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.

The content is a strong, highly actionable operational runbook: concrete commands, validation tables, and triage sequences dominate, and it correctly points heavy logic to the bundled scripts. Its main weaknesses are a dated narrative migration caveat that pads the body and inlined reference tables that could live in separate files for cleaner progressive disclosure.

Suggestions

Move the dated 'Migration caveat — 2026-07-09' rationale into a 'Deprecated / migration TODOs' section or a separate reference file so the dated, time-sensitive narrative does not pad the main runbook.

Extract the 16-component Full Health Check table and the long agent-session-audit-backup command block into a reference file (e.g. references/health-checks.md) and link to it from SKILL.md to improve progressive disclosure.

Add an explicit validate->fix->re-run loop for the postboot path (e.g. 'after fixing a critical failure, re-run postboot.sh and confirm green before moving to warning/reference checks') to lift workflow clarity to the top anchor.

Dimension	Reasoning	Score
Conciseness	The body is information-dense with non-obvious operational specifics (IPs, ports, env vars, exact paths) that Claude would not already know, but the dated 'Migration caveat — 2026-07-09' narrative and a few prose explanations could be trimmed; it is efficient with minor instances of over-explanation rather than the lean-every-token-earns-its-place anchor 5.	4 / 5
Actionability	Guidance is fully executable and copy-paste ready: full script paths with env var prefixes (POSTBOOT_NAS_BENCHMARK_MIB=1 .../postboot.sh), concrete CLI invocations with flags, and specific fix commands covering common cases, matching the anchor 5 example.	5 / 5
Workflow Clarity	Multiple workflows (postboot/daily, transcript review, full health, session-capture backup, hung-run triage) are sequenced with priority guidance and green/yellow/red validation tables, but a fully explicit validate->fix->re-run feedback loop is only implied rather than spelled out, so it sits below the anchor 5 checklist-with-feedback-loops bar.	4 / 5
Progressive Disclosure	Structure is good with clear section headers and well-signaled references to the real bundle scripts (scripts/postboot.sh, scripts/health.sh) plus pointers to sibling skills for durable facts; minor organization gaps remain because the large 16-component health table and several long fix/audit command blocks are inlined rather than split into reference files.	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.

The description is excellent: it states a clear purpose, enumerates the specific subsystems it checks, and provides a rich set of natural trigger phrases plus a session-start usage cue. The only minor weakness is that the action is framed as a single 'run checks' verb rather than several distinct actions, which keeps specificity just below the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ('joelclaw health checks') and enumerates many specific component targets (NAS, MinIO, Convex, Postgres, Typesense, Inngest, Panda/Flagg authority split, k8s, worker, Redis, OTEL, tests, repo sync, memory pipeline, disk), but the action verb is essentially a single one ('Run comprehensive... checks') rather than multiple distinct actions, leaving a minor gap versus the comprehensive-multi-action anchor 5.	4 / 5
Completeness	Explicitly answers both 'what' (Run comprehensive joelclaw health checks, including the enumerated postboot/daily checks) and 'when' (a 'Use when:' clause with concrete trigger phrases plus 'at session start to orient'), matching the anchor 5 example structure.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural phrases a user would actually say ('system health', 'postboot check', 'daily system check', 'health check', 'is everything working', 'system status', "how's the system", 'check everything') plus the 'at session start to orient' usage cue, matching the comprehensive-synonyms anchor 5.	5 / 5
Distinctiveness Conflict Risk	The skill is anchored to a clearly distinct niche ('joelclaw' system with Panda/Flagg authority split) and uses uniquely targeted triggers, making conflict with other generic skills minimal.	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: 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.