Name: ubuntu-helm-creator
Rating: 75.2 (1 reviews)
Author: canonical

ubuntu-helm-creator

Generate Kubernetes Helm charts backed by Canonical Ubuntu OCI images (rocks). Use when creating a new Helm chart from scratch for a rock; achieving feature parity with an upstream chart (Bitnami, ArtifactHub, GitHub); adding features to an existing chart. Trigger phrases are "generate helm chart", "create helm chart based on upstream chart", "helm chart for app", "feature parity with upstream", "add feature to chart", "scaffold chart", "ubuntu rock helm", "rock-backed chart". Produces chart scaffolding, values.yaml with image.digest, PSS-Restricted security defaults, Pebble-wired probes, tests, and README.md.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable templates, scripts, and explicit validation/retry feedback loops across two well-sequenced modes. Conciseness and progressive disclosure are strong but have minor room to tighten inline explanations and better signal external references.

Suggestions

Tighten the prose around PSS-Restricted and the Pebble probe WARNING block to code-plus-a-single-line rationale, reducing token cost without losing the safety guidance.

Move the three Pebble documentation URLs and the Spread/helm-unittest links into a short "References" subsection so they are clearly signaled one-level-deep pointers rather than inline within steps.

Consider extracting the canonical overrides block (image/Chart.yaml/securityContext/probes) into a referenced file if it grows, keeping SKILL.md as the overview that points to it.

Dimension	Reasoning	Score
Conciseness	Mostly lean and efficient with executable YAML/commands and little concept-explanation padding, but a few sections over-explain (e.g., the rationale paragraphs around PSS-Restricted and the multi-line WARNING block on probe behavior); not 5 because those passages could be trimmed, and not 3 because the bulk assumes Claude's competence and earns its tokens.	4 / 5
Actionability	Provides copy-paste-ready YAML blocks, exact script invocations (e.g., "scripts/inspect-rock.sh digest <repo>/<name>:<tag>"), jq pipelines, and concrete probe/test templates covering the common cases; not 4 because guidance is fully executable across both modes with no meaningful gaps.	5 / 5
Workflow Clarity	Clear sequenced workflows (Step 0 mode decision, Zero-to-One Steps 1-6, Feature Development Steps 1-10) with explicit validation checkpoints (Step 5 Validate, Failure and Retry Protocol, max 5 attempts) and feedback loops for error recovery; not 4 because validation and retry loops are explicit rather than implicit.	5 / 5
Progressive Disclosure	Good structure with one-level-deep references to sibling skills (ubuntu-helm-analyzer, -validator, -docs) and real referenced bundle scripts (scripts/setup.sh, scripts/inspect-rock.sh verified present); not 5 because some authoritative material (canonical overrides, probe wiring) is fairly detailed inline and the Pebble docs are linked as raw URLs rather than cleanly signaled reference files, leaving minor organization gaps.	4 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is third-person, concise, and explicitly covers both what the skill does and when to use it, with a concrete list of trigger phrases and deliverables. It is a strong example of a high-quality skill description with no notable weaknesses.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and outputs: "Generate Kubernetes Helm charts", "Produces chart scaffolding, values.yaml with image.digest, PSS-Restricted security defaults, Pebble-wired probes, tests, and README.md", matching the comprehensive-coverage anchor; not 4 because coverage of actions and deliverables is broad rather than having minor gaps.	5 / 5
Completeness	Clearly answers both what ("Generate Kubernetes Helm charts... Produces chart scaffolding...") and when ("Use when creating a new Helm chart... achieving feature parity... adding features") with concrete trigger phrases; not 4 because the when is fully explicit rather than only improvable.	5 / 5
Trigger Term Quality	Provides an explicit trigger-phrase list including natural synonyms ("generate helm chart", "scaffold chart", "ubuntu rock helm", "rock-backed chart", "feature parity with upstream"), giving comprehensive natural-term coverage; not 4 because it explicitly enumerates many user-sayable phrases rather than leaving a few missing.	5 / 5
Distinctiveness Conflict Risk	A clear niche (Helm charts backed by Canonical Ubuntu rocks) with distinct triggers and minimal overlap risk with generic Helm or container skills; not 4 because the niche and triggers are unambiguous with essentially no overlap concern.	5 / 5
	Total	20 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 7 suspicious	Warning

	Total	14 / 16 Passed

Repository: canonical/helm-charts
Path: .agents/skills/ubuntu-helm-creator/SKILL.md
Commit: 78b355b

Reviewed: 23 days ago

Table of Contents

Discovery Implementation Validation

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.