inngest-local

Set up self-hosted Inngest on macOS as a durable background task manager for AI agents. Interactive Q&A to match intent — from Docker one-liner to full k8s deployment with persistent state. Use when: 'set up inngest', 'background tasks', 'durable workflows', 'self-host inngest', 'event-driven functions', 'cron jobs', or any request for a local workflow engine.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

87%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.

A well-organized, highly actionable skill body with clear multi-step workflows, explicit verification checkpoints, and sensible sectioning; minor trimming of restated gotchas and offloading of the large k8s/launchd blocks would push it to fully lean.

Suggestions

Consolidate the k8s Service-naming gotcha so it appears once (either the inline ⚠️ note or the Gotchas #3 entry) rather than restated in YAML comments, prose, and the Gotchas list — this trims repeated content.

Consider moving the full k8s StatefulSet/Service YAML and the launchd plist into referenced files (e.g. inngest-k8s.yaml, worker.plist) linked from the body, reducing inlined bulk and improving progressive disclosure.

The Decision Chain table references external ADRs (/adrs/...) and joelclaw.com paths that are not part of the bundle; either confirm these resolve for the end user or note they are optional context so navigation expectations stay accurate.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence — every code block earns its place and avoids explaining what Inngest/Docker/k8s are — though the Decision Chain table and a few explanatory asides (e.g. the GOTCHA callouts restated in both inline comments and prose) could be trimmed slightly.	4 / 5
Actionability	Fully executable guidance throughout: copy-paste-ready bash, TypeScript, YAML, XML, and curl examples cover the common cases (docker run, worker init, client setup, function authoring, serving, testing, launchd persistence).	5 / 5
Workflow Clarity	Multi-step processes are clearly sequenced with validation checkpoints — the Setup Tiers and Build a Worker sections are numbered steps, the Gotchas encode failure modes, and the Verification checklist provides explicit feedback loops (kill worker mid-function → restart → confirm resume).	5 / 5
Progressive Disclosure	Good structure with well-labeled sections (Before You Start, Intent Alignment, Setup Tiers, Patterns, Verification) and a couple of one-level-deep references (ADR links, the external setup script); most content is appropriately inline, but the k8s YAML and launchd plist blocks are sizeable inlined material that could live in separate files, keeping it just short of a 5.	4 / 5
	Total	18 / 20 Passed

Description

100%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, third-person description that concretely states what the skill does and when to invoke it, with a rich set of natural trigger phrases and minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Names the domain and lists multiple concrete actions — 'Set up self-hosted Inngest', 'durable background task manager', 'Interactive Q&A', 'persistent state', spanning 'Docker one-liner to full k8s deployment' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (set up self-hosted Inngest as a durable background task manager with interactive Q&A across deployment tiers) and 'when' via a clear 'Use when:' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides comprehensive natural trigger phrases including synonyms and quoted user utterances — 'set up inngest', 'background tasks', 'durable workflows', 'self-host inngest', 'event-driven functions', 'cron jobs', 'local workflow engine'.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (self-hosted Inngest on macOS for AI agents) with distinct, specific triggers unlikely to collide with other skills; the k8s/Docker-tier framing further narrows its scope.	5 / 5
	Total	20 / 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: 6 suspicious	Warning

	Total	14 / 16 Passed

Repository: joelhooks/joelclaw
Path: skills/inngest-local/SKILL.md
Commit: 7094ced

Reviewed: 3 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.