5.5K skills · sorted by relevance
Review page language attributes so HTML and XML readers receive consistent language information. Check matching lang and xml:lang values, validate language codes, and recommend keeping both attributes for XHTML or removing the unnecessary XML attribute from standard HTML5.
Inspect raw HTML responses for a correct HTML5 doctype at the start of the document. Identify missing or outdated declarations and preceding content, then guide fixes that enable standards-mode rendering in browsers.
Helps integrate YAML output into json-render, turning incoming text into incremental UI updates. Covers prompt generation, streaming parsing, and targeted edits to existing UI specifications through merge, patch, or diff formats.
Find and fix malformed HTML, including unclosed tags, incorrect nesting, and document structure errors. Inspect rendered HTML and HTTP responses to identify specific pages or templates with problems that may affect rendering and search engine parsing.
Turn completed research, analysis, reports, or plans from the current session into a self-contained HTML artifact. A renderer controls layout, typography, and color, using structured content and a choice of two visual styles.
Compare a PPTX exported from HTML with its source slides to find cropped text, footer overlaps, and lost styling. Identify shared causes, revise layout rules, and re-export the deck with automated checks for content extending beyond slide boundaries.
Convert Markdown files into styled HTML suitable for WeChat and other platforms. Choose themes, colors, and fonts, preserve code and diagrams, and optionally turn external links into numbered references at the end.
Classical end-to-end empirical analysis workflow in the traditional Python econometric stack — pandas + numpy + scipy + statsmodels + linearmodels + pyfixest + rdrobust + econml + causalml + matplotlib/seaborn. **Defaults to economics empirical-paper style** (AER / QJE / AEJ) — every run produces a publication-ready output set with a multi-column regression table (M1→M6 progressive controls/FE) as the centerpiece, plus Table 1 (descriptives), mechanism / heterogeneity / robustness tables, and event-study + coefficient + trend figures. Covers the full 8-step pipeline an applied economist or quantitative social scientist runs on every paper — (1) data cleaning, (2) variable construction & transformation, (3) descriptive statistics & Table 1, (4) statistical diagnostic tests, (5) baseline empirical modeling, (6) robustness battery, (7) further analysis (mechanism, heterogeneity, mediation, moderation), (8) publication-ready tables & figures. **Also covers two parallel domain modes that share the same 8-step scaffolding** — **Mode A — Epidemiology / public health** (target-trial emulation via `zepid` / hand-rolled `pandas`, IPTW + g-formula + TMLE doubly-robust triplet via `zepid` / `econml` / `lifelines`, Mendelian randomization via `pymr` / `mrtool` (or `rpy2` → `MendelianRandomization`/`TwoSampleMR`), KM / AFT / Cox survival via `lifelines`, E-value sensitivity, principal stratification — STROBE / TRIPOD reporting), and **Mode B — ML causal inference** (DML via `econml.dml` / `doubleml`, S/T/X/R/DR meta-learners via `econml.metalearners` / `causalml`, causal forest via `econml.grf` / `causalml`, Dragonnet / TARNet / CEVAE neural causal via `causalml`, BCF via `pymc-bart` / `bcf-py`, matrix completion, CATE distribution + policy tree via `econml.policy` / `policytree-py`, off-policy evaluation, conformal causal via `mapie`, fairness audit via `fairlearn`, DAG learning via `causal-learn` / `cdt` / LLM-assisted). Prescribes which library to reach for at each step, shows the canonical code, and links to deeper `references/` files for variant-specific patterns. Use when the user asks for a **complete empirical analysis** in Python, wants to replicate an applied-economics paper from scratch, needs a reproducible workflow that is NOT opinionated on any single vertical package (contrast with StatsPAI), wants explicit control over every estimator and diagnostic, or asks "how do I write a full empirical pipeline in Python?". Also triggers when the user names a specific classical step in isolation — "winsorize at 1/99%", "run Breusch-Pagan", "build a Table 1 balance table", "do a placebo test", "event study plot", "mediation analysis" — and wants it wired into the broader pipeline. Mode A triggers on "target trial emulation", "IPTW", "TMLE", "Mendelian randomization", "STROBE", "公共健康", "流行病学". Mode B triggers on "DML", "double machine learning", "causal forest", "meta-learner", "Dragonnet", "BCF", "policy tree", "conformal causal", "fairness audit", "因果机器学习".
The English summary is being prepared. Showing the original description.
Review HTML pages, presentations, or prototypes across five design dimensions. Receive evidence-backed scores, a radar chart, and practical lists of what to keep, fix, or improve quickly, all packaged in a single self-contained HTML report.
Review rendered HTML and replace generic div elements with elements that describe their purpose, such as main, nav, and article. Clarify page structure to support screen-reader navigation, search-engine understanding, and code maintenance.
Audit HTML page size and identify oversized embedded JSON, SVGs, images, or scripts. Use the findings to plan lighter pages and investigate whether document size could explain content missing from Google's search index.
Review HTML for deprecated ARIA roles, which describe elements to assistive technology, and abstract roles that should not appear in markup. Suggest recommended replacements or native HTML elements and explain potential browser and screen reader compatibility issues.
Convert Markdown documents into HTML for web pages, documentation, or previews. Covers single files, batch conversion, and static site workflows, with guidance on tables, code blocks, math rendering, and handling untrusted content safely.
Develop and troubleshoot Apache Beam's YAML SDK. Understand its source files, run data processing pipelines locally or on Dataflow, test changes, and investigate provider issues or mismatched record fields.
Turn long Markdown files into a single HTML file for reading, reviewing code, or presenting slides. Routes each input to a specialized converter and applies shared design settings, with navigation and interaction suited to the document type.
Create browser-based HTML presentations from notes or PowerPoint files. Choose a visual direction through slide previews, then build slides with animations, keyboard and touch navigation, and layouts that fit the screen without internal scrolling.
Use MLflow to record machine learning experiments, compare results, and manage model versions. The skill covers logging training settings, metrics, and files, organizing a model registry, and preparing models for local or cloud deployment.
Set shared brand colors, fonts, layout style, and table of contents behavior for markdown-html outputs. A guided setup checks text and link contrast, derives twelve reusable CSS settings, and saves preferences globally or per project.
Check XML sitemaps for format errors, problematic URLs, inaccurate modification dates, and missing pages. Generate new sitemaps using industry templates, with file splitting where needed and documentation of the planned site structure.
Generate FrontendIntegration YAML for frontend-forge from a simplified configuration containing one menu and one or more pages. Define resource tables or embedded iframe pages, with the bundled generator expanding menu placements into the required YAML structure.
Build complex interactive artifacts for claude.ai with React, Tailwind CSS, and shadcn/ui. Start from a configured project, develop interfaces with state management or navigation, and bundle the result into one shareable HTML file.
Create text diagrams with PlantUML for README files, emails, and terminal workflows. Convert diagram definitions into plain ASCII or Unicode box-drawing output to share interactions and relationships where image-based diagrams are unsuitable.
Turn ARIS research reports in Markdown or JSON into a single HTML file for reading. Choose a report or dashboard layout, retain source version details, and optionally review whether the conversion preserves content and structure.
Creates SVG technical diagrams for system architecture, UML, cloud systems, agents, and workflows. It checks labels and connections, exports PNG or offline HTML, and can animate supported diagrams as GIFs for explaining how components interact.