

  build secrets or env at runtime | `COPY .env .` or `ENV SECRET=value` |

• NoteMentions a .env fileSKILL.md:152

  | Environment | `env_file: .env` | Inline secrets in compose |

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from borghei/Claude-Skills at commit 4a698e8, republished under its MIT licence (© borghei). 509 words, ~1,527 tokens.

name

docker-development

description

This skill should be used when the user asks to "analyze a Dockerfile", "optimize Docker layers", "validate docker-compose", "check container best practices", or "audit Docker configurations".

license

MIT + Commons Clause

metadata.version

1.0.0

metadata.author

borghei

metadata.category

engineering

metadata.domain

containers

metadata.updated

2026-04-02

metadata.tags

docker, containers, devops, compose, dockerfile

# Analyze a Dockerfile for best practices
python scripts/dockerfile_analyzer.py --file Dockerfile

# Analyze with JSON output
python scripts/dockerfile_analyzer.py --file Dockerfile --format json

# Validate a docker-compose file
python scripts/compose_validator.py --file docker-compose.yml

# Check for port conflicts across compose files
python scripts/compose_validator.py --file docker-compose.yml --check-ports

# Full analysis
python scripts/dockerfile_analyzer.py --file Dockerfile

# Security-focused scan
python scripts/dockerfile_analyzer.py --file Dockerfile --security-only

# JSON output for CI integration
python scripts/dockerfile_analyzer.py --file Dockerfile --format json

# Full validation
python scripts/compose_validator.py --file docker-compose.yml

# Check port conflicts only
python scripts/compose_validator.py --file docker-compose.yml --check-ports

# JSON output
python scripts/compose_validator.py --file docker-compose.yml --format json

# Example GitHub Actions step
- name: Docker Lint
  run: |
    python scripts/dockerfile_analyzer.py --file Dockerfile --format json > results.json
    python scripts/compose_validator.py --file docker-compose.yml --format json >> results.json

© borghei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (scripts, references) in engineering/docker-development of borghei/Claude-Skills.

• SKILL.md
• examples/Dockerfile.sample
• examples/docker-compose.sample.yml
• references/docker-best-practices.md
• scripts/compose_validator.py
• scripts/dockerfile_analyzer.py

Open the folder on GitHubat commit 4a698e8