Piaoxuemoli

Create low-friction coursework deliverables for general education, elective, and low-stakes college assignments, including PPT slides, short papers, reading reports, reflection essays, presentation scripts, discussion posts, and course summaries. Use this skill whenever the user mentions 水课, 通识课, 选修课, 小论文, 课程论文, 读书报告, 观后感, 汇报PPT, 课堂展示, 演讲稿, or asks to turn scattered course materials into a polished student-style deliverable.

Write experiment and lab reports from source materials (lab manuals, PPT, Word, PDF). Use this skill whenever the user needs to write a lab report, experiment report, course report, 实验报告, 课程报告, or any structured academic/technical writeup based on experiment procedures. Proactively suggest this skill when the user mentions "lab report," "experiment report," "实验报告," or describes running an experiment that needs documenting.

学术论文路由器：收集需求、起 router-agent 调度 233 个专业 skills、 三代理流水线（调度→写作→导出）。主 agent 不加载任何 skill 内容。 Use when the user mentions 小论文, 课程论文, IEEE, 论文写作, 学术论文, 文献综述, literature review, paper writing, scientific paper, 研究报告.

How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv, Foundry API, protein binding assays, protein screening experiments, BLI/SPR assays, thermostability assays, or wants to submit protein sequences for experimental characterization. Also trigger when code imports `adaptyv`, `adaptyv_sdk`, or `FoundryClient`, or references `foundry-api-public.adaptyvbio.com`.

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.

Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions. Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone.

Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.

把静态 HTML 站点部署到服务器对外访问的标准 SOP。覆盖 Caddy(Docker,:80/:443) 与 nginx(宿主,独立端口) 两条路径、端口约定、80 端口冲突坑、部署目录、reload 与 curl 验证。任何"部署/上线/开放访问一个 HTML 页面或静态站点"的请求都必须先读这里，不要自己瞎配。

Diagnose RL agent behavioral issues by analyzing reward structure. Use when the agent exhibits unwanted behavior (random skills, wandering, avoiding combat, etc.) to identify root causes in the reward function.

Author/validate/export Google's DESIGN.md token spec files.

Configure, troubleshoot, and operate the Feishu (Lark) gateway integration — group chats, @mention gating, permissions, message routing, and diagnostics.

Scrape training metrics from Tencent AI Arena (tencentarena.com) monitoring dashboard. Covers JWT auth, x-kaiwu-auth signature, API endpoints, and metric extraction.

Write and maintain Kaiwu_2026 答辩材料 (defense/presentation docs). Covers technical writing for innovation points, updating the main summary doc, and git workflow for doc commits.

Use when working with the Kaiwu platform monitoring system — fetching training metrics, plotting charts, running anomaly checks, or updating monitor config. Covers the monitoring/ directory: fetch.py, check.py, plot.py, config.yaml.

Use when the user asks about training status, or when a cron alert fires. Fetches training monitoring data (including eval/matchup win rates and skill usage) from Tencent Arena API, runs anomaly detection, generates charts, keeps a per-run long-term record, and sends code-based analysis with prioritized recommendations via Feishu.

Bug 调试记录技能：将调试过程标准化写入 test_book/无分类/Bug调试记录.md，包含问题发现、描述、根因分析、解决方案、效果、知识点与面试问答。触发词：总结这次调试, 总结这个bug, 记录bug, 记录调试, debug log, 写入test_book, 调试记录, log this bug, summarize debug

Test & Fix skill for ImmerseAI. Supports automated testing (AT-01~AT-14), manual test report fixing (HT-01~HT-10), and CR(Code Review) report output. Trigger with: 自动化测试, 自动测试, auto test, 人工测试, manual test, 测试报告, test report, 运行测试, run tests, CR, code review, 代码审查.

Bug 调试记录技能：将调试过程标准化写入 docs/test_book.md，包含问题发现、描述、根因分析、解决方案、效果、知识点与面试问答。触发词：总结这次调试, 总结这个bug, 记录bug, 记录调试, debug log, 写入test_book, 调试记录, log this bug, summarize debug

Test & Fix skill for ImmerseAI. Supports automated testing (Agent runs code audits and auto-fixes) and manual test report fixing (Agent parses human test reports and fixes failures). Trigger with: 自动化测试, 自动测试, auto test, 人工测试, manual test, 测试报告, test report, 运行测试, run tests.

Create, manage, and clean up temporary Git branches for making isolated modifications. Supports creating feature/fix branches from main, committing changes, merging back or discarding, with automatic cleanup.

Automatically fetch latest World Cup 2026 match information and results, then update the 世界杯预测.html file. Covers match schedule sync, result fetching, AI_ROUNDS updates, prize calculation, and leaderboard refresh.

Sync betting data from agents/*/round-N/bets.md into the HTML AI_ROUNDS array. Parses each model's bets.md, extracts bet entries, and updates the HTML file.

Automatically fetch China Sports Lottery (竞彩足球) odds, match results, and betting data, then update the 世界杯预测.html file. Covers odds scraping, result verification, HTML AI_ROUNDS sync, and nginx reload.

Launches a full Superpowers development workflow from `/dev`. Use when the user wants one guided entry point to go from idea to implementation, verification, review, and branch completion while relying on native Superpowers skills.

Deploy, update, roll back, and operate Colosseum (Next.js AI Arena) on a cloud server via Docker Compose + SQLite + Caddy, or on Vercel as a fallback. USE FOR: deploy colosseum, update production, rollback, backup, restore, server maintenance, production smoke, docker compose deploy, caddy config. DO NOT USE FOR: local development setup (use ops/dev/README.md), code-level feature implementation, LLM provider configuration.

统计简历投递记录并自动更新 README，支持新增/修改记录和可选同步到 GitHub。