config-as-data
Use whenever the user is authoring or modifying Kubernetes configuration stored in ConfigHub, or is about to reach for Helm, Kustomize, Jsonnet, cdk8s, or a values file. This skill enforces the "configuration as data" doctrine — Units contain fully-materialized, literal YAML, mutated in place via cub functions or direct edits, never re-rendered from templates. Load this proactively any time the user says things like "add a chart", "values file", "overlay", "template this", "parameterize", "set up Helm for this", "make this reusable across envs", or starts generating K8s YAML that will be stored in ConfigHub. Do not load for: pure import-from-helm / import-from-kustomize flows (those have their own skills that handle one-shot render + store), or authoring config outside ConfigHub.
89
88%
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 its scope, provides abundant natural trigger terms, and explicitly delineates boundaries with related skills. The 'Do not load for' exclusion clause is particularly effective at reducing conflict risk. The description is detailed without being padded, and every sentence serves a functional purpose for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists multiple concrete actions: authoring/modifying Kubernetes configuration, enforcing 'configuration as data' doctrine, mutating YAML in place via cub functions or direct edits, and explicitly contrasts with template-based approaches. It also specifies what it does NOT do. | 3 / 3 |
Completeness | Clearly answers both 'what' (enforces configuration-as-data doctrine with fully-materialized YAML, mutated in place) and 'when' (explicit 'Use whenever...' clause with detailed trigger phrases, plus a 'Do not load for' exclusion clause). This is comprehensive. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'add a chart', 'values file', 'overlay', 'template this', 'parameterize', 'set up Helm for this', 'make this reusable across envs', plus tool names like Helm, Kustomize, Jsonnet, cdk8s. These are highly natural phrases. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear boundaries: scoped to ConfigHub-stored Kubernetes config using the configuration-as-data approach. Explicitly excludes import-from-helm/kustomize flows and config outside ConfigHub, which sharply delineates it from related skills. | 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, well-structured skill that provides clear, actionable guidance for the 'configuration as data' discipline in ConfigHub. Its main strengths are the concrete CLI commands, well-sequenced workflow with validation checkpoints, and clear stop conditions. Minor weaknesses include some redundancy between the activation context and body sections, and a slightly verbose verify chain section that could benefit from tighter editing or offloading detail to references.
Suggestions
Trim the 'When to use' and 'Do not load for' sections since they largely duplicate the skill description/frontmatter — or reduce them to a brief sentence each pointing to the frontmatter.
Consider moving the detailed Trigger re-run explanation (step 3 of Verify chain) to a reference or the `triggers-and-applygates` companion skill to keep this skill leaner.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining basic Kubernetes concepts, but some sections are slightly verbose — e.g., the 'When to use' and 'Do not load for' sections largely repeat the frontmatter description, and the 'The rule' section could be tighter. The verify chain section is thorough but somewhat wordy with the Trigger explanation. | 2 / 3 |
Actionability | The skill provides fully executable CLI commands throughout — `cub unit create`, `cub function set`, `cub function vet`, `kubectl create --dry-run=client` with concrete flags and arguments. The change description format is specified with a concrete template. Placeholder conventions (`confighubplaceholder`, `999999999`) are specific and actionable. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (preflight gates → establish intent → produce YAML → store → apply defaults → env variations) with explicit validation checkpoints in the 'Verify chain' section. Stop conditions are defined, and there's a clear feedback loop: store → vet → fix. The preflight gates act as entry validation. | 3 / 3 |
Progressive Disclosure | The skill references several companion files (`references/cub-cli.md`, `references/functions-catalog.md`, `references/yaml-patterns.md`) and companion skills (`kubernetes-resources`, `space-topology`, `triggers-and-applygates`), which is good structure. However, no bundle files were provided, so we can't verify these references resolve. The main body is fairly long and some content (e.g., the detailed Trigger re-run explanation) could potentially be offloaded to a reference. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- confighub/confighub-skills
- Commit
59ea831
- 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.