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

90%

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

88%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 body is a highly actionable operations runbook: exact commands, environment-specific facts, explicit priority ordering, and symptom-to-fix recovery guidance, with references that resolve to real bundle files. Its main gaps are moderate length with large inline tables that could be split into a reference file, and a dated migration caveat that will age.

Dimension	Reasoning	Score
Conciseness	The body is dense with environment-specific operational facts (IPs, ports, MTU, NFS options, launchd labels) that Claude could not know, so most tokens earn their place; however, the dated "Migration caveat — 2026-07-09" block and the 16-component full-health table (which largely restates what health.sh reports) could be trimmed or split, matching 'efficient; minor instances of over-explanation'.	4 / 5
Actionability	Guidance is fully executable and copy-paste ready: exact invocations like "POSTBOOT_NAS_BENCHMARK_MIB=1 .../scripts/postboot.sh", a complete "bun scripts/agent-session-audit-backup.ts --hosts flagg,blaine,panda ..." command with all flags, and concrete fix commands ("joelclaw inngest restart-worker --register", "kubectl rollout restart deployment/bluesky-pds -n joelclaw") covering the common cases, matching the level-5 anchor.	5 / 5
Workflow Clarity	Sequences are clear with explicit validation and prioritization: the critical-vs-warning check table acts as a checklist, "If postboot.sh fails, fix critical failures first. Do not chase warning/reference failures before the required path is green" gives an explicit checkpoint, and the Inngest hung-run triage gives a numbered verify-then-fix loop with symptom-keyed recovery guidance in "Fixing Common Issues", matching the level-5 anchor.	5 / 5
Progressive Disclosure	Structure is good: well-organized sections, references to the real bundle scripts scripts/postboot.sh and scripts/health.sh (both present in ./scripts/), and one-level-deep pointers to sibling skills ("agent-session-capture-backup", promote-facts targets). It is not level 5 because the body is a ~210-line monolith with large inline check tables and fix recipes that would fit better in a separate reference file, per the guideline to score against the actual bundle structure.	4 / 5
	Total	18 / 20 Passed

Description

91%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 description that clearly states what the skill does, enumerates concrete check surfaces, and gives an explicit, natural-language 'Use when' clause with varied trigger phrases. The only weaknesses are a single repeated action verb and a few broadly generic trigger terms that could collide with sibling operations skills.

Dimension	Reasoning	Score
Specificity	"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" enumerates many concrete check surfaces with comprehensive coverage, but the action itself is a single one (running checks) rather than multiple distinct concrete actions, matching the 'several specific actions; minor gaps' anchor rather than the level-5 anchor's multiple distinct verbs.	4 / 5
Completeness	It explicitly answers 'what' (comprehensive joelclaw health checks across a named list of surfaces) and 'when' with concrete quoted trigger phrases plus "or at session start to orient", matching the level-5 anchor that requires both what and when with concrete triggers.	5 / 5
Trigger Term Quality	"Use when: 'system health', 'postboot check', 'daily system check', 'health check', 'is everything working', 'system status', 'how's the system', 'check everything'" provides comprehensive natural phrases a user would actually say, including synonyms and casual variants, matching the level-5 anchor; it is not merely a shorter keyword list as at level 4.	5 / 5
Distinctiveness Conflict Risk	The "joelclaw" niche and named subsystems make it mostly distinct, but generic triggers like 'health check', 'system status', and 'check everything' could overlap with a closely related diagnostics/operations skill, matching the 'minor overlap risk' anchor at level 4 rather than level 5's minimal-conflict profile.	4 / 5
	Total	18 / 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: aa0116c

Reviewed: 8 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.