gateway

Operate the joelclaw gateway daemon — the always-on pi session that receives events, notifications, and messages. Use the joelclaw CLI for ALL gateway operations. Use when: 'restart gateway', 'gateway status', 'is gateway healthy', 'push to gateway', 'gateway not responding', 'telegram not working', 'messages not going through', 'gateway stuck', 'gateway debug', 'check gateway', 'drain queue', 'test gateway', 'stream events', or any task involving the gateway daemon.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

71%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 highly actionable with concrete commands, code, and a triage workflow that has real checkpoints, but it is a long monolithic reference that doesn't use progressive disclosure to offload deep runtime detail into separate files. Tightening or splitting the ADR-rank-slice sections would improve both conciseness and organization.

Suggestions

Move the deep rank-5/rank-6 ADR-slice detail (operator ack/timeout tracing, channel runtime contracts, low-signal guardrails) into reference files under references/ and keep SKILL.md as a concise overview with one-level-deep links.

Add an explicit validation/verification step after destructive or batch operations such as `joelclaw gateway drain` (e.g., confirm `events` is empty afterward).

Trim the verbose low-signal operator-spam guardrail bullet list to the operator-actionable rules, or relocate the full rationale to a reference doc, to reduce token cost without losing the actionable guidance.

Dimension	Reasoning	Score
Conciseness	The ~330-line body is information-dense and avoids explaining concepts Claude already knows, but several sections (e.g., the long "Channel runtime contracts" low-signal guardrail bullet list and the rank-5/rank-6 ADR slices) carry deep runtime internals that could be tightened or offloaded; not 4 because the over-detail is more than minor, not 2 because it is not padded with generic explanation.	3 / 5
Actionability	Provides copy-paste-ready CLI commands (doctor/status/restart/test/push/drain/stream/channel/behavior), two complete TypeScript examples (Inngest middleware notify and pushGatewayEvent), and a symptom/cause/fix table covering common cases.	5 / 5
Workflow Clarity	The Quick Triage section gives an explicit ordered sequence ("Run in order, stop at first failure") with numbered steps and validation via `doctor --live`, plus a feedback loop (pending > 0 persisting → restart); not 5 because some destructive/batch operations like `drain` lack explicit validation guidance and restart is offered as a fix in several places without a verification step.	4 / 5
Progressive Disclosure	The body has clear section headers and tables, but the bundle has no reference files (references/ and scripts/ are empty; assets are unreferenced logos), so deep ADR-slice detail that belongs in separate files is inlined in a 330-line overview rather than split into one-level-deep references; not 4 because the absence of any reference offloading for a skill this large is a real organization gap.	3 / 5
	Total	15 / 20 Passed

Description

95%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 third-person, specific, and rich with natural trigger phrases, clearly stating both what the skill does and when to use it. Its only weakness is that concrete actions are conveyed through the trigger list rather than a dedicated action enumeration, leaving slight specificity gaps.

Dimension	Reasoning	Score
Specificity	Names the domain ("Operate the joelclaw gateway daemon — the always-on pi session that receives events, notifications, and messages") and enumerates several concrete operations (restart, status, push, drain, test, stream) via the trigger list, but the actions are surfaced through triggers rather than a clean declarative action list, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both "what" (operate the gateway daemon via the joelclaw CLI) and "when" (a long explicit "Use when:" clause with concrete trigger phrases), matching the anchor that requires both with concrete triggers.	5 / 5
Trigger Term Quality	Comprehensive natural-language triggers with synonyms ("gateway not responding", "gateway stuck", "telegram not working", "messages not going through", "drain queue", "stream events") that an operator would naturally say; not score 4 because the synonym coverage is broad rather than missing only a few.	5 / 5
Distinctiveness Conflict Risk	Targets a clearly proprietary niche ("joelclaw gateway daemon") with distinct triggers and minimal overlap risk with other skills; no generic phrasing that would fire for unrelated tasks.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: joelhooks/joelclaw
Path: skills/gateway/SKILL.md
Commit: d952451

Reviewed: 4 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.