configure-replication-agent
Configure AEM 6.5 LTS replication agents for content publishing, dispatcher cache flushing, and reverse replication
63
55%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/aem/6.5-lts/skills/aem-replication/configure-replication-agent/SKILL.mdQuality
Discovery
82%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 is a strong, specific description that clearly identifies the technology platform (AEM 6.5 LTS) and lists three concrete replication-related actions. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The domain-specific terminology serves as excellent natural trigger terms for the target audience.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about setting up or troubleshooting AEM replication agents, publish/author synchronization, dispatcher flush agents, or reverse replication configuration.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'content publishing', 'dispatcher cache flushing', and 'reverse replication'. These are distinct, well-defined operations within the AEM replication domain. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (configure replication agents for three specific purposes), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this dimension at 2 per the rubric. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords a user would say: 'AEM 6.5 LTS', 'replication agents', 'content publishing', 'dispatcher cache flushing', 'reverse replication'. These are the exact terms an AEM developer would use when seeking help. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific technology (AEM 6.5 LTS) and the narrow domain (replication agents). Very unlikely to conflict with other skills given the precise platform version and feature area. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is comprehensive in coverage but severely over-engineered for a SKILL.md file. It reads more like full product documentation than a concise skill guide, explaining obvious UI fields and concepts at length. The content would benefit enormously from splitting into multiple files and trimming redundant explanations, keeping only the configuration-specific details Claude wouldn't already know.
Suggestions
Reduce the document to ~100 lines by removing field-by-field explanations of obvious settings (Enabled, Log Level, etc.) and focusing only on AEM-specific configuration values and gotchas that Claude wouldn't know.
Split agent-specific configurations (Dispatcher Flush, Reverse Replication), troubleshooting, and security best practices into separate referenced files to improve progressive disclosure.
Remove the 'When to Use This Skill' and 'Prerequisites' sections entirely — Claude can infer these from context, and they add no actionable value.
Add scriptable/API-based configuration examples (e.g., CRXDE Lite API calls, curl commands to create agents via Sling POST) instead of relying solely on UI click-through instructions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Explains concepts Claude already knows (what replication agents are, what PDF-like basic AEM concepts mean), includes extensive tables of obvious field descriptions (e.g., explaining what 'Enabled' checkbox does), and repeats information across sections. The prerequisites section, 'When to Use This Skill' section, and much of the field-by-field documentation could be dramatically condensed. | 1 / 3 |
Actionability | Provides specific URIs, field names, and configuration values which are useful, but lacks executable code/scripts for automation. The guidance is mostly UI-click-based instructions rather than concrete commands or API calls. Some curl examples exist in troubleshooting but the core configuration steps are manual UI walkthroughs rather than scriptable actions. | 2 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced across the 9-step workflow, and there is a 'Test Connection' step (Step 8) before enabling. However, the validation section is separated from the main workflow rather than integrated as checkpoints, and there's no explicit feedback loop (validate → fix → retry) embedded in the configuration steps themselves. The troubleshooting section is helpful but reactive rather than preventive. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no bundle files to offload detailed content. Agent-specific configurations, troubleshooting, security best practices, and monitoring could all be separate referenced files. Everything is inline in a single massive document, making it difficult to navigate and consuming excessive context window space. | 1 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (525 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- adobe/skills
- Commit
ca72b27
- Reviewed
Table of Contents
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.