Expert C4 Container-level documentation specialist.
49
22%
Does it follow best practices?
Impact
99%
2.75xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/c4-container/SKILL.mdQuality
Discovery
22%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is far too vague and relies on buzzwords ('Expert', 'specialist') rather than concrete actions. It fails to explain what the skill actually does or when Claude should select it. The only redeeming quality is the mention of 'C4 Container-level' which provides some domain specificity.
Suggestions
Replace vague terms like 'specialist' with concrete actions, e.g., 'Generates C4 Container diagrams, documents system containers and their interactions, creates PlantUML or Structurizr DSL representations of container-level architecture.'
Add an explicit 'Use when...' clause with trigger terms, e.g., 'Use when the user asks about C4 model containers, architecture diagrams, system decomposition, or container-level views.'
Include common file formats or tools associated with C4 modeling (e.g., '.puml', 'Structurizr', 'Mermaid') to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language with no concrete actions listed. 'Expert' and 'specialist' are buzzwords that don't describe what the skill actually does (e.g., generate diagrams, write documentation, create container views). | 1 / 3 |
Completeness | The 'what' is extremely vague ('documentation specialist' says almost nothing about concrete capabilities), and there is no 'when' clause or explicit trigger guidance whatsoever. | 1 / 3 |
Trigger Term Quality | 'C4' and 'Container-level' are relevant domain keywords that a user familiar with C4 modeling might use, but common variations like 'architecture diagram', 'system context', 'PlantUML', or 'structurizr' are missing. | 2 / 3 |
Distinctiveness Conflict Risk | 'C4 Container-level' provides some niche specificity that distinguishes it from generic documentation skills, but 'documentation specialist' is broad enough to overlap with other documentation-related skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is primarily a documentation template with placeholder brackets rather than actionable guidance for Claude. It lacks a clear workflow, includes verbose boilerplate that Claude doesn't need (OpenAPI spec structure, basic C4 concepts), and the four-line instruction section is too vague to drive meaningful behavior. The Mermaid diagram example is a strength but doesn't compensate for the overall lack of concrete, executable steps.
Suggestions
Replace the generic 4-bullet instruction list with a concrete, sequenced workflow (e.g., 1. Analyze deployment configs → 2. Identify container boundaries → 3. Document interfaces → 4. Generate Mermaid diagram → 5. Validate completeness against checklist).
Remove the inline OpenAPI template and Mermaid boilerplate—Claude knows these formats. Instead, specify only the project-specific conventions or deviations from standard formats.
Add validation checkpoints to the workflow, such as 'Verify each container has at least one documented interface' or 'Confirm all inter-container relationships appear in the Mermaid diagram'.
Move the template sections (Containers, Interfaces, Infrastructure) to a separate reference file and keep SKILL.md focused on the process and decision-making guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is heavily padded with template placeholders (e.g., '[Container Name]', '[Description]') that provide no actionable value. It explains concepts Claude already knows (what REST/GraphQL are, what containers are) and includes verbose boilerplate like the OpenAPI template that Claude can generate on its own. The 'Use this skill when' / 'Do not use this skill when' sections are generic filler. | 1 / 3 |
Actionability | The Mermaid diagram example is concrete and executable, and the OpenAPI template is copy-paste ready. However, most of the content consists of empty templates with bracket placeholders rather than executable guidance. The 'Instructions' section is extremely vague ('Clarify goals, constraints, and required inputs'). | 2 / 3 |
Workflow Clarity | There is no clear multi-step workflow or sequenced process. The skill describes what documentation artifacts to produce but never defines a clear sequence of steps to follow, nor any validation checkpoints. The instructions are just four bullet points of generic advice with no ordering logic. | 1 / 3 |
Progressive Disclosure | There is one reference to an external file ('resources/implementation-playbook.md') and mentions of component documentation links, which shows some awareness of progressive disclosure. However, the skill itself is a monolithic wall of templates that could be split into separate reference files, and the inline OpenAPI template and Mermaid example bloat the main file. | 2 / 3 |
Total | 6 / 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 | |
e18e63c
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.