Master defensive Bash programming techniques for production-grade scripts. Use when writing robust shell scripts, CI/CD pipelines, or system utilities requiring fault tolerance and safety.

This skill should be used when the user asks to "run initial analysis", "analyze single-cell data", "QC my data", "run bioinformatics pipeline", "generate analysis report", "explore my dataset", "do exploratory data analysis", "initial data analysis", or needs to perform quality control, dimensionality reduction, clustering, or marker analysis on single-cell biology data (CyTOF, scRNA-seq, flow cytometry, proteomics).

Help professors and researchers write, revise, adapt, and polish grant proposals for US agencies (NSF, NIH, DOE, DARPA, NASA), Chinese agencies (NSFC 国自然), and other national agencies (JSPS KAKENHI 科研費, ERC, DFG, SNSF, ARC, NWO). Use this skill whenever the user mentions grants, proposals, funding applications, 基金申请, 本子, R01, R21, CAREER, 面上, 青年基金, specific aims, 立项依据, broader impacts, or wants to plan, draft, review, or resubmit any research funding proposal — even if they don't explicitly say "grant". Also use this skill when the user wants to adapt a previous proposal for a new submission. Six-phase workflow: profiling → planning → drafting → quality review → simulated peer review → submission prep.

Generates research ideas for a defined research problem. Reads the project's literature and context, explores directions with research ideation lenses, writes three full candidate proposals, and selects one through an explicit gate. Writes Ideation/ideas/selected_idea.txt for inno-idea-eval. Use when the user wants research ideas, hypotheses, a research direction, or a method idea for a paper or project. Runs after literature survey and before inno-idea-eval.

Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.

Workflow 1: Full idea discovery pipeline. Orchestrates research-lit → idea-creator → novelty-check → research-review to go from a broad research direction to validated, pilot-tested ideas. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向", or wants the complete idea exploration workflow.

Render a 4-panel regional LocusCompare diagnostic for one (lead variant, exposure study, outcome study) tuple - overlays GWAS Manhattan, QTL Manhattan, GENCODE gene track, and cross-trait scatter colored by LD r². Use when an agent needs visual confirmation that two GWAS / QTL signals share the same causal variant (the Liu 2019 LocusCompare convention). Inputs: lead variant + two pre-fetched harmonised sumstats slices (or eQTL Catalogue / GWAS Catalog identifiers for bundled fetch). Output: PNG + JSON manifest.

Step of the analyze-performance playbook: ranks creative by angle, hook and format with spend gates, writes short per-channel reads and drafts what to make next. Run analyze-performance instead; not for direct use.

CloudBase PostgreSQL access-pattern and slow-query quality guidance. Use when designing how tables are read and written, eliminating per-row database calls, adding indexes for filters or joins, reviewing high-traffic data access, or explaining a slow SQL query. Not for first-time PG SDK setup, login UI, or NoSQL collections.

WeChat Mini Program development skill for building, debugging, previewing, testing, publishing, and optimizing mini program projects (小程序开发、调试、预览、发布). Covers project structure and config (`project.config.json`, `appid`, `miniprogramRoot`, `tabBar`, routing/navigation, icon assets), WeChat Developer Tools Nightly workflows (`wechatide` CLI, WeChat IDE Skills/MCP), `miniprogram-ci` preview/upload, console/network debugging, message push (消息推送) and customer-service auto-reply (客服消息), mini program SEO / search indexing (小程序搜索优化、页面收录、搜索推广、mpcrawler), and CloudBase integration (`wx.cloud`, 腾讯云开发, 云开发) when explicitly used. Use when users create, develop, modify, debug, preview, deploy, publish, or promote WeChat Mini Programs. NOT for Web frontend (use web-development), pure backend services (use cloudrun-development / cloud-functions), or UI-design-only tasks (use ui-design).

Use when working with HealthKit, WorkoutKit, health data, workouts, or fitness features on iOS or watchOS. Covers permissions, queries, background delivery, custom workouts, multidevice coordination.

Builds PocketBase superuser admin UI extensions (admin plugins) on PB ≥0.37: ServeEvent.uiExtensions, client main.js, window.app SPA hooks, Shablon UI, reactive stores, CSP, SSE/realtime topics. Use when extending the PocketBase admin dashboard, operator pages, custom collection tabs/fields, live dashboards, or mothership post-v0.39 operator tooling — not for pb_hooks server logic alone (see pocketbase-jsvm) or external SPAs.

Write PocketHost blog posts in Ben Allfree's voice (@cap'n). Use when drafting or editing posts under packages/dashboard/src/routes/(static)/blog/, updating blog/toc.ts, announcing a shipped feature (with feature-blog skill), or when the user asks for blog content in the PocketHost style.

Query a user's Gemini Notebook (formerly NotebookLM) for source-grounded answers through a logged-in browser session on their Google account. Uses the account's usage limits and writes browser state. Runs only on an explicit request: /blog notebooklm, "ask my Gemini Notebook", "ask my NotebookLM notebook", or "query my notebook library". Also used by blog-write when the user named a notebook for research. Not for generic research or note-taking.

One-command multilingual blog creation. Writes a blog post, translates it into user-specified languages, applies cultural adaptation, and emits hreflang tags, sitemap entries, and a CMS-ready language map. The complete write-to-publish pipeline for international content. Orchestrates blog-write, blog-translate, blog-localize, and (optionally) seo-hreflang. Use when user says "multilingual blog", "blog multilingual", "write in multiple languages", "international blog", "mehrsprachiger Blog", "blog multilingue", "blog multilingue", "create blog in German and French".

Credentialed Google API calls for a blog: PageSpeed Insights, CrUX history, Search Console performance and URL Inspection, GA4 organic traffic, Cloud NLP entities, YouTube video search, Google Ads Keyword Planner, and the Indexing API (job and livestream pages only). Uses the user's Google credentials, quotas, and sometimes billing, and asks for consent before the first call. Runs only on an explicit request: /blog google, "run PageSpeed on this blog URL", "pull my Search Console data", "inspect this URL's index status", "set up Google API credentials". Shares config with claude-seo at ~/.config/claude-seo/google-api.json.

Verify statistics and claims in blog posts by fetching cited source URLs and checking if the claimed data actually appears on the page. Extracts all load-bearing claims (statistics, product or policy claims, ranking and comparative claims, named sources), validates cited URLs before fetching, and scores match confidence (exact match 1.0, paraphrase 0.7-0.9, not found 0.0). Flags uncited claims as UNVERIFIED and marks a claim verified only when this run fetched the source and found the passage. Checks that a source says what the post says it says; it cannot prove the source is true or verify first-hand experience. Use when the user says "fact check", "verify statistics", "check sources", "factcheck". Report only; not for rewriting posts (blog-rewrite).

Compare two Google Search Console page exports (current vs previous period) to flag pages whose clicks or impressions fell by a chosen threshold, with a triage hint (refresh, query shift, consolidate, prune). The 20% default is a screening heuristic, not proof of decay. Use for "/blog decay", "content decay", "QoQ decline", "refresh declining posts". Needs two GSC exports; not for diagnosing a single traffic drop live (blog-google) or rewriting posts (blog-rewrite).

Build, repair, or review Maple dashboard widgets via the MCP. Triggers on phrases like 'create_dashboard', 'add_dashboard_widget', 'update_dashboard_widget', 'dashboard widget JSON', 'panel_type', 'QueryDraft', or any session that submits widget JSON to the maple MCP. Covers the panel-type table, the kind-discriminated data source, the percent vs percent_100 unit rule, valid aggregations and group-by tokens per source, the custom whereClause grammar, the scalar reduceToValue transform, and the verification step (MCP success != chart correctness).

Build AI scientist systems with the ToolUniverse Python SDK for scientific research. Covers the 3 calling patterns (`tu.run` portable dict API, `tu.tools.X` function API, direct class instantiation), tool loading, batch execution, MCP server integration, and embedding-based tool search. Use for SDK programming, custom tool composition, benchmarking pipelines, and integrating ToolUniverse into research workflows.