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.
90
88%
Does it follow best practices?
Impact
94%
2.93xAverage score across 3 eval scenarios
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 skill description that clearly identifies a specific product and use case, provides concrete deployment options as capabilities, and includes an explicit 'Use when' clause with comprehensive trigger terms. The description is concise yet informative, uses third-person voice correctly, and would be easily distinguishable from other skills in a large collection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions and deployment options: 'Set up self-hosted Inngest on macOS', 'Docker one-liner', 'full k8s deployment with persistent state', 'Interactive Q&A to match intent'. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (set up self-hosted Inngest on macOS as a durable background task manager, from Docker to k8s) and 'when' with an explicit 'Use when:' clause listing multiple trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'set up inngest', 'background tasks', 'durable workflows', 'self-host inngest', 'event-driven functions', 'cron jobs', 'local workflow engine'. These are terms users would naturally use when seeking this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific product (Inngest), a specific platform (macOS), and a specific use case (self-hosted durable workflow engine). Terms like 'inngest' and 'durable workflows' are niche enough to avoid conflicts with generic task or deployment skills. | 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 examples across all three deployment tiers and a complete worker implementation. Its main weaknesses are length (the Intent Alignment Q&A, ADR table, and Credits add bulk without proportional value for Claude) and the monolithic structure that could benefit from splitting detailed content into referenced files. The gotchas section is genuinely valuable with hard-won debugging knowledge.
Suggestions
Move the Intent Alignment Q&A section to a separate file or remove it — Claude can determine user intent without a scripted questionnaire, and this adds ~20 lines of non-technical content.
Split the k8s manifest (Tier 3) and launchd plist into referenced files (e.g., `inngest-k8s.yaml` and `inngest-worker.plist`) to keep the main skill focused on the common path.
Remove or compress the Decision Chain / ADR table — it provides architectural context but isn't actionable for setting up Inngest. A single line linking to an ADR index would suffice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly efficient but includes some unnecessary sections like the Intent Alignment Q&A (which is more of a conversational script than actionable instruction), the Decision Chain ADRs table, and the Credits section. The core technical content is well-written but the overall document could be tightened by ~30%. | 2 / 3 |
Actionability | Excellent actionability throughout — every tier has copy-paste-ready commands, the worker build is a complete 6-step walkthrough with executable TypeScript, the k8s manifest is deployable, and even the launchd plist is fully specified. The signing key generation, curl test command, and setup script are all immediately usable. | 3 / 3 |
Workflow Clarity | The multi-step processes are clearly sequenced (tiered setup, 6-step worker build), with explicit validation via the Verification checklist that includes testing resumption after kill, persistence after restart, and reboot survival. The gotchas section serves as error-recovery guidance, and the tier progression provides a natural escalation path. | 3 / 3 |
Progressive Disclosure | The document is quite long (~300 lines) with everything inline — the patterns section, k8s manifests, launchd plists, and ADR table could be split into referenced files. There are some references to external ADRs and blog posts, but the core content itself would benefit from being split into a quick-start overview with links to detailed tier guides and pattern references. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%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
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.