Skip to content

stark-ai-de/agent-skills / plugins/stark-ai-developer/skills/visual-reports

visual-reports

Verified

Create and update visual reports with optional native interaction, one guided topic at a time, useful diagrams, concise points, joint comparisons and complete offline HTML/Markdown/JSON exports. Use when richer output helps an authorized answer or the user asks for a visual report; keep small answers in chat. Not production application UI or clinical advice.

FileKindSize
SKILL.mdskill md11.5 KB
agents/openai.yamlconfig779 B
assets/completion-example.mdmarkdown3.2 KB
assets/graphite-grain/configurator.htmlother17.7 KB
assets/graphite-grain/configurator.mjsscript6.9 KB
assets/graphite-grain/relaxed.cssother4.2 KB
assets/openai-icon.pngbinary10.3 KB
assets/openai-icon.svgother318 B
assets/preview.jsscript3.4 KB
assets/report-recipes.mjsscript19.2 KB
assets/report-runtime.cssother16.4 KB
assets/report-runtime.jsscript23.9 KB
assets/report-shell.htmlother14.1 KB
references/comparisons.mdmarkdown4.8 KB
references/filesystem-handoff.mdmarkdown4.7 KB
references/managed-reports.mdmarkdown5.2 KB
references/markdown-input.mdmarkdown3.9 KB
references/model-v2.mdmarkdown10.1 KB
references/renderer.mdmarkdown24.5 KB
references/report-contract.mdmarkdown33.1 KB
references/selection.mdmarkdown4.8 KB
scripts/benchmark.mjsscript2.2 KB
scripts/cache_icon.pyscript9.2 KB
scripts/export-assets.mjsscript4.1 KB
scripts/lib/blocks-v2.mjsscript21.7 KB
scripts/lib/cli.mjsscript3.7 KB
scripts/lib/export-path.mjsscript1.6 KB
scripts/lib/generator-entry.mjsscript472 B
scripts/lib/markdown-input.mjsscript9.8 KB
scripts/lib/preview.mjsscript4.9 KB
scripts/lib/report-state.mjsscript13.4 KB
scripts/lib/report-store.mjsscript7.0 KB
scripts/lib/templates.mjsscript4.7 KB
scripts/render-report.mjsscript40.0 KB
tests/browser-delivery.mjsscript25.4 KB
tests/browser-smoke.pyscript15.5 KB
tests/browser-topics.mjsscript21.1 KB
tests/cache-icon.test.mjsscript5.0 KB
tests/export-assets.test.mjsscript5.5 KB
tests/render-report.test.mjsscript14.3 KB
tests/report-state.test.mjsscript11.7 KB
tests/topics.test.mjsscript6.4 KB
tests/v2.test.mjsscript21.1 KB

references/comparisons.md

View on GitHub
# Comparable products and capabilities

Use these patterns for comparing products, harnesses or technical approaches.
Choose views from the reader's task; not every report is a catalogue, feature
matrix or market map. Product research stays in the consuming repository.

## Comparison first

The initial view presents multiple options and their common criteria together.
Use aligned charts for comparable numbers and a shared matrix for qualitative
facts. Keep units, periods, denominators, evidence states and decisive conditions
beside the values. Unknown values use explicit text/dashed marks, not invented
zeros. Numeric scales are common per criterion; do not imply that different units
share a meaningful magnitude or normalize them into an unexplained score.

Option/metric toggles, search and sorting refine an already visible comparison.
A long entry list followed by individual detail panels fails the comparison goal.
Do not require the reader to remember values from other screens or repeatedly open
products to find differences. There is no general four-item cap. On small screens,
a labeled horizontal scroller can preserve a standalone wide comparison instead
of stacking product essays. This exception does not make a guided tab body or its
title bar scrollable; use the [guided layout contract](report-contract.md#guided-layout-and-navigation)
there, and choose a standalone comparison when joint criteria need that space.
Ordinary vertical page scrolling is allowed. Details can hold supporting evidence,
never decisive limitations.

Product details are retained, not removed: decision-relevant properties, values,
conditions and boundaries belong on the joint surface; long explanations and
sources remain accessible. All selections use the same facts as unfiltered exports.

## Shared criteria and badges

Define one source-backed feature vocabulary with stable IDs and concise labels.
Use the same small icon/color for a feature wherever it appears. Feature identity
is separate from evidence/status: always show a textual state, supplemented by a
shape or symbol when useful. A color is not proof that a feature is available.

Keep supported/documented, partial, explicitly absent, unknown/unverified and
planned states distinct. Missing documentation is not proof of absence; a plan is
not delivered. Place decisive conditions and source links beside badges. Preserve
scope, version and snapshot limits. Use meaningful criteria, not a universal
feature list or invented product score.

## KPIs and editorial estimates

Inventory, documentation coverage and source availability can be KPIs only when
derived from the actual dataset. Show units, denominator, snapshot and excluded
items. Unknown cells stay unknown; do not fabricate a percentage to fill a chart.
Distinguish measurements, documentation coverage and editorial estimates.

When including the user's product, separate actual implementation from its target.
Do not grant a perfect similarity score or count plans as shipped features. State
its reference role and whether competitor KPIs exclude it. A similarity-to-vision
estimate requires an editorial label, assessment basis and uncertainty; it is not
measured quality or feature coverage. Domain profiles may require fields/checks,
but must not supply fictitious evidence, weights or scores.

## Product screenshots

Use genuine available product screenshots when requested or useful. Prefer official
pages, documentation or repositories and retain exact source, retrieval/snapshot,
component scope and known usage terms. Label manufacturer screenshots accordingly.
An image is not a successful test or proof of feature availability. Never substitute
an invented UI or namesake product for missing evidence.

Use consistent small thumbnails, useful alt text and optional larger views. Mark
unavailable images explicitly. Keep discovery/download material in ignored local
`.cache/show-html/screenshots/`. Consumers may retain reviewed assets and source
manifests for reproducible generation; embed required bytes in standalone HTML.
Do not commit private captures or infer a license from public visibility.

## Area maps and positioning

Maps may show role, primary use and documented/editorially assessed strengths.
Use meaningful labeled dimensions/areas; some tools are terminals, access layers
or specialists rather than harnesses. Distinguish measured coordinates from
editorial placement. Without quantitative evidence, area, distance, size and order
must not imply measured quality, performance or market share.

Explain areas and placements with source references and uncertainty. Retain an
unclassified area when identity/scope is unknown. Separate the user's target from
implemented competitors. Provide equivalent readable table/text without JavaScript.
Filters and map jumps must preserve recognizable selection and location. The shared
renderer offers labeled diagrams, not an automatic market-positioning algorithm.
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall