Tessl • The management layer for AI agent skills

SkillPublic

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

85%

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

75%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 exceptionally actionable — every check and fix is a concrete, executable command with expected green/red outcomes and clear failure-prioritization guidance. Its weaknesses are token efficiency (a dated migration-caveat narrative, repeated absolute paths, and verbose transcript-review instructions) and inline bulk detail that could move to reference files.

Suggestions

Trim or relocate the dated 'Migration caveat — 2026-07-09' section into a deprecated/old-patterns note and compress it to the lane-based TODO list, removing narrative commentary about the migration vision.

State each script path once and reference it thereafter (e.g., use bundle-relative paths like scripts/postboot.sh instead of repeating the full ~/Code/joelhooks/joelclaw-runtime/... absolute path for every invocation).

Move the 16-component full-health table and the Inngest hung-run triage into a reference file, keeping SKILL.md as a lean overview with clearly signaled one-level-deep links, and add an explicit 're-run postboot.sh to verify the fix' step to the Fixing Common Issues section.

Dimension	Reasoning	Score
Conciseness	The content is dense with genuinely non-obvious operational specifics, but the dated 'Migration caveat — 2026-07-09' meta-commentary, the repeated absolute script paths for the same commands, and the lengthy transcript-review prose could all be tightened; the time-sensitive migration narrative is not placed in a deprecated/old-patterns section, so the mostly-efficient-but-could-be-tighter 3 anchor fits better than 4.	3 / 5
Actionability	Fully copy-paste ready throughout: exact script invocations with env flags (POSTBOOT_NAS_BENCHMARK_MIB=1 ... postboot.sh), a complete audit command with all flags (--hosts flagg,blaine,panda ... --replay-max-bytes 10485760), and precise fix commands (kubectl rollout restart deployment/bluesky-pds -n joelclaw), matching the 5 anchor's executable-with-common-cases coverage.	5 / 5
Workflow Clarity	Clear sequencing with an explicit prioritization checkpoint ('If postboot.sh fails, fix critical failures first. Do not chase warning/reference failures before the required path is green'), green/yellow/red validation tables, and a numbered hung-run triage with an error-recovery path — but there is no explicit re-run-to-verify loop after applying a fix, so it sits between the 4 and 5 anchors, clearly above 3.	4 / 5
Progressive Disclosure	Well-sectioned body whose two script references (scripts/postboot.sh, scripts/health.sh) are real one-level-deep bundle files, but large detail blocks (the 16-component health table, triage procedures) are inlined rather than split into reference files and invocations use absolute home paths instead of clearly signaled bundle-relative links — good structure with minor organization gaps, matching the 4 anchor.	4 / 5
	Total	16 / 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: it names a distinct system niche, comprehensively enumerates the checked surfaces, and supplies an explicit 'Use when' clause with natural trigger phrases plus session-start orientation. Its only weaknesses are the single generic action verb ('run health checks') and a few overly broad triggers.

Dimension	Reasoning	Score
Specificity	Enumerates ~14 concrete check targets ('NAS, MinIO, Convex, Postgres, Typesense, Inngest, Panda/Flagg authority split, k8s, worker, Redis, OTEL, tests, repo sync, memory pipeline, and disk'), but the only action verb is 'Run ... health checks' — a single action type rather than the multiple distinct concrete actions of the 5 anchor, so anchor 4 fits best.	4 / 5
Completeness	Explicitly answers both: what ('Run comprehensive joelclaw health checks, including postboot/daily checks for [enumerated surfaces]') and when ('Use when: ... or at session start to orient') with concrete trigger phrases, exactly matching the 5 anchor.	5 / 5
Trigger Term Quality	Comprehensive natural-language triggers users would actually say — 'health check', 'is everything working', 'system status', 'how's the system', 'check everything', 'postboot check', 'daily system check' — plus session-start orientation, matching the 5 anchor's synonym coverage; not 4 because no common variation is missing.	5 / 5
Distinctiveness Conflict Risk	The 'joelclaw' namespace carves a clear niche with low conflict risk, but broad triggers like 'check everything' and 'is everything working' could overlap other diagnostic/ops skills — mostly distinct with minor overlap risk, matching the 4 anchor rather than the minimal-conflict 5 anchor.	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
Revision: 1fb2468

Reviewed: 5 days ago

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.

joelclaw-system-check

Table of Contents

Is this your skill?