iii-dead-letter-queues
Inspects and redrives jobs that exhausted all retries. Use when handling failed queue jobs, debugging processing errors, or implementing retry strategies.
73
66%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/iii-dead-letter-queues/SKILL.mdQuality
Discovery
75%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 well-structured with a clear 'what' and 'when' clause, making it functionally complete. Its main weakness is moderate specificity—it could enumerate more concrete actions—and the trigger terms, while relevant, miss common synonyms like 'dead letter queue' or 'DLQ' that users would naturally use.
Suggestions
Add more specific concrete actions such as 'view error details, filter by failure reason, bulk redrive, configure retry limits'.
Include common synonyms and variations in trigger terms: 'dead letter queue', 'DLQ', 'stuck jobs', 'job failures', or platform-specific terms like 'SQS', 'Sidekiq', 'Bull'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (queue jobs) and some actions ('inspects and redrives jobs that exhausted all retries'), but doesn't list multiple concrete actions comprehensively—e.g., doesn't mention viewing error logs, filtering by error type, or configuring retry policies. | 2 / 3 |
Completeness | Clearly answers both 'what' (inspects and redrives jobs that exhausted all retries) and 'when' (Use when handling failed queue jobs, debugging processing errors, or implementing retry strategies) with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'failed queue jobs', 'retry', 'processing errors', but misses common natural variations users might say such as 'dead letter queue', 'DLQ', 'stuck jobs', 'job failures', or specific queue systems like SQS, Sidekiq, Bull. | 2 / 3 |
Distinctiveness Conflict Risk | The description targets a clear niche—failed queue job inspection and redriving—which is unlikely to conflict with other skills. The combination of 'redrives', 'exhausted retries', and 'queue jobs' creates a distinct trigger profile. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a solid overview of DLQ concepts with good progressive disclosure and clear references to related skills and implementation files. However, it lacks inline executable code examples (relying on external references), and the workflow for inspecting and redriving is described narratively rather than as a clear, validated step-by-step process. Some sections are redundant or could be consolidated for better token efficiency.
Suggestions
Add an inline, executable code block showing the complete inspect-then-redrive workflow (check status → inspect errors → redrive → verify) with explicit validation steps, rather than deferring entirely to reference files.
Consolidate the 'Architecture' narrative into 'Key Concepts' since they overlap, and remove or merge the boilerplate 'When to Use' and 'Boundaries' sections to improve conciseness.
Structure the redrive process as a numbered workflow with explicit checkpoints, e.g., '1. Check DLQ depth with status call → 2. Investigate root cause → 3. Deploy fix → 4. Redrive → 5. Verify DLQ is empty'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some redundancy — the 'When to Use' and 'Boundaries' sections at the end are boilerplate that adds little value. The 'Architecture' section restates what's already conveyed in 'Key Concepts'. Some sections like 'Adapting This Pattern' could be tightened. | 2 / 3 |
Actionability | Provides concrete SDK calls and CLI commands with specific examples (e.g., redrive payload, expected return format), but the actual reference implementations are deferred to external files rather than shown inline. There's no executable, copy-paste-ready code block in the skill itself — just inline command snippets in bullet lists. | 2 / 3 |
Workflow Clarity | The Architecture section describes the workflow narratively (fail → retry → DLQ → inspect → fix → redrive) and 'Common Patterns' mentions best practice of investigating before redriving, but there's no explicit numbered sequence with validation checkpoints. Missing a clear 'check DLQ status before and after redrive' step in a structured workflow, and no error recovery feedback loop is formalized. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections, a primitives table for quick reference, and one-level-deep references to external files (JS, Python, Rust implementations, config YAML). The 'Pattern Boundaries' section clearly directs to related skills. Navigation is straightforward. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- iii-hq/iii
- Commit
8921efa
- 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.