Docker image reviews, optimization, and step-building guidance. Analyzes Dockerfiles for best practices, security issues, and anti-patterns.
70
63%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./analysis/agent-ops-docker-review/SKILL.mdQuality
Discovery
57%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description adequately identifies its domain and lists several relevant capabilities around Docker image analysis and optimization. However, it lacks an explicit 'Use when...' clause, which limits its completeness score and makes it harder for Claude to know exactly when to select this skill. Adding natural trigger terms and explicit usage guidance would meaningfully improve selection accuracy.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to review, optimize, or troubleshoot a Dockerfile, or mentions Docker image size, build performance, or container security.'
Include additional natural trigger terms users might say, such as 'container', 'multi-stage build', 'image size', 'docker-compose', 'layer caching', or '.dockerfile'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Docker images/Dockerfiles) and some actions (reviews, optimization, step-building guidance, analyzes for best practices/security/anti-patterns), but doesn't list multiple granular concrete actions like 'reduce image layers, pin base image versions, identify exposed secrets'. | 2 / 3 |
Completeness | Clearly answers 'what does this do' (reviews, optimization, analyzes Dockerfiles for best practices/security/anti-patterns), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Docker image', 'Dockerfiles', 'optimization', 'security issues', and 'best practices', but misses common user variations like 'container', 'docker-compose', '.dockerfile', 'image size', 'multi-stage build', or 'layer caching'. | 2 / 3 |
Distinctiveness Conflict Risk | Docker/Dockerfile analysis is a clear niche that is unlikely to conflict with other skills. The specific mention of Dockerfiles, image optimization, and security anti-patterns makes it distinctly identifiable. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive and highly actionable Docker review skill with excellent concrete examples, clear workflows, and good safety constraints. Its main weakness is that it's far too long for a single SKILL.md — the language templates, detailed report formats, and scan procedures should be split into referenced files to improve token efficiency and progressive disclosure. The content quality is high but the structure needs reorganization.
Suggestions
Extract language templates (Python, Node, Go, .NET) into a separate TEMPLATES.md file and reference it from the main skill with a brief summary table
Move the detailed report output formats (review report, scan report, optimize output) into a REPORT-FORMATS.md reference file, keeping only a brief description of each in the main skill
Trim the mode overview table and procedures to be more concise — the current level of detail for each mode could be reduced by ~30% without losing clarity
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~300 lines) with four full language templates that are largely repetitive patterns. The templates could be referenced from a separate file. However, it avoids explaining basic Docker concepts and stays focused on actionable content, so it's not egregiously verbose. | 2 / 3 |
Actionability | Excellent actionability throughout — concrete executable Dockerfiles, specific bash commands for scanning tools, complete language-specific templates with copy-paste ready code, and specific rule IDs with clear descriptions. The before/after optimization example is particularly strong. | 3 / 3 |
Workflow Clarity | Each mode has a clearly numbered procedure with explicit steps. The Review mode has a clear locate→analyze→report flow, Optimize builds on Review then generates comparison, Build mode uses an interview pattern with sequential questions, and Scan mode checks prerequisites before running. The forbidden behaviors section adds important safety constraints. Validation is present (e.g., showing diff before modifying, requiring user confirmation before docker build). | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of content with no references to external files for detailed content. The four language templates, the full scan report format, and the complete optimization output format all live inline. These should be split into separate reference files (e.g., TEMPLATES.md, SCAN-REPORT.md) with the SKILL.md serving as an overview with links. | 1 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
3dd3ac0
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.