CtrlK
BlogDocsLog inGet started
Tessl Logo

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

2.93x
Quality

88%

Does it follow best practices?

Impact

94%

2.93x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

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 (sets up self-hosted Inngest with various deployment options), when to use it (explicit 'Use when' clause with diverse trigger terms), and occupies a distinct niche. It uses proper third-person voice and provides concrete deployment scenarios without being overly verbose.

DimensionReasoningScore

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, from Docker to k8s) and 'when' (explicit 'Use when:' clause with multiple trigger phrases). Both are well-articulated.

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). The combination of product name, deployment styles, and domain-specific terms 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 highly actionable and well-structured skill with excellent executable examples across multiple deployment tiers. Its main weakness is length — at ~300 lines it tries to be both overview and comprehensive reference, when the k8s manifests, patterns, launchd config, and ADR table would be better as linked files. The Intent Alignment Q&A section is a nice touch for interactive use but adds bulk.

Suggestions

Move the k8s manifest, launchd plist, and patterns section to separate referenced files (e.g., K8S.md, PATTERNS.md, LAUNCHD.md) to keep SKILL.md as a lean overview

Move the Decision Chain ADR table to a separate file or remove it — it's context for humans, not actionable guidance for Claude

DimensionReasoningScore

Conciseness

The skill is fairly comprehensive but includes some sections that add bulk without proportional value — the Intent Alignment Q&A section, the Decision Chain ADR table, and the Credits section are verbose for a skill file. The core technical content is reasonably efficient, but the overall document is long (~300 lines) and could be tightened by moving patterns, k8s config, and ADRs to separate files.

2 / 3

Actionability

Excellent actionability throughout — every tier has copy-paste-ready commands, the worker setup is fully executable TypeScript with complete files, the k8s manifest is deployable, and even the test/verification steps include concrete curl commands. The signing key generation, launchd plist, and setup script are all immediately usable.

3 / 3

Workflow Clarity

The multi-step workflow is clearly sequenced across tiers (1→2→3), the worker build process has explicit numbered steps (1-6), and there's a verification checklist at the end with specific checkpoints including failure recovery testing ('Kill the worker mid-function — restart worker, function resumes'). The gotchas section serves as an error-recovery guide.

3 / 3

Progressive Disclosure

The skill has good structural organization with clear headers and tiered setup, but it's monolithic — the k8s manifest, patterns section, launchd plist, and ADR table could all be in separate referenced files. The document is quite long for a SKILL.md and would benefit from splitting detailed configs into linked files while keeping the overview lean.

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
joelhooks/joelclaw
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.