agent-ops-docker-review

Docker image reviews, optimization, and step-building guidance. Analyzes Dockerfiles for best practices, security issues, and anti-patterns.

Quality

61%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/analysis/agent-ops-docker-review/SKILL.md

Quality

Discovery

67%

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 is specific about capabilities and clearly scoped to the Docker/Dockerfile domain, making it distinctive. However, it lacks an explicit 'Use when...' clause, which weakens its completeness, and could benefit from additional natural trigger terms users might use when seeking Docker help.

Suggestions

Add a 'Use when...' clause such as 'Use when the user asks about Dockerfiles, container images, Docker optimization, or image build issues.'

Include additional natural trigger terms like 'container', 'multi-stage build', 'image size', 'docker build', or 'Dockerfile linting' to improve keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'reviews', 'optimization', 'step-building guidance', 'Analyzes Dockerfiles for best practices, security issues, and anti-patterns'. These are specific, actionable capabilities.	3 / 3
Completeness	Clearly answers 'what does this do' with reviews, optimization, and analysis, but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric.	2 / 3
Trigger Term Quality	Includes good terms like 'Docker image', 'Dockerfiles', 'best practices', 'security issues', but misses common user variations like 'container', 'docker-compose', 'multi-stage build', '.dockerfile', or 'image size'.	2 / 3
Distinctiveness Conflict Risk	Clearly scoped to Docker/Dockerfile domain with specific triggers like 'Docker image', 'Dockerfiles', 'anti-patterns'. Unlikely to conflict with other skills given the narrow, well-defined niche.	3 / 3
	Total	10 / 12 Passed

Implementation

55%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable with excellent workflow clarity, providing concrete commands, executable templates, and well-structured procedures for each mode. However, it is severely bloated — cramming 4 language templates, multiple full report examples, scanner configurations, and rule tables into a single file that could easily be 3-4x shorter with proper progressive disclosure. The content would benefit enormously from splitting templates and detailed examples into referenced files.

Suggestions

Extract language-specific Dockerfile templates into a separate TEMPLATES.md file and reference it from the Build Mode section

Move the detailed report output examples into a REPORT-FORMATS.md reference file, keeping only a brief description of the format in the main skill

Consolidate the rules tables into a separate RULES.md file — Claude already knows Docker best practices and only needs the rule IDs and severity mappings as a quick reference

Remove explanatory descriptions from rule tables (e.g., 'Use COPY unless ADD features needed') since Claude already knows these concepts — just keep the rule ID and name

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~300+ lines. It includes extensive template code for 4 languages (Python, Node, Go, .NET), full report output examples repeated multiple times, and detailed scanner output examples. Much of this could be condensed or split into reference files. Claude already knows Docker best practices, Dockerfile syntax, and how to use these tools.	1 / 3
Actionability	The skill provides fully executable Dockerfiles, concrete bash commands for scanning tools, specific rule tables with IDs, and complete before/after examples. Every mode has clear triggers, procedures, and output formats that are copy-paste ready.	3 / 3
Workflow Clarity	Each mode has a clearly numbered procedure with explicit steps. The Review mode has locate → analyze → report flow, Optimize builds on Review then generates comparison, Build mode has an interview → generate → review sequence, and Scan mode checks prerequisites before running. The forbidden behaviors section adds safety constraints.	3 / 3
Progressive Disclosure	Everything is in a single monolithic file with no references to supporting files. The language templates, detailed report formats, scanner configurations, and rule tables should be split into separate reference files. The output paths (.agent/docker-review.md, .agent/references/dockerfile-optimized.md) are mentioned but no bundle files exist to support the structure.	1 / 3
	Total	8 / 12 Passed

Validation

90%

Warnings & errors only

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

Repository: majiayu000/claude-skill-registry
Commit: ac1dcdc

Reviewed: 22 minutes ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

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.