Data & AI skills

Use when asked 质量追溯体系怎么建, 产品追溯方案, 批次追溯, 一物一码, 客户要求可追溯性, 召回演练, 正向追溯和反向追溯, or plan product and batch traceability in a Chinese factory. Produces a traceability plan in Chinese: the trace unit and coding rule, the data to capture at each process step (material lots, work orders, equipment, people, inspection results), forward and backward trace paths, record retention, a mock recall drill with a target time, gaps against the current system, and a phased rollout, with industry rules (food, medical devices, automotive) marked to confirm.

The English summary is being prepared. Showing the original description.

Use when asked 帮我写教案, 写一份新课标教案, 教学设计, 单元教学设计, 大单元教案, or a lesson plan in the format Chinese schools expect. Produces a complete 教案 in Chinese with 教材分析, 学情分析, 教学目标 tied to the subject's 核心素养, 教学重难点, 教学方法, a timed 教学过程 with teacher and student activity, 板书设计, layered 作业设计 within the 双减 time limits, and 教学反思 prompts, with curriculum references marked to confirm against the current 课程标准.

The English summary is being prepared. Showing the original description.

Plan preparation for the Chinese postgraduate entrance examination (考研): choosing target schools and programmes with realistic odds, a phased study plan for the national subjects and the specialist papers, and preparation for the re-examination (复试) and adjustment (调剂). Use when asked 考研怎么规划, 帮我做考研复习计划, 择校择专业, 考研时间线, 复试怎么准备, 调剂, or plan my kaoyan. Produces a school-and-programme shortlist method with the data to collect, a month-by-month study plan by subject, weekly templates, the key-date checklist to confirm against official notices, and a 复试 and 调剂 preparation guide.

The English summary is being prepared. Showing the original description.

Fit a retention curve to observed cohort data and project LTV — computed, not estimated. Use when someone has real cohort retention numbers (month 0, 1, 2…) and asks what lifetime value, lifetime periods, or long-run retention they imply, or whether retention is flattening or leaking. Produces a fitted power curve (parameters, R², retention floor), a 24-36 period projection, and a real .xlsx with live formulas where editing ARPU recalculates LTV — via the bundled zero-dependency script.

The English summary is being prepared. Showing the original description.

Write a Chinese annual self-review (述职报告 / 年终总结) for a performance cycle: results against OKR or KPI with evidence, the two or three things that mattered most, honest lessons, and next year's plan, in the form Chinese employers expect. Use when asked 帮我写年终总结, 写述职报告, 年度绩效自评, 半年总结, or a year-end review in Chinese. Produces the review in Chinese, a one-page summary for the presentation, a data appendix, and likely questions from the reviewer.

The English summary is being prepared. Showing the original description.

Help a student and family plan university applications after the 高考 (gaokao): use the student's provincial rank rather than raw score, build a 冲 / 稳 / 保 (reach, match, safe) list from official historical admission data, check subject requirements under the new gaokao, and weigh major against university. Use when asked 帮我填高考志愿, 志愿怎么填, 冲稳保怎么排, 这个分数能上什么学校, or plan gaokao applications. Produces a structured application list with the reasoning for each choice, a risk check of the whole list, and the questions to settle as a family. Never guarantees admission.

The English summary is being prepared. Showing the original description.

Use when asked 数据出境要申报吗, 数据出境安全评估还是标准合同, 个人信息出境标准合同怎么备案, 我们把数据传到海外总部合规吗, or decide how to transfer data out of mainland China lawfully. Produces a data map of what leaves China, the route that applies (an exemption, the personal information export standard contract, certification, or a CAC security assessment) with the thresholds to confirm, the filing steps, and the documents to prepare, including the personal information protection impact assessment.

The English summary is being prepared. Showing the original description.

Use when asked 出口报关需要什么单证, 报关资料清单, 申报要素怎么填, 报关单和发票对不上, 出口退税需要的单证, 进口清关资料, or prepare customs documents for an export or import shipment in mainland China. Produces a document checklist for this shipment (报关单 data, 商业发票, 装箱单, 合同, 委托书, licences and certificates), a cross-document consistency check, the 申报要素 to prepare for the HS code, inspection and licence flags, the timeline with the customs broker, and the records to keep for the export rebate, all marked to confirm with the broker and customs.

The English summary is being prepared. Showing the original description.

Draft a clinical trial protocol synopsis with the elements regulators and IRBs expect. Use when asked to write a clinical trial protocol, a study protocol synopsis, a trial design, or to structure endpoints/eligibility/statistics for an interventional study. Produces a structured protocol synopsis — objectives, design, population with eligibility, interventions, endpoints, statistics, and safety/ethics — for expert review. (For non-clinical/UX research, use research-protocol.)

The English summary is being prepared. Showing the original description.

Plan a Chinese company's entry into an overseas market (出海): choose the market with evidence, then plan entity, payments, localisation, compliance, channels and team for the first twelve months. Use when asked 出海计划, 我们要进入东南亚 / 中东 / 欧洲 / 美国市场, how should a Chinese company expand overseas, or a go-global plan. Produces a market scorecard, a twelve-month entry plan by workstream, the compliance and data checklist for the chosen market, and the top risks with mitigations. Bilingual output on request.

The English summary is being prepared. Showing the original description.

Turn numbers into a chart — bar, line, area, pie, or doughnut. Use when asked to chart or graph data, visualize metrics/trends/breakdowns, or show numbers as a picture instead of a table. Produces a ready-to-render chart spec (renders live in the playground and exports as PNG) plus a one-line read of what the chart shows.

The English summary is being prepared. Showing the original description.

Pick the chart the data and the point actually need — the question-to-chart mapping (comparison, trend, composition, distribution, relationship), the honesty rules (axes, baselines, dual-axis traps), and the one-chart-one-point discipline. Use when asked what chart should I use, make this data visual, why does this chart feel misleading, or fix this graph for the deck. Produces the chart verdict with its reasoning, the honesty checklist applied, and the labeling that lets the chart travel without its author.

The English summary is being prepared. Showing the original description.

Extract pixel-level data from an image of a chart or graph and produce a structured data table. Use when asked to extract data from a chart image, transcribe numbers from a graph, digitise a chart, or turn a screenshot of data into a table. Produces a structured table with extracted values, confidence levels, and a reconstructed chart source. Best used with Claude Opus 4.7 or newer for reliable chart data extraction.

The English summary is being prepared. Showing the original description.

Interview you into a durable personal MEMORY.md — your decision rules, patterns, past failures, and preferences — that any AI can read to help you better, with privacy guardrails built in. Use when asked to build my memory file, help my AI remember me, create a MEMORY.md, or set up context about myself. Produces a structured personal-context file drawn out through good questions (how you decide, what you keep repeating, what you don't want to repeat), organized for an AI to use — while explicitly refusing to store sensitive data like credentials, financial, health, or others' personal info.

The English summary is being prepared. Showing the original description.

Build a tiered classroom behavior intervention plan (BIP) for a K-12 student, grounded in the function of the behavior. Use when asked to plan a behavior intervention, address a disruptive or off-task pattern, write a BIP, or set up positive behavior supports. Produces a function hypothesis, prevention/antecedent strategies, teaching of a replacement behavior, a response plan for when it happens, and a simple data-tracking method — positive and skill-building, not punitive.

The English summary is being prepared. Showing the original description.

Get started birding from where you are — what you're likely to see, how to tell confusing species apart, and a simple life-list to track sightings. Use when asked to start birdwatching, what bird did I see, help me identify a bird, or set up a birding log. Produces a likely-species list for your area and season, ID prompts (the field marks and sounds that separate look-alikes), a beginner gear-and-timing note, and a lightweight life-list format — pointing you to a live ID app to confirm any specific sighting.

The English summary is being prepared. Showing the original description.

Diagram a system or technical architecture — services, data stores, and how they connect. Use when asked to draw an architecture, show how components fit together, map a system/data flow, or visualize services and dependencies. Produces a ready-to-render Mermaid diagram with grouped subgraphs (renders live, exportable as PNG/SVG) plus a component legend and notes.

The English summary is being prepared. Showing the original description.

Write an AI usage policy people can actually follow — approved tools, data rules, disclosure duties, and review obligations, in one page instead of legal fog. Use when asked for a company AI policy, acceptable-use rules for ChatGPT/Claude/Copilot at work, guidance on what data may go into AI tools, or to fix a policy nobody reads. Produces a one-page usable policy plus the decision log behind it. Not a substitute for legal advice; pairs with compliance-checklist for regulatory mapping and ai-ethics-review for system-level assessments.

The English summary is being prepared. Showing the original description.

Build the context an AI needs to do a task well — the background, constraints, examples, and format it can't guess — so you get a great result on the first try instead of a generic one you have to keep correcting. Use when asked why does AI give me generic answers, how do I give AI better context, my AI results are mediocre, or how do I get it right the first time. Produces the specific context this task needs (who/what/constraints/examples/format), a reusable primer you can paste ahead of the request, the difference between a starved prompt and a well-briefed one, and what to leave out — turning vague back-and-forth into a strong first result.

The English summary is being prepared. Showing the original description.

Write a PRD for an AI-powered feature, covering the things normal PRDs miss. Use when asked to spec an AI/LLM feature, write a PRD for a feature that uses a model, or plan an AI capability (assistant, summarizer, generator, classifier). Produces an AI feature PRD — problem & UX of uncertainty, model approach, eval criteria, guardrails, fallback behaviour, the data flywheel, and cost/latency budget.

The English summary is being prepared. Showing the original description.

Run a blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped to users, runaway tool use, prompt injection, cost blowouts, or wrong actions taken autonomously. Use when asked to write up an AI incident, analyse why an agent did something wrong, or produce corrective actions after an LLM failure. Produces a structured postmortem with trace reconstruction, a root-cause layer analysis, and corrective actions including a permanent regression case. For non-AI production incidents use incident-postmortem.

The English summary is being prepared. Showing the original description.

Design an evaluation plan for an LLM or AI feature before shipping it. Use when asked how to evaluate a prompt/model/agent, set up an eval harness, define quality metrics for an AI feature, or build a regression gate. Produces an eval plan — task definition, datasets, metrics & rubrics, baselines, automated + human evals, a pass bar, and a regression gate.

The English summary is being prepared. Showing the original description.

Octane bindings for TanStack DB. useLiveQuery hook with dependency arrays (8 overloads: query function, config object, pre-created collection, disabled state via returning undefined/null). useLiveSuspenseQuery for Octane Suspense with Error Boundaries (data always defined). useLiveInfiniteQuery for cursor-based pagination (pageSize, fetchNextPage, hasNextPage, isFetchingNextPage). usePacedMutations for debounced Octane state updates. Return shape: data, state, collection, status, isLoading, isReady, isError. Import from @octanejs/tanstack-db (re-exports all of @tanstack/db).

The English summary is being prepared. Showing the original description.

Intelligent network quality analysis with adaptive loading strategies. Detects connection type (2g/3g/4g), bandwidth, RTT, and save-data mode, then automatically triggers appropriate optimization workflows. Includes decision trees that recommend image compression for slow connections, critical CSS inlining for high RTT, and save-data optimizations (disable autoplay, reduce quality). Features connection-aware performance budgets (500KB for 2g, 1.5MB for 3g, 3MB for 4g+) and adaptive loading implementation guides. Cross-skill integration with Loading (TTFB impact), Media (responsive images), and Core Web Vitals (connection impact on LCP/INP). Use when the user asks about slow connections, mobile optimization, save-data support, or adaptive loading strategies. Compatible with Chrome DevTools MCP.

The English summary is being prepared. Showing the original description.