CtrlK
BlogDocsLog inGet started
Tessl Logo

swift-docc-github-pages

Use when setting up DocC documentation for a Swift package, deploying to GitHub Pages, or encountering "no such module 'UIKit'" during doc generation

91

1.53x
Quality

Does it follow best practices?

Impact

83%

1.53x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

A tight, highly actionable single-file skill with executable YAML and a useful decision graph and mistakes table. Its main gap is the absence of an explicit validation checkpoint in the build workflow before deployment.

Suggestions

Add an explicit validation step in the Build Documentation job (e.g., verify the .doccarchive was produced and that ./docs contains the expected documentation folder) before the upload-pages-artifact step.

Include a brief 'verify after deploy' note (e.g., curl the published URL / check the GitHub Pages deployment status) so the workflow has a feedback loop for failed deploys.

Consider moving the full workflow YAML into a references/ file and keeping SKILL.md as an overview with a one-level-deep pointer, to reduce the inline token footprint for callers who only need the decision logic.

DimensionReasoningScore

Conciseness

Lean body that assumes Claude's competence — no explanation of what DocC or GitHub Actions is, just a decision graph, a quick-reference table, full workflow YAML, and a mistakes table, with every token earning its place.

3 / 3

Actionability

Provides fully executable, copy-paste-ready GitHub Actions YAML and Swift Package.swift snippets with clearly marked placeholders (TARGET_NAME, REPO_NAME) plus local-testing commands.

3 / 3

Workflow Clarity

The build → transform → redirect → upload → deploy sequence is clear and the iOS-only vs cross-platform branch is well-modeled, but there is no explicit validation/verification checkpoint step within the build before deploy proceeds.

2 / 3

Progressive Disclosure

A single self-contained file with no nested references, organized into well-signaled sections (Which Build Method, Quick Reference, Workflow, Local Testing, Common Mistakes, Optional) appropriate for a cohesive CI-publishing task.

3 / 3

Total

11

/

12

Passed

Description

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.

A strong, concise description with an explicit 'Use when' trigger, concrete actions, and a distinctive error-message trigger that sharply scopes when it applies. It answers both what and when without padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'setting up DocC documentation for a Swift package', 'deploying to GitHub Pages', and 'encountering no such module UIKit during doc generation' — rather than vague language.

3 / 3

Completeness

Opens with an explicit 'Use when...' clause that answers both what the skill does and when Claude should invoke it, including a specific error-trigger condition.

3 / 3

Trigger Term Quality

Covers natural terms a user would actually say ('DocC documentation', 'Swift package', 'GitHub Pages') plus the literal 'no such module UIKit' error string as a trigger.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche (Swift DocC → GitHub Pages) with distinctive triggers including a unique compiler error message, making conflict with other skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
ivan-magda/claude-superpowers
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.