sse-resilience
Redis-backed SSE stream management with stream registry, heartbeat monitoring, completion store for terminal events, and automatic orphan cleanup via background guardian process.
79
53%
Does it follow best practices?
Impact
97%
1.90xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/api/sse-resilience-dadbodgeoff-drift/SKILL.mdQuality
Discovery
50%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 excels at specificity and distinctiveness, clearly naming a narrow technical domain with concrete components. However, it completely lacks trigger guidance ('Use when...') which is critical for Claude to know when to select this skill. The technical jargon, while precise, may not match how users naturally phrase requests.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when implementing or debugging SSE streaming endpoints, managing server-sent event connections, or handling Redis pub/sub stream lifecycle.'
Include natural language trigger terms users might say, such as 'server-sent events', 'streaming connections', 'real-time event delivery', or 'stream disconnection handling'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: SSE stream management, stream registry, heartbeat monitoring, completion store for terminal events, and automatic orphan cleanup via background guardian process. | 3 / 3 |
Completeness | Describes what the skill does but completely lacks any 'Use when...' clause or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'when' is entirely absent with no implicit triggers, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant technical terms like 'Redis', 'SSE', 'stream', 'heartbeat', 'orphan cleanup', but these are fairly technical. Missing common user-facing variations like 'server-sent events', 'streaming', 'real-time events', or 'event stream'. Users might not naturally say 'guardian process' or 'completion store'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of Redis-backed, SSE streams, heartbeat monitoring, completion store, and orphan cleanup via guardian process is highly specific and unlikely to conflict with other skills. This is a clear, narrow niche. | 3 / 3 |
Total | 9 / 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.
The skill provides highly actionable, executable TypeScript code for a complete SSE stream resilience system with Redis backing. However, it suffers from being a monolithic document with all implementation details inline rather than properly structured with progressive disclosure. The workflow is implicit in the code rather than explicitly documented with validation checkpoints.
Suggestions
Split the large inline code blocks into referenced files (e.g., 'See [stream-registry.ts](examples/stream-registry.ts) for full implementation') and keep only a concise overview with key patterns in SKILL.md
Add an explicit workflow section with numbered steps showing the full lifecycle: register → heartbeat loop → completion storage → client recovery → guardian cleanup, with validation checkpoints at each stage
Remove the 'Best Practices' and 'Common Mistakes' sections as they largely restate what's already demonstrated in the code, or consolidate them into brief inline comments within the code examples
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long with extensive inline code that could be split into referenced files. The 'When to Use' and 'Core Concepts' sections add some value but the bullet lists in 'Best Practices' and 'Common Mistakes' partially repeat what's already shown in the code. The types/interfaces section explains things Claude would understand from context. | 2 / 3 |
Actionability | The code is fully executable TypeScript with concrete implementations for stream registry, completion store, guardian process, SSE endpoint, and client-side recovery hook. All examples are copy-paste ready with specific Redis key patterns, TTL values, and complete class implementations. | 3 / 3 |
Workflow Clarity | While the architecture diagram shows the flow and the code implicitly demonstrates the sequence (register → heartbeat → complete/recover → cleanup), there are no explicit validation checkpoints or error recovery steps documented as a workflow. The guardian handles orphans but there's no explicit verification step after operations like registration or completion storage. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of code (~250 lines of inline TypeScript) that would benefit greatly from splitting into separate reference files. The 'Related Patterns' section references other files but the main content dumps everything inline with no separation between overview and detailed implementation. | 1 / 3 |
Total | 8 / 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 |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- majiayu000/claude-skill-registry
- Commit
d156cd1
- 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.