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 service and target cluster, and provides explicit trigger conditions including the rationale for manual deployment. The description is concise yet comprehensive, covering both the 'what' and 'when' with natural trigger terms that a developer working on this system would use.
| 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 targeting 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 GitHub Actions deploy job can't complete). The 'Use when' clause is explicit. | 3 / 3 |
Trigger Term Quality | Includes natural keywords a user would say: 'deploy', 'system-bus-worker', 'joelclaw', 'Kubernetes', 'k8s', 'packages/system-bus', 'GitHub Actions', 'self-hosted runner'. These are highly specific and cover the terms someone working on this system would use. | 3 / 3 |
Distinctiveness Conflict Risk | Extremely specific to a particular service (system-bus-worker), a particular cluster (joelclaw), and a particular workflow limitation (broken GitHub Actions self-hosted runner). This is 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 skill with excellent workflow clarity and real, executable commands throughout. Its main weakness is length — the Talon rebuild section and detailed secret mappings table make it longer than ideal for a SKILL.md, and this content would benefit from being split into a referenced file. The restart safety explanation, while valuable domain knowledge, could be more concise.
Suggestions
Move the Talon Rebuild section (including SECRET_MAPPINGS table and key paths) to a separate TALON.md file and reference it with a one-line link from the main skill.
Condense the Restart Safety section to the critical rule ('NEVER set retries: 0') and a 1-2 line explanation, moving the detailed memoization explanation to an ADR reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with useful project-specific information Claude wouldn't know, but the Restart Safety section and Talon Rebuild section add significant length. The explanation of how Inngest step memoization works and the deploy sequence diagram, while useful, could be more terse. The SECRET_MAPPINGS table and Talon details could be split to a separate file. | 2 / 3 |
Actionability | Excellent actionability throughout — every step has concrete, copy-paste-ready commands. The quick deploy path is a single command, manual fallback steps are fully executable with real paths and image names, and the Talon rebuild section provides numbered steps with exact commands. | 3 / 3 |
Workflow Clarity | The primary workflow is crystal clear: run the publish script which handles build→auth→push→apply→rollout→verify. The script's internal steps are enumerated. Manual fallback steps are clearly sequenced. Post-deploy verification has explicit commands. The Talon rebuild section includes a proper sequence with validation (curl health check). Error recovery is addressed via the gotchas table. | 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) and the detailed SECRET_MAPPINGS table are substantial inline content that would be better as a separate referenced file. The document is quite long for a SKILL.md and mixes the primary deploy workflow with secondary Talon management concerns. | 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.