Build and improve ScienceDiscovery frontend UI in apps/web. Use proactively for React/CSS changes, responsive layouts, chat/composer, panels, dialogs, artifacts, settings, or reports of clipped text, hidden content and overlap. Implement the requested change and inspect the rendered result, rather than returning an audit only. Review aesthetics, layout, interaction, accessibility and adaptation broadly; the hard-constraint allowlist limits deterministic GitHub Actions checks only, never AI review. Preserve the existing visual system and proactively improve relevant problems. No hooks or runtime installs.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Improve the research workbench, not a marketing landing page. Help a user understand the current Project / Session / Run, act on it, and inspect evidence without losing their place. This skill provides development guidance and optional diagnostics. It does not introduce an approval stage or test gate. Existing repository contribution and E2E requirements remain unchanged.
AI reviews broadly. Inspect and improve visual quality, hierarchy, typography, colour, spacing, density, interaction, task flow, accessibility, content states and responsive behavior. These are examples, not an exhaustive allowlist. Use code, browser interaction and screenshots when available. A real usability or design defect remains a defect even without a deterministic test; do not reduce AI work to FQ-01 through FQ-05 or stop because the helper passes.
Actions rules stay narrow. The new frontend visual/layout rule checks are limited to reproducible, state-specific hard constraints: unintended overflow, missing/clipped content, blocked actions and unintended overlap. Do not turn AI aesthetic scores or design preferences directly into Actions pass/fail. This restriction does not narrow existing lint, type, security or functional checks. No Actions workflow is added by this skill package.
Review breadth is not permission to rewrite unrelated features. Proactively fix relevant issues within the authorized task and surface wider issues with evidence and impact instead of silently expanding the implementation scope.
Read the affected React component, its styles, a neighbouring component and existing tests. Use the task's actual product state, not an invented demo. Explain the main layout decision briefly, then implement it; do not wait for an extra approval for ordinary changes already covered by the request. Do not treat permission to improve a component as permission for a site-wide redesign, a backend/API change, a new dependency, or a production deployment.
Keep the repository's React/Vite and native CSS approach. The inspected baseline
uses global widths of 600, 900 and 1180 CSS px in
apps/web/src/styles/responsive.css, plus component breakpoints and container
queries. Re-read current code before editing; these are existing conditions,
not proof that every screen is already supported. Do not import Tailwind,
Carbon components, or a new breakpoint scale merely because an upstream guide
uses them. Reuse current typography, theme variables, icons and primitives.
| Task | Read |
|---|---|
| New or changed UI, visual quality, hierarchy, interaction, density | Product UI |
| Width, height, zoom, panels, touch or high-DPI | Responsive layout |
| Overlap, clipping, text loss or invisible controls | Hard constraints |
| Browser verification, stress content and reporting | Verification |
These references are local and reviewed. Do not fetch newer upstream rules at runtime. Do not load all third-party skills or licensing files into every frontend task. Traceability is in NOTICE.md and sources.json, not in the default prompt.
For the changed area, include realistic long names/paths/URLs, CJK and English, empty/loading/error states, streaming content, or permission decisions as appropriate. Preserve data and scientific meaning: do not round scientific values, crop evidence, remove tools or hide errors just to make a layout fit. Fix the sizing chain before adding clipping: shrinking Grid/Flex children, wrapping ordinary text, and local scroll regions are different decisions.
For narrow layouts, move secondary work into a reachable drawer, tab or detail view. Preserve primary actions, drafts, selection and the active Run while resizing. For wide layouts, use useful parallel panels and constrain long reading passages; do not enlarge every element or stretch a paragraph to 4K.
When a browser is available, navigate the affected user path and inspect a narrow, intermediate/low-height and wide state chosen for this change. Resize through affected breakpoints and inspect after opening relevant panels/dialogs. Use existing journey fixtures and reports when running product E2E; read the E2E skill. A standalone HTML fixture proves only the diagnostic helper, not the product or the user journey.
Actively identify and fix relevant design and UX defects, not just detectable geometry errors. Explain the user impact of AI-assessed issues and distinguish an actual usability problem from an optional stylistic preference. Neither category becomes a deterministic Actions failure just because AI reports it. The optional layout helper is supporting evidence; its limited rule coverage does not limit AI inspection. It is not a beauty score, universal DOM crawler, accessibility certification, or substitute for user actions and screenshot inspection. Do not add hooks; changing default tests or Actions workflows requires a task that requests that integration.
When verification is unavailable, finish the safe implementation and state what remains unverified. Never report a screenshot, viewport, browser, real phone or E2E run that was not actually exercised. A missing selector, stale contract or missing browser is not a successful check.
State what changed, the actual viewport/DPR and states checked, deterministic results, AI-assessed design/UX issues fixed or remaining, optional refinements, and coverage gaps. Distinguish measured facts from visual judgement; neither replaces the other. Use paths and reproducible steps. Do not claim that the entire 320–3840 CSS px range passes from a few samples, or that emulation proves real mobile behavior.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Prepare, launch, monitor, and summarize the real RFdiffusion to ProteinMPNN to Protenix antibody pipeline on a local or remote ScienceDiscovery Runner with sandboxed Ascend NPUs.
The English summary is being prepared. Showing the original description.
Independent multi-dimensional assessor for material design candidates. Loads configurable scoring rubrics to evaluate candidates from different expert perspectives. Each dispatch produces structured scores, pros/cons, and verification data without sharing results with other assessors.
The English summary is being prepared. Showing the original description.
Read, diagnose, and change the CI pipeline: GitHub Actions on pull requests, the merge queue, the nightly schedule and the release tag. Use when a job fails, when editing .github/workflows/, when asking which layer runs what, when reproducing a pipeline failure locally, or when a job needs the bubblewrap sandbox. Running the layers before proposing a change, and reading the result a proposal receives, belong to create-github-pr.
The English summary is being prepared. Showing the original description.
Verify cited paper identity and decide whether claims in an Artifact are supported by their linked Evidence using a governed source snapshot.
The English summary is being prepared. Showing the original description.
Use this skill when you need to write and execute Python/R code to process, transform, and analyze data, delivering reproducible computational results with complete code-level methodology documentation. Supports statistical analysis, data transformation, visualization, method justification, and structured result output.
The English summary is being prepared. Showing the original description.
Check whether numeric claims marked with Evidence aliases in an Artifact agree with the linked Evidence content and context.
The English summary is being prepared. Showing the original description.