visual-answer

Answer code/product questions as visual Plan artifacts using repo, bridge, or GitHub context; use for API specs, UI look, schema models, and architecture.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/visual-answer/SKILL.md

Quality

Content

75%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.

A well-structured, actionable body that sequences a publish workflow clearly and stays lean. The consistent 4s reflect minor gaps: Agent-Native tool-call signatures, no explicit validation checkpoint, and an inline example block that nudges it past the simple-skill threshold.

Dimension	Reasoning	Score
Conciseness	The body is lean and purposeful with no padding or explanation of concepts Claude already knows. It is not a 5 because the intro restates the description and "rather than a chat paragraph" is mild editorializing that could be trimmed.	4 / 5
Actionability	Concrete JSON source template, a copy-paste publish command with flags, and named evidence blocks make this mostly executable. It is not a 5 because the Agent-Native chat path names tools (get-plan-blocks, list-plan-components) without invocation signatures; only the terminal path is fully copy-paste ready.	4 / 5
Workflow Clarity	A clear 5-step numbered sequence with guardrails (anti-invention in step 1, a Don't section). It is not a 5 because there is no explicit validation/retry checkpoint, though the operation is neither destructive nor batch so the at-3 cap does not apply.	4 / 5
Progressive Disclosure	Well-organized into clear sections, self-contained, with no nested references and a Related Skills list for navigation. It is not a 5 because at ~90 lines with an inline JSON+command block it exceeds the under-50-line simple-skill exception that would let well-organized sections alone score 5.	4 / 5
	Total	16 / 20 Passed

Description

70%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.

A solid description that states both what the skill does and when to use it with concrete trigger domains. Its main weakness is specificity: it rests on one core action applied to several domains rather than enumerating multiple distinct actions.

Suggestions

Add one or two more distinct concrete actions (e.g., "inspect source, render evidence blocks, publish a Plan artifact") to lift specificity toward the 4-anchor.

Tie the "when" clause to user phrasings (e.g., "use when the user asks 'what is the API spec', 'what does this UI look like', or 'draw the flow") to push completeness toward 5.

Add a disambiguating phrase (e.g., "for new answers from inspected source, not PR recaps") to reduce overlap with visual-plan/visual-recap.

Dimension	Reasoning	Score
Specificity	Names the domain and one core action ("Answer code/product questions as visual Plan artifacts") plus context sources and use domains, but does not list several distinct concrete actions like the 4-anchor's extract/fill/convert. It is above a 2 because the action and domains are concrete, not generic.	3 / 5
Completeness	It has an explicit "what" (answer questions as visual Plan artifacts from repo/bridge/GitHub) and an explicit "when" ("use for API specs, UI look, schema models, and architecture"). It is not a 5 because the when lists domains rather than tying them to user-utterance phrasings like the 5-anchor.	4 / 5
Trigger Term Quality	"API specs", "UI look", "schema models", and "architecture" are natural terms a user would say, giving good keyword coverage. It is not a 5 because no synonyms or file extensions are included and "visual Plan artifacts" is product jargon.	4 / 5
Distinctiveness Conflict Risk	"Visual Plan artifacts" carved from repo/bridge/GitHub inspection is a clear niche with distinct triggers. It is not a 5 because the sibling visual-plan/visual-recap family creates minor overlap risk on the visual-artifact trigger.	4 / 5
	Total	15 / 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
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: BuilderIO/agent-native
Path: .agents/skills/visual-answer/SKILL.md
Commit: bb282b1

Reviewed: ~21 hours 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.