Diagnose and fix common AEM 6.5 LTS replication issues including blocked queues, connectivity failures, and content distribution problems
45
47%
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/troubleshoot-replication/SKILL.mdQuality
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 strong in specificity and distinctiveness, clearly identifying a narrow technical domain (AEM 6.5 LTS replication) with concrete problem types. However, it lacks an explicit 'Use when...' clause which limits its completeness score, and could benefit from additional natural trigger terms that users might employ when encountering these issues.
Suggestions
Add a 'Use when...' clause such as 'Use when the user reports AEM replication errors, publish agent failures, content not syncing between author and publish instances, or blocked replication queues.'
Include additional natural trigger terms like 'publish agent', 'replication agent', 'dispatcher flush', 'author-publish sync', or 'AEM content not publishing' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and problem types: 'diagnose and fix', 'blocked queues', 'connectivity failures', and 'content distribution problems'. These are concrete, actionable capabilities within a well-defined domain. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (diagnose and fix AEM replication issues), 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 good domain-specific terms like 'AEM 6.5 LTS', 'replication', 'blocked queues', 'connectivity failures', and 'content distribution', but misses common user variations like 'publish agent', 'dispatcher', 'flush agent', 'replication agent', or 'AEM replication error'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specific niche targeting AEM 6.5 LTS replication issues specifically. This is unlikely to conflict with other skills given the very specific technology, version, and problem domain. | 3 / 3 |
Total | 10 / 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 of AEM replication issues but severely suffers from verbosity and monolithic structure. At 600+ lines with 12 detailed issues all inline, it would consume enormous context window space. The content would benefit greatly from being restructured into a concise overview SKILL.md that links to separate issue-specific files, and from trimming repetitive patterns and sections that don't add value beyond what Claude already knows.
Suggestions
Split the 12 issues into separate files (e.g., issues/queue-blocked.md, issues/connection-refused.md) and make SKILL.md a concise overview with a quick-reference table linking symptoms to the appropriate file.
Remove or drastically condense sections like 'When to Use This Skill', 'Prerequisites', 'Preventive Measures', 'Escalation Path', 'Success Criteria', and 'Additional Resources' — these are either inferrable by Claude or not actionable troubleshooting guidance.
Add explicit verification/validation steps after each solution (not just Issue 9), especially for destructive operations like clearing replication data or deleting event jobs.
Consolidate repetitive solution patterns — many issues share the same 'edit agent → transport tab → save → test connection' flow, which could be a single referenced procedure instead of repeated inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 600+ lines. Massive amounts of content that could be condensed significantly. Many sections repeat similar patterns (check agent, edit, save, test connection). The 'When to Use This Skill', 'Prerequisites', 'Preventive Measures', 'Escalation Path', 'Success Criteria', and 'Additional Resources' sections add substantial bulk with information Claude can infer. The diagnostic checklist largely repeats what was already covered in the issues above. | 1 / 3 |
Actionability | Provides specific navigation paths (e.g., 'Tools → Deployment → Replication') and some executable bash commands (curl, telnet, grep), which is good. However, many 'solutions' are UI click-through instructions rather than executable code, and several steps are described at a high level ('Fix network/firewall', 'adjust permissions') without concrete commands. The Java code snippet is a useful exception. | 2 / 3 |
Workflow Clarity | The initial diagnostic workflow flowchart provides a clear sequence, and each issue follows a symptoms → diagnosis → solutions pattern. However, validation/verification steps are inconsistent — only Issue 9 has an explicit verification section. For destructive operations like clearing replication data or deleting event jobs, there are warnings but no explicit validate-then-proceed feedback loops. The checklist at the end partially compensates but is disconnected from the individual issue workflows. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with 12 detailed issues all inline in a single file. No bundle files are provided, and the 'Related Skills' section references skills that don't exist in the bundle. This content desperately needs to be split — e.g., common issues in separate files, advanced troubleshooting in its own file — with SKILL.md serving as a concise overview with links. | 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 (1067 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
e23271f
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.