sync-system-bus
Deploy the system-bus-worker to the joelclaw Kubernetes cluster from local machine. Use when syncing changes in packages/system-bus to k8s, especially because the GitHub Actions deploy job targets a non-existent self-hosted runner and cannot complete deploys automatically.
92
88%
Does it follow best practices?
Impact
100%
2.77xAverage 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 a strong, well-crafted skill description that clearly identifies a specific deployment task, names the exact components involved, and provides explicit trigger conditions including the rationale for when this skill is needed. The description is concise yet comprehensive, with natural trigger terms and a clear niche that minimizes conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists a specific concrete action: deploying the system-bus-worker to a named Kubernetes cluster (joelclaw) from local machine. It also explains the context of why this is needed (GitHub Actions deploy job targets a non-existent self-hosted runner). | 3 / 3 |
Completeness | Clearly answers both 'what' (deploy system-bus-worker to joelclaw Kubernetes cluster from local machine) and 'when' (when syncing changes in packages/system-bus to k8s, especially because the GitHub Actions deploy job cannot complete automatically). Has an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes highly specific natural keywords a user would say: 'system-bus-worker', 'joelclaw', 'Kubernetes', 'k8s', 'deploy', 'packages/system-bus', 'GitHub Actions'. These are precise terms that match real user requests in this domain. | 3 / 3 |
Distinctiveness Conflict Risk | Extremely specific to a particular service (system-bus-worker), a particular cluster (joelclaw), and a particular workflow context (GitHub Actions runner issue). Very unlikely to conflict with any other skill. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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 deployment skill with excellent executable commands and a well-structured troubleshooting table. Its main weakness is length — the Talon rebuild section and restart safety explanation add significant content that could be split into referenced files, improving token efficiency. The core deploy workflow is exemplary with clear sequencing and validation.
Suggestions
Move the Talon rebuild section to a separate TALON.md file and reference it with a one-line link, reducing the main skill by ~50 lines.
Trim the 'Restart Safety' section — the ASCII flow diagram and memoization explanation could be condensed to just the critical rule about retries and a link to ADR-0156.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with useful tables and concrete commands, but includes some sections that could be trimmed — the 'Restart Safety' explanation is somewhat verbose for Claude (explaining how Inngest step memoization works), and the Talon rebuild section adds significant length for what could be a separate referenced file. | 2 / 3 |
Actionability | Excellent actionability throughout — every step has copy-paste ready commands, the quick deploy is a single script invocation, manual fallback steps are fully executable, and the troubleshooting table maps problems directly to fixes. | 3 / 3 |
Workflow Clarity | The deploy workflow is clearly sequenced with the script handling build→auth→push→apply→rollout→verify in numbered steps. Validation checkpoints are explicit (rollout wait with timeout, health probe, post-deploy verification commands), and the manual fallback provides a clear alternative path when the script fails. | 3 / 3 |
Progressive Disclosure | The skill has good section structure with a quick deploy up front, but the Talon rebuild section (adding secrets, changing supervision) is substantial inline content that would be better as a separate referenced file. The skill is ~180 lines when the core deploy content could be ~80 lines with the Talon and restart safety details linked out. | 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
ce9ca8e
- 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.