gateway-setup

Set up a persistent AI agent gateway on macOS with Redis event bridge, heartbeat monitoring, and multi-session routing. Interactive Q&A to match your intent — from minimal (Redis + extension) to full (embedded daemon + Telegram + watchdog). Use when: 'set up a gateway', 'I want my agent always on', 'event bridge', 'heartbeat monitoring', 'agent notifications', or any request to make an AI agent persistent and reachable.

2.08x

Quality

88%

Does it follow best practices?

Impact

96%

2.08x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong description that clearly communicates a specific, niche capability with concrete actions, explicit trigger guidance, and distinctive terminology. It covers both the 'what' and 'when' thoroughly, and the domain is narrow enough to avoid conflicts with other skills. The description is detailed without being unnecessarily verbose.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'persistent AI agent gateway on macOS', 'Redis event bridge', 'heartbeat monitoring', 'multi-session routing', 'embedded daemon', 'Telegram', 'watchdog'. Also describes the interactive Q&A approach and the range from minimal to full setup.	3 / 3
Completeness	Clearly answers both 'what' (set up a persistent AI agent gateway with Redis, heartbeat, multi-session routing, interactive Q&A for configuration) and 'when' (explicit 'Use when:' clause with multiple trigger phrases and a catch-all condition).	3 / 3
Trigger Term Quality	Includes a rich set of natural trigger terms: 'set up a gateway', 'agent always on', 'event bridge', 'heartbeat monitoring', 'agent notifications', 'persistent and reachable'. These cover a good range of how users might phrase such requests.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche — persistent AI agent gateway on macOS with Redis event bridge is very specific and unlikely to conflict with other skills. The combination of macOS, Redis, heartbeat monitoring, and Telegram integration creates a clear, unique identity.	3 / 3
	Total	12 / 12 Passed

Implementation

77%

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

This is a highly actionable and well-structured skill with excellent executable code examples and clear multi-step workflows across four tiers. Its main weakness is length — at ~400 lines it tries to be both an overview and a complete implementation guide, when the detailed tier implementations and ADR history could be split into referenced files. The intent alignment questions and verification checklist are strong additions that demonstrate thoughtful design.

Suggestions

Move Tier 2-4 implementation details into separate files (e.g., TIER2-HEARTBEAT.md, TIER3-MULTISESSION.md) and keep SKILL.md as a concise overview with links to each tier's guide.

Move the Decision Chain ADR table and Known Limitations into a separate ARCHITECTURE.md or DECISIONS.md file, referenced from the main skill.

Dimension	Reasoning	Score
Conciseness	The skill is quite long (~400 lines) and includes some sections that could be trimmed (Credits, Decision Chain ADRs, explanations of why two ioredis clients are needed). However, most content is substantive code and configuration rather than padding. The tiered architecture justifies length but some sections like the ADR table and Known Limitations could be in separate files.	2 / 3
Actionability	Excellent actionability throughout — fully executable TypeScript code for the extension, complete package.json, working bash commands for cron/Redis/tmux/launchd, and a verification checklist with concrete redis-cli test commands. Code is copy-paste ready with real imports and types.	3 / 3
Workflow Clarity	Each tier has clearly numbered build steps that build on the previous tier. The verification checklist provides explicit validation checkpoints per tier. Critical setup notes at the top catch common failure modes (GATEWAY_ROLE, serveHost, ioredis issues). The Known Limitations section honestly documents the drain race condition and other edge cases.	3 / 3
Progressive Disclosure	The tiered architecture provides good conceptual progressive disclosure, and ADR references point to separate files. However, the skill itself is monolithic — Tiers 2-4 code, the ADR table, Known Limitations, and Credits are all inline when they could be split into separate files. The Intent Alignment Q&A section is well-placed but the overall file is very long for a SKILL.md overview.	2 / 3
	Total	10 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: joelhooks/joelclaw
Commit: 825972c

Reviewed: 7 days 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.