CtrlK
BlogDocsLog inGet started
Tessl Logo

arn-code-sketch

This skill should be used when the user says "sketch", "arness code sketch", "preview this", "show me what this looks like", "UI preview", "sketch the feature", "visual preview", "sketch this page", "what will this look like", "mock this up", "prototype this UI", "preview the design", "sketch the UI", "preview this command", "show me what the output looks like", "sketch the TUI", "what will the CLI look like", "mock up the terminal output", or wants to see a working interface preview of a feature in the context of their existing application before committing to full implementation. Creates real, runnable artifacts using the project's actual framework and conventions, rendered in a dedicated sketch namespace.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-3

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

A well-structured, highly actionable orchestration skill with clear sequenced workflow, validation checkpoints, and proper progressive disclosure into real reference files. Its main weakness is conciseness — the pipeline diagram and some threshold/error guidance are repeated across sections.

Suggestions

Remove or shrink the ASCII 'Pipeline Position' diagram since the numbered Workflow already covers the same flow, cutting duplicated content.

Consolidate the threshold rules so they appear once (e.g., keep them in Step 3 and reference them from the pipeline diagram instead of restating).

Consider moving the inline sketch-manifest.json schema and the 'Populating component mapping' detail into a reference file, keeping SKILL.md focused on the orchestration overview.

DimensionReasoningScore

Conciseness

Mostly efficient and free of concept-explanation padding, but the ASCII pipeline diagram duplicates the numbered workflow, the manifest schema is shown inline and then deferred, and threshold/error guidance is restated across the Pipeline Position, Step 3, and Error Handling sections.

2 / 3

Actionability

Concrete and executable throughout — literal file paths to read, a copy-paste-ready sketch-manifest.json schema, exact quoted user prompts, a defined artifact namespace, and a structured builder context block; delegation of artifact creation to the builder agent and paradigm refs is explicitly justified.

3 / 3

Workflow Clarity

Explicit numbered Steps 1–8 with clear sequencing and validation checkpoints ('Verify the sketch files were created', 'Halt with...', 'Do not proceed without...'), plus a dedicated Error Handling section with feedback loops for build/preview failures.

3 / 3

Progressive Disclosure

The body serves as an overview that delegates detail to one-level-deep, clearly signaled references — sketch-setup.md, paradigm-<paradigm>.md (with paradigm-stub.md fallback), and iteration-guide.md — all of which are real files present in references/.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 description that uses third-person voice, lists concrete capabilities, and provides an explicit, exhaustive trigger clause covering multiple paradigms. It clearly answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'Creates real, runnable artifacts using the project's actual framework and conventions, rendered in a dedicated sketch namespace' and 'working interface preview of a feature in the context of their existing application before committing to full implementation' — with no vague filler.

3 / 3

Completeness

Explicitly answers both 'what' (creates real runnable artifacts / interface preview) and 'when' via the explicit 'This skill should be used when the user says...' trigger clause.

3 / 3

Trigger Term Quality

Extensive coverage of natural phrases users would say ('sketch', 'preview this', 'show me what this looks like', 'mock this up', 'prototype this UI', 'sketch the TUI', 'mock up the terminal output'), spanning web/CLI/TUI paradigms.

3 / 3

Distinctiveness Conflict Risk

Clear niche — interface sketch/preview before implementation — with distinct triggers unlikely to fire for non-UI code skills; the sketch-specific framing separates it from general feature/spec skills.

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
AppsVortex/arness
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.