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.
72
89%
Does it follow best practices?
Impact
—
No eval scenarios have been run
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 thoroughly enumerates the specific components being checked, clearly describes the output format, and provides comprehensive trigger terms covering both formal and informal user phrasings. The description is well-structured with a clear 'Use when' clause and is highly distinctive due to its system-specific scope. The only minor note is the description is quite dense, but the information density is justified given the breadth of the health check.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists numerous specific concrete components checked: 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 across enumerated components, output 1-10 score with breakdown) and 'when' (explicit 'Use when:' clause with multiple trigger phrases and the additional context of 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', and 'at session start to orient'. These cover both formal and casual phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to the 'joelclaw system' with a unique combination of components (k8s, Inngest, Redis, Typesense, pi-tools, memory pipeline). The system-wide health check with scoring output is a clear niche unlikely to conflict with individual component 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, actionable skill with excellent conciseness — the table format for 16 components is particularly effective. The main weakness is the lack of explicit verification steps after applying fixes (re-run health check to confirm), which is important for operations like deleting test files or restarting deployments. The content could also benefit from splitting the triage/fix guidance into a separate reference file to keep the main skill leaner.
Suggestions
Add a verification step after each fix in 'Fixing Common Issues' (e.g., 'Then re-run health.sh to confirm the component is green')
Consider splitting the 'Fixing Common Issues' and 'Inngest Hung-Run Quick Triage' sections into a separate TRIAGE.md, referenced from the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. The table format is extremely token-efficient for conveying 16 component checks with scoring thresholds. No unnecessary explanations of what k8s or Redis are — assumes Claude's competence throughout. | 3 / 3 |
Actionability | Fully executable: the primary action is a single bash command, and every 'Fixing Common Issues' entry provides copy-paste-ready commands with specific paths. The Inngest triage section gives concrete CLI commands and a clear diagnostic sequence. | 3 / 3 |
Workflow Clarity | The health check itself is a single command (clear), and the triage section provides steps, but there are no explicit validation/feedback loops after fixes — e.g., after restarting the worker or PDS, there's no 'then re-run health.sh to confirm' checkpoint. For destructive operations like deleting stale tests or loop tmp, there's a safety note but no verification step. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and a table, but everything is inline in a single file. The 16-component table and fixing guide could benefit from being split — e.g., a separate TRIAGE.md for common fixes. No bundle files are provided, so there's no external reference structure, though the script reference (health.sh) is appropriate. | 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
03f0a59
- 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.