visual-recap

Turn a PR, branch, commit, or git diff into an interactive visual recap with diagrams, file maps, API/schema summaries, annotated diffs, and focused review notes.

Quality

83%

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

85%

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

Highly actionable, clearly sequenced content with strong progressive disclosure and verified reference files; the main weakness is length and thematic repetition across sections that could be consolidated.

Suggestions

Consolidate the before/after headline guidance, which appears in 'Diff → Block Mapping', 'Before / After Is The Headline', and 'UI Impact Needs Wireframes', into one authoritative section that the others point to.

Tighten the lengthy 'Open And Report The Recap' URL-resolution material — the core resolution order (1–3) is enough; the surrounding dev-server/mismatch exposition repeats the same 'do not guess an origin' point several times.

Consider moving the dense block-authoring prop rules (TabsBlock, WireframeBlock, Diagram, Endpoint) into a reference file, leaving SKILL.md with the conceptual mapping and a single pointer, since get-plan-blocks is already the source of truth for exact tags.

Dimension	Reasoning	Score
Conciseness	The body is densely directive and assumes Claude's competence (no concept padding), but it runs ~540 lines with repeated themes — the before/after headline, key-changes horizontal tabs, and URL-resolution rules each recur across multiple sections — that could be consolidated, matching the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	Provides fully executable commands (e.g. 'npx @agent-native/core@latest plan blocks --out plan-blocks.md', 'plan local check/serve/verify'), exact prop schemas, JSON-authoring rules, and a concrete block-mapping table, reaching the 'copy-paste ready' anchor.	3 / 3
Workflow Clarity	Multi-step processes are explicitly sequenced (canonical shape skeleton 1–5, URL resolution order 1–3) with validation checkpoints ('plan local check', 'get-plan-blocks' before authoring, a capped render-and-inspect pass) and a feedback loop (annotation → 'get-plan-feedback' → 'update-visual-plan'), matching the score-3 anchor.	3 / 3
Progressive Disclosure	SKILL.md is a clear overview with well-signaled, one-level-deep references — references/connection.md, references/local-files.md, references/wireframe.md — each verified to exist as real files, with heavy detail (wireframe quality, local-files contract, connection rules) appropriately split out rather than inlined.	3 / 3
	Total	11 / 12 Passed

Description

82%

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, specific description with good natural trigger terms and a clear niche, but it lacks an explicit 'Use when...' trigger clause, which caps completeness at 2.

Suggestions

Add an explicit trigger clause such as 'Use when a PR, branch, or commit is large or multi-file and a reviewer would benefit from a structured visual summary before reading the raw diff.'

Mirror the natural phrasing users actually say, e.g. 'recap this PR' or 'show me what this branch changed', so the description surfaces the trigger verbs users invoke.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions and inputs — 'PR, branch, commit, or git diff' turned into 'diagrams, file maps, API/schema summaries, annotated diffs, and focused review notes' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly answers 'what' the skill does but contains no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2 rather than 3.	2 / 3
Trigger Term Quality	Covers natural terms users would say — PR, branch, commit, git diff, visual recap, review notes — giving good coverage of the vocabulary a user would naturally invoke, matching the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	The visual-recap-of-git-changes niche has distinct triggers ('PR, branch, commit, or git diff' → 'visual recap') and is unlikely to be confused with other skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	11 / 12 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
skill_md_line_count	SKILL.md is long (553 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: BuilderIO/agent-native
Path: .agents/plugins/agent-native-visual-plans/skills/visual-recap/SKILL.md
Commit: c1ee18b

Reviewed: 5 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.