joelclaw-system-check

Run comprehensive joelclaw health checks, including postboot/daily checks for NAS, MinIO, Convex, Postgres, Typesense, Inngest, Panda/Flagg authority split, k8s, worker, Redis, OTEL, tests, repo sync, memory pipeline, and disk. Use when: 'system health', 'postboot check', 'daily system check', 'health check', 'is everything working', 'system status', 'how's the system', 'check everything', or at session start to orient.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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.

A highly actionable, well-structured operational skill that leans on real bundled scripts for executable detail and provides clear triage and fix feedback loops. Its main weakness is moderate verbosity from a dated migration-vision narrative and inline time-sensitive configuration.

Suggestions

Move the 2026-07-09 migration caveat and lane-vision narrative into a clearly marked 'Migration / deprecated assumptions' section or a separate reference file so the core check workflow stays lean.

Factor the 16-component health table and the fix recipes into a references/ file (e.g. HEALTH-COMPONENTS.md) referenced one level deep, keeping SKILL.md as a tighter overview.

Pull volatile IP addresses, ports, and mount paths into named variables or a config reference so the prose does not decay when topology changes.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational, avoiding beginner-concept padding, but the dated migration caveat narrative and inline time-sensitive config (specific IPs, ports, the 2026-07-09 lane-vision prose) could be trimmed or moved to a deprecated/caveat section, keeping it just below the lean anchor.	4 / 5
Actionability	Provides copy-paste-ready commands throughout (env-var-prefixed script invocations, exact kubectl/curl/joelclaw CLI commands, a fully flagged bun script call) covering postboot, health, transcript review, backup audit, fixes, and hung-run triage.	5 / 5
Workflow Clarity	Sequenced procedures with checkpoints exist (the Inngest hung-run triage is a 4-step validate-then-advance loop, and fix recipes give feedback loops), plus a critical/warning triage priority, but the overall skill is a collection of procedures rather than one master workflow with validation at every stage.	4 / 5
Progressive Disclosure	SKILL.md acts as an overview pointing to the executable detail in scripts/postboot.sh and scripts/health.sh (both real bundle files), with summary tables and section headers; minor gaps are inlined fix recipes and external skill references listed without a dedicated references directory.	4 / 5
	Total	17 / 20 Passed

Description

95%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, well-scoped description that clearly answers both what the skill does and when to use it, with rich natural-language triggers and low conflict risk. The only minor weakness is that the action verb is essentially 'run checks' across many surfaces rather than a diverse set of distinct operations.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete check targets (NAS, MinIO, Convex, Postgres, Typesense, Inngest, k8s, worker, Redis, OTEL, repo sync, memory pipeline, disk), but the underlying action is uniform ('run health checks') rather than a set of distinct concrete operations like extract/fill/merge, so it sits just below the comprehensive-action anchor.	4 / 5
Completeness	Explicitly states what it does ('Run comprehensive joelclaw health checks, including...') and when to use it with concrete trigger phrases, satisfying both the 'what' and 'when' requirements.	5 / 5
Trigger Term Quality	Includes a rich set of natural phrases a user would actually say ('system health', 'health check', 'is everything working', 'how's the system', 'check everything', 'at session start to orient') with synonym coverage, matching the comprehensive natural-terms anchor.	5 / 5
Distinctiveness Conflict Risk	Scoped tightly to the 'joelclaw' system with system-specific triggers, giving it a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	19 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: joelhooks/joelclaw
Path: skills/joelclaw-system-check/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.