joelclaw-system-check
Run a comprehensive health check of the joelclaw system — k8s cluster, worker, Inngest, Redis, Typesense/OTEL, tests, TypeScript, repo sync, memory pipeline, pi-tools, git config, active loops, disk, stale tests. Outputs a 1-10 score with per-component breakdown. Use when: 'system health', 'health check', 'is everything working', 'system status', 'how's the system', 'check everything', or at session start to orient.
92
89%
Does it follow best practices?
Impact
99%
7.07xAverage score across 3 eval scenarios
Passed
No known issues
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 an excellent skill description that hits all the marks. It provides a comprehensive list of specific components to check, clearly states the output format, and includes a well-crafted 'Use when' clause with natural trigger phrases. The system-specific naming (joelclaw) and detailed component list make it highly distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists many specific concrete components to check: k8s cluster, worker, Inngest, Redis, Typesense/OTEL, tests, TypeScript, repo sync, memory pipeline, pi-tools, git config, active loops, disk, stale tests. Also specifies the output format (1-10 score with per-component breakdown). | 3 / 3 |
Completeness | Clearly answers both 'what' (run comprehensive health check of specific components, output a 1-10 score with breakdown) and 'when' (explicit 'Use when:' clause with multiple trigger phrases and a contextual trigger for session start). | 3 / 3 |
Trigger Term Quality | Includes excellent natural trigger terms that users would actually say: 'system health', 'health check', 'is everything working', 'system status', 'how's the system', 'check everything'. Also includes the useful contextual trigger 'at session start to orient'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — it's specific to the 'joelclaw system' with a very particular set of components (k8s, Inngest, Redis, Typesense, pi-tools, etc.). The combination of system-specific naming and comprehensive component list makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill that efficiently communicates a complex 16-component health check system. The table format is an excellent choice for the component breakdown, and the fixing section provides immediately executable remediation commands. The main weakness is the lack of explicit validation/feedback loops after applying fixes — the skill should tell Claude to re-run the health check after remediation to confirm resolution.
Suggestions
Add explicit 're-run health.sh to verify fix' after each remediation command in the 'Fixing Common Issues' section to create proper feedback loops.
Add a validation step to the Inngest hung-run triage (e.g., 'After removing stale registrations, re-run `joelclaw inngest status` to confirm clean state').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. The table format is extremely efficient for conveying 16 component checks with their scoring thresholds. No unnecessary explanations of what k8s or Redis are — assumes Claude's competence throughout. | 3 / 3 |
Actionability | Provides exact executable commands for running the health check, fixing every common issue, and triaging hung Inngest runs. All commands are copy-paste ready with full paths and flags. | 3 / 3 |
Workflow Clarity | The 'When to Run' section provides clear triggers, and the fixing section gives concrete remediation steps. However, there's no explicit validation after fixes (e.g., 're-run health.sh to confirm fix'), and the Inngest triage is sequential but lacks a feedback loop for re-checking after remediation. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a compact table, but everything is inline in one file. The 16-component table and fixing section could potentially reference separate docs for detailed component troubleshooting. However, at ~80 lines this is borderline acceptable as a single file. | 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- joelhooks/joelclaw
- Commit
825972c
- 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.