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.

2.93x

Quality

91%

Does it follow best practices?

Impact

94%

2.93x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%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 body is highly actionable with copy-paste-ready commands and code, well-sequenced setup and worker-build workflows, and a useful verification checklist. It loses points only for minor verbosity (ADR decision chain) and a monolithic structure with broken relative links rather than split reference files.

Suggestions

Trim or move the 'Decision Chain (compressed ADRs)' table into a separate reference file — it adds tradeoff context but competes with the context window for readers who just need to set up Inngest.

Fix or remove the broken relative links (e.g. /adrs/0010-system-loop-gateway, /adrs/0029-colima-talos-migration, /joel-deploys-k8s) since no such bundle files exist; either point to real reference files or drop the links.

Add an explicit inline validate-then-fix feedback loop after each Setup Tier (e.g. 'If the dashboard is unreachable, check container logs with docker logs inngest and re-run') to lift workflow clarity to the top anchor.

Dimension	Reasoning	Score
Conciseness	Largely lean and concrete (docker commands, k8s YAML, TypeScript worker, gotchas) with only minor over-explanation such as the opening restatement of the description and the ADR decision-chain table; not 5 because the ADR table and narrative paragraphs are extra context that does not fully earn its tokens, but more efficient than the 3-anchor's unnecessary explanation.	4 / 5
Actionability	Fully executable, copy-paste-ready code and commands throughout — docker run one-liners, a complete StatefulSet+Service manifest, a full typed worker (client, function, serve), curl test invocation, and launchd plist — with examples covering the common cases (event chaining, concurrency keys, cron, claim-check); matches the 5-anchor.	5 / 5
Workflow Clarity	Clear numbered sequences (Setup Tiers 1–3, Build a Worker Steps 1–6) plus inline checkpoints ('Open http://localhost:8288 — you should see the dashboard') and a Verification checklist including a kill/restart resume test; not 5 because the setup tiers lack explicit validate-then-fix feedback loops inline, and not 3 because checkpoints and a checklist are present.	4 / 5
Progressive Disclosure	Well-organized with clear section headers (Before You Start, Intent Alignment, Setup Tiers, Build a Worker, Patterns, Gotchas, Verification) and signaled references (ADR table, Credits); not 5 because content is monolithic with full manifests/plists inlined rather than split into reference files and several ADR links are relative/broken, but better structured than the 3-anchor.	4 / 5
	Total	17 / 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.

The description is exemplary: third-person voice, concrete multi-action scope, an explicit 'Use when' clause with rich natural triggers, and a distinct named-product niche. It hits the top anchor on every dimension with no verbosity.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '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' — giving comprehensive coverage; not the 4-anchor because the scope spans several distinct concrete actions rather than having minor gaps.	5 / 5
Completeness	Explicitly answers both what (self-hosted durable background task manager, Q&A intent matching, Docker-to-k8s deployment) and when via a literal 'Use when:' clause with concrete trigger phrases; matches the 5-anchor exactly.	5 / 5
Trigger Term Quality	Provides comprehensive natural triggers — 'set up inngest', 'background tasks', 'durable workflows', 'self-host inngest', 'event-driven functions', 'cron jobs', 'local workflow engine' — covering synonyms and user phrasings; not 4 because the set is exhaustive rather than missing common variations.	5 / 5
Distinctiveness Conflict Risk	Targets a named product (Inngest) on a specific platform (macOS) with dedicated triggers, giving a clear niche and minimal conflict risk; not 4 because the named-product scope leaves little overlap with adjacent skills.	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: 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.