managing-cluster-capacity
Manages CockroachDB cluster capacity across all tiers. Self-Hosted covers node decommissioning for permanent removal and adding nodes for expansion. Advanced/BYOC covers scaling node count and machine size via Cloud Console, API, or Terraform. Standard covers adjusting provisioned compute (vCPUs). Basic auto-scales — guidance covers spending limits and cost management. Use when scaling capacity up or down, permanently removing nodes, or managing costs.
94
92%
Does it follow best practices?
Impact
Pending
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 clearly defines what it does across multiple CockroachDB tiers, includes rich natural trigger terms, and provides an explicit 'Use when' clause. The tier-based organization adds clarity and distinctiveness, making it easy for Claude to select this skill appropriately.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions organized by tier: node decommissioning, adding nodes, scaling node count and machine size, adjusting provisioned compute (vCPUs), managing spending limits. Very detailed and actionable. | 3 / 3 |
Completeness | Clearly answers both 'what' (manages CockroachDB cluster capacity with tier-specific details) and 'when' (explicit 'Use when scaling capacity up or down, permanently removing nodes, or managing costs' clause). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'scaling capacity', 'removing nodes', 'decommissioning', 'vCPUs', 'machine size', 'Terraform', 'Cloud Console', 'API', 'spending limits', 'cost management'. Good coverage of terms across different tiers and use cases. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — specifically scoped to CockroachDB cluster capacity management with tier-specific breakdowns (Self-Hosted, Advanced/BYOC, Standard, Basic). Unlikely to conflict with other skills due to the narrow, well-defined domain. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%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, comprehensive skill covering a complex multi-tier topic. Its greatest strengths are actionability (executable commands and queries throughout) and workflow clarity (explicit validation steps and feedback loops for destructive operations). The main weakness is moderate verbosity — the context-gathering tables and some explanatory prose could be tightened, though the multi-tier scope inherently requires more content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient given its multi-tier scope, but the extensive context-gathering tables and some explanatory text (e.g., 'Basic is a serverless offering that auto-scales. There are no nodes or provisioned compute to manage.') explain things Claude likely already knows. The tier routing tables add structure but also bulk. | 2 / 3 |
Actionability | Provides fully executable SQL queries, CLI commands, API calls, Terraform configs, and bash commands across all tiers. Commands include specific flags and placeholders, making them copy-paste ready with minimal adaptation. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints (pre-decommission validation, monitor progress, post-scaling verification). Includes feedback loops like 'If under-replicated ranges exist, wait for re-replication to complete before proceeding' and 'If errors: fix and re-validate' patterns. The dead node procedure has clear step-by-step with verification at each stage. | 3 / 3 |
Progressive Disclosure | Well-organized with clear routing table directing to tier-specific sections, references to external skill files and reference documents are one level deep and clearly signaled. The content is appropriately split between inline essentials and referenced details (e.g., replacing-failed-nodes.md, storage-management.md). | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- cockroachlabs/cockroachdb-skills
- Commit
84bc1e4
- 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.