CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

68%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.

An exceptionally lean, policy-focused body that respects the token budget but operates at a high level of abstraction. It names the right constraints and verification concerns yet gives no concrete commands or an explicit step sequence, leaving Claude to reconstruct the how.

Suggestions

Add concrete executable anchors: the actual installer invocation, the live-help command, and an example health-check command, so 'use the current repository installer' becomes actionable.

Make the workflow explicit as a short numbered sequence (read state → confirm scope → install → discover config → verify → report) with the verification step as a named checkpoint.

Add 2-3 section headers (e.g., 'Scope', 'Install', 'Verify') to give the prose body light structure without adding length.

DimensionReasoningScore

Conciseness

The ~200-word body is pure directive prose with zero padding and no explanation of concepts Claude already knows ('Never create a second poller, socket listener, gateway session...'), so every token earns its place as in the anchor-5 example.

5 / 5

Actionability

Concrete referents exist ('Read `gateway` and the existing service ownership configuration', 'Use the current repository installer and live help') but there are no commands, paths, or executable steps — 'Verify credentials through the owning secret mechanism' and 'Discover current endpoint and model configuration' leave the how unspecified, matching anchor 3 rather than 4.

3 / 5

Workflow Clarity

A rough sequence is implied by paragraph order (read current state → infer scope → install → discover config → verify → report) and verification is mentioned ('Verify readiness, event correlation, and supported health checks'), but the sequence is never made explicit and checkpoints are implicit, matching anchor 3 ('sequence present but checkpoints missing or implicit') rather than 4.

3 / 5

Progressive Disclosure

The 13-line body keeps all content appropriately inline with no nested references (the bundle contains only logo assets, and `gateway` points to a repo artifact, not a bundled file); the only organization gap is the absence of section headers, keeping it at anchor 4 rather than the well-sectioned anchor-5 case.

4 / 5

Total

15

/

20

Passed

Description

86%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.

A strong description with excellent trigger-term coverage and an explicit what/when structure. Its main deductions are the second-person phrasing ('match your intent'), which costs specificity, and slightly broad trigger terms that create minor conflict risk.

Suggestions

Rewrite in third person: replace 'Interactive Q&A to match your intent' with 'Interactive Q&A to match user intent' to recover the specificity penalty.

Tighten the broad triggers: qualify 'agent notifications' (e.g., 'agent notifications via Telegram through the gateway') to reduce overlap with generic notification skills.

DimensionReasoningScore

Specificity

The description lists several concrete capabilities ('Redis event bridge, heartbeat monitoring, and multi-session routing', 'from minimal (Redis + extension) to full (embedded daemon + Telegram + watchdog)'), matching anchor 4, but the second-person phrase 'Interactive Q&A to match your intent' triggers the rubric's third-person voice penalty of 1, reducing it to 3.

3 / 5

Completeness

It explicitly answers both what ('Set up a persistent AI agent gateway on macOS with Redis event bridge...') and when (a 'Use when:' clause with concrete quoted trigger phrases), matching the anchor-5 example pattern.

5 / 5

Trigger Term Quality

The 'Use when' clause quotes natural user phrasing ('set up a gateway', 'I want my agent always on', 'agent notifications') plus synonyms ('persistent', 'always on', 'reachable') and a catch-all, giving comprehensive coverage of terms a user would naturally say.

5 / 5

Distinctiveness Conflict Risk

The Redis/heartbeat/gateway niche is clearly distinct, but the broad trigger 'agent notifications' and 'make an AI agent persistent and reachable' create minor overlap risk with generic notification or daemon-management skills, matching anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

joelhooks/joelclaw

Path

skills/gateway-setup/SKILL.md

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.