CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

troubleshoot-replication

Diagnose and fix common AEM 6.5 LTS replication issues including blocked queues, connectivity failures, and content distribution problems

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/aem/6.5-lts/skills/aem-replication/troubleshoot-replication/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%Weight 40%Scale 1-5

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

The content is a genuinely actionable, well-structured troubleshooting guide with concrete commands, paths, and validation checkpoints — its strongest dimensions are actionability and workflow clarity. Its weaknesses are a bloated, over-formatted presentation (prose in code fences, ~1060 lines that could be halved) and a complete absence of progressive disclosure, with everything monolithically inlined in SKILL.md.

Suggestions

Split per-issue detail (Issues 1–12) into one-level-deep references/ files (e.g. references/queue-blocked.md, references/connectivity.md) and keep SKILL.md as a symptom→file index plus the diagnostic workflow and checklist.

Convert prose-in-code-fence blocks ("Steps: 1. Open blocked replication agent...") into plain numbered lists, reserving code fences for genuinely executable commands like the curl/telnet/keytool/grep examples.

Add explicit post-fix verification steps after every destructive or risky operation — e.g. after "rm -rf" dispatcher cache clears, verify content serves fresh and the flush agent re-populates the cache.

DimensionReasoningScore

Conciseness

The body is dense with domain-specific detail (real paths, ports, defaults, bundle names) rather than concepts Claude already knows, but at ~1060 lines / 24 KB it is heavily over-long: prose navigation instructions wrapped in code fences, repetitive Symptoms/Diagnosis/Root Causes/Solutions scaffolding, and sections that could be halved. Mostly substantive but with substantial tightening possible — matches anchor 3, not 2 because there is little conceptual fluff or padding.

3 / 5

Actionability

Guidance is consistently concrete — exact URIs ("http://publish-host:4503/bin/receive?sling:authRequestLogin=1"), copy-paste bash (curl, nc -zv, openssl s_client, keytool -import, grep patterns), and specific config values (Connection Timeout: 30000). Falls short of 5 because many fenced "code" blocks are actually prose steps ("Steps: 1. Open blocked replication agent 2. Click \"Force Retry\""), not executable commands.

4 / 5

Workflow Clarity

An 8-step diagnostic workflow ending in "Validate Resolution", per-issue Diagnosis→Solutions sequences, an 18-item Diagnostic Checklist, and explicit Success Criteria provide clear sequencing with most checkpoints present. Not 5 because validation after risky fixes is inconsistent — e.g. the Issue 5 dispatcher cache clear ("rm -rf *") has no post-verification while Issue 11's riskier /var/replication/data deletion does include backup and verify steps.

4 / 5

Progressive Disclosure

Internally well-sectioned with clear headers, but it is a 1000+ line monolith with zero bundle files — twelve detailed issues plus Advanced Troubleshooting, Preventive Measures, and escalation material are all inlined in SKILL.md when they are prime candidates for one-level-deep references/ files. Matches anchor 3 (structure present but content that should be separate is inline); not 4 because nothing is split out at all.

3 / 5

Total

14

/

20

Passed

Description

70%Weight 40%Scale 1-5

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, well-targeted, and clearly distinguishable, with a concrete enumeration of the failure modes it covers. Its main weakness is the absence of any explicit "Use when..." trigger clause, which caps completeness and leaves natural trigger terms like "publish", "agent", and "dispatcher" implicit.

Suggestions

Append an explicit trigger clause, e.g. "Use when replication queues are blocked, content is not appearing on Publish, agents show red/error status, or replication fails with connection, timeout, or 401 errors."

Add common natural trigger terms users would actually say — "publish/publishing", "replication agent", "dispatcher cache" — to broaden keyword coverage.

Mention authentication/401 failures in the description since they are a significant covered topic currently absent from the summary.

DimensionReasoningScore

Specificity

Names the domain (AEM 6.5 LTS replication) and lists several concrete issue categories — "blocked queues, connectivity failures, and content distribution problems" — matching the anchor for several specific actions with minor gaps. Falls short of 5 because coverage is not comprehensive (no mention of agent configuration, dispatcher cache, or authentication failures).

4 / 5

Completeness

The "what" is clear ("Diagnose and fix common AEM 6.5 LTS replication issues") but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 2 because the "what" is specific and concrete, not vague.

3 / 5

Trigger Term Quality

Good keyword coverage with natural phrases users would say ("replication", "blocked queues", "connectivity failures"), but a few common terms are missing ("publish", "agent", "dispatcher", "401"). Not 5 because synonym and variation coverage is incomplete.

4 / 5

Distinctiveness Conflict Risk

"AEM 6.5 LTS replication" is a clear niche with distinct, product-specific triggers (blocked queues, connectivity failures, content distribution) and minimal conflict risk with other skills. Clearly matches the anchor-5 example's clear-niche pattern.

5 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1067 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

adobe/skills

Path

plugins/aem/6.5-lts/skills/aem-replication/troubleshoot-replication/SKILL.md

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.