CtrlK
BlogDocsLog inGet started
Tessl Logo

import-from-kustomize

Use when the user wants to bring a Kustomize overlay or base into ConfigHub as Units — phrases like "I have a kustomization.yaml, how do I use it with ConfigHub?", "import my Kustomize overlays", "migrate from Kustomize to ConfigHub", "render this overlay into ConfigHub", "kustomize build into Units", or "I have a base + overlays directory structure". Runs `kustomize build` locally, splits the result into one or more ConfigHub Units via `cub unit create`, and hands off ongoing customization to `cub-mutate`. Do not load for Flux `Kustomization` CRDs (use `import-from-flux` — that's the renderer-bridge pipeline), for Helm charts (use `import-from-helm`), for adopting live cluster resources (use `import-from-cluster`), or for authoring raw YAML from scratch (use `config-as-data`).

89

Quality

88%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

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 hits all the marks. It opens with a clear 'Use when' clause containing multiple natural trigger phrases, describes concrete technical actions with specific tool commands, and explicitly disambiguates from four related skills to minimize conflict risk. The negative boundary conditions ('Do not load for...') are a particularly strong feature for skill selection in a large skill library.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: runs `kustomize build` locally, splits results into ConfigHub Units via `cub unit create`, and hands off customization to `cub-mutate`. Very concrete and actionable.

3 / 3

Completeness

Clearly answers both 'what' (runs kustomize build, splits into Units, hands off to cub-mutate) and 'when' (explicit 'Use when' clause with multiple trigger phrases). Also explicitly states when NOT to use it, which further strengthens completeness.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger phrases: 'kustomization.yaml', 'import my Kustomize overlays', 'migrate from Kustomize to ConfigHub', 'kustomize build into Units', 'base + overlays directory structure'. These are phrases users would naturally say.

3 / 3

Distinctiveness Conflict Risk

Exceptionally distinctive — explicitly delineates boundaries by listing four related but different skills (import-from-flux, import-from-helm, import-from-cluster, config-as-data) and explains when to use each instead. This virtually eliminates conflict risk.

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 well-structured, highly actionable migration skill with clear sequencing, validation steps, and concrete CLI commands. Its main weakness is moderate verbosity — the positioning/strategy section and some contextual explanations could be trimmed — and the lack of bundle files to support the referenced paths limits progressive disclosure. The workflow clarity is excellent with explicit preflight gates, stop conditions, and a verify chain.

Suggestions

Trim the 'Positioning: this is an onboarding tool' section to 2-3 sentences — Claude doesn't need the strategic rationale explained at length; focus on the behavioral directive (call out the config-as-data trajectory to the user).

Consolidate the 'Do not load for' section since it duplicates the skill description/frontmatter; a single sentence referencing the routing rules would suffice.

DimensionReasoningScore

Conciseness

The skill is reasonably efficient for a complex multi-step migration workflow, but includes some unnecessary explanatory content (e.g., the 'Positioning: this is an onboarding tool' section explains strategic context Claude doesn't need at that length, and the 'Do not load for' section duplicates the frontmatter description). The table for Unit granularity and the upstream-linking pattern are valuable but could be tighter.

2 / 3

Actionability

Provides fully executable commands throughout: `kustomize build`, `cub unit create` with complete flag syntax, `cub unit update`, diff verification commands, and concrete directory/file patterns. The code blocks are copy-paste ready with clear placeholder conventions (`<app>`, `<env>`, `<git-ref>`).

3 / 3

Workflow Clarity

The workflow is clearly sequenced (inventory → render → inspect → create Units → customize → hand off to apply) with explicit validation checkpoints: inspecting rendered output for artifacts/stale fields, verifying Units match rendered output via diff, checking revision history. Stop conditions and error handling are well-defined (e.g., don't fix broken overlays, redirect Helm inflators).

3 / 3

Progressive Disclosure

References to companion skills and external docs are well-signaled at the end, but no bundle files are provided to support the referenced paths (e.g., `references/cub-cli.md`, `references/functions-catalog.md`, `import-unit-granularity`). The skill itself is quite long (~200+ lines) and some sections like the upstream-linking pattern and the granularity table could potentially be split into referenced files to keep the main skill leaner.

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.

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.