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 communicates what the skill does (set up self-hosted Inngest with various deployment options), when to use it (explicit trigger terms covering multiple natural phrasings), and differentiates itself through specific product and platform references. It uses proper third-person voice and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions and deployment options: '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, interactive Q&A, Docker to k8s deployment) and 'when' (explicit 'Use when:' clause with multiple trigger phrases). | 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 tool (Inngest), a specific platform (macOS), and a specific use case (self-hosted durable workflow engine). The combination of product name and deployment context makes conflicts with other skills very unlikely. | 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 strong, highly actionable skill with excellent executable examples across three deployment tiers and a complete worker tutorial. The workflow is clear with good validation checkpoints and hard-won gotchas. Main weaknesses are the monolithic structure (no bundle files for offloading detail) and some token inefficiency from the Decision Chain table, Credits section, and Intent Alignment Q&A that could be more compact.
Suggestions
Split the k8s manifest, launchd plist, and patterns into separate bundle files (e.g., K8S.md, LAUNCHD.md, PATTERNS.md) and reference them from the main skill to improve progressive disclosure.
Trim or remove the Decision Chain/Credits sections — these serve the author's documentation needs more than Claude's task execution. Move to a separate CONTEXT.md if needed.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good code examples and practical content, but includes some unnecessary sections (Credits, Decision Chain ADRs, Setup Script for a personal URL) and the Intent Alignment Q&A section adds bulk that could be trimmed. The gotchas section is valuable but slightly verbose. | 2 / 3 |
Actionability | Excellent actionability throughout — every tier has copy-paste-ready Docker/k8s commands, the worker build is a complete 6-step walkthrough with fully executable TypeScript, and patterns section provides concrete code for common use cases. The signing key generation, curl test command, and launchd plist are all immediately usable. | 3 / 3 |
Workflow Clarity | The tiered setup is clearly sequenced with explicit validation via the verification checklist at the end. The worker build follows a clear 6-step sequence. The 'What happens on reboot' section explicitly describes the recovery flow. The gotchas section serves as error-recovery guidance for known failure modes. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical sections, but it's a long monolithic file (~300 lines) with no bundle files to offload detail into. The k8s YAML, launchd plist, and patterns sections could be split into separate referenced files. ADR links reference paths that don't exist in the bundle. | 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
03f0a59
- 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.