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.

1.90x

Quality

—

Does it follow best practices?

Impact

97%

1.90x

Average score across 6 eval scenarios

Securityby

Passed

No known issues

Quality

Content

65%

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

The body is highly actionable with executable code and good sectioning, but it reads as a component catalog rather than a sequenced workflow, and it keeps a large amount of code inline instead of progressively disclosing it. Consolidating redundant prose and adding validation checkpoints would lift the weaker dimensions.

Suggestions

Add an explicit numbered workflow (register stream → heartbeat → store completion → guardian cleanup → client recovery) with a validation/checkpoint after the orphan-sweep step.

Trim the Best Practices and Common Mistakes lists to only items not already self-evident from the code, or fold them into inline comments.

Move the full class implementations into reference files (e.g. references/stream-registry.ts) and keep SKILL.md as a concise overview with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The executable code earns its tokens, but the "Best Practices" and "Common Mistakes" sections largely restate what the code already demonstrates, and "Core Concepts" repeats the frontmatter description.	2 / 3
Actionability	Provides complete, copy-paste-ready TypeScript classes (StreamRegistry, CompletionStore, StreamGuardian) plus a working SSE endpoint and a client recovery hook — fully executable rather than pseudocode.	3 / 3
Workflow Clarity	The components are documented individually but never assembled into a sequenced end-to-end workflow, and the orphan-cleanup batch operation has no explicit validation/feedback checkpoint, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	No bundle files exist and the body is organized into clear sections, but all implementation code is inlined in SKILL.md where it could be split into referenced reference files; navigation is flat rather than one-level-deep.	2 / 3
	Total	9 / 12 Passed

Description

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 specific and occupies a clear niche, but it is written as a feature inventory rather than a user-facing trigger and lacks an explicit "Use when..." clause. Tightening the jargon and adding natural trigger terms would raise completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g. "Use when building server-sent events (SSE) streams that must survive client disconnects, recover missed completion events, or avoid resource leaks from abandoned streams."

Replace internal jargon ("completion store for terminal events", "background guardian process") with terms users actually say, such as "persist final results for reconnection" and "background cleanup of dead streams".

Spell out "SSE / server-sent events" so the description matches natural user phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "stream registry", "heartbeat monitoring", "completion store for terminal events", and "automatic orphan cleanup via background guardian process" — rather than vague abstractions.	3 / 3
Completeness	It clearly answers "what" the skill does but provides no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	It names relevant terms (SSE, stream, heartbeat, orphan cleanup) but leans on internal jargon like "completion store for terminal events" and "background guardian process", and omits common user phrasings such as "server-sent events", "reconnect", or "recovery".	2 / 3
Distinctiveness Conflict Risk	The SSE-stream-resilience niche scoped to Redis-backed stream management is distinct and unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: majiayu000/claude-skill-registry
Commit: cb3ef45

Reviewed: about 18 hours ago

Table of Contents

Discovery Implementation Validation

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.