Latest Agent Skills
Everything added to the registry recently, newest first.
- shone-navabrind SkillOdoo Test First
Implement Odoo behavior changes with focused tests first when a meaningful, runnable regression test can be written.
- shone-navabrind SkillOdoo Orm Models
Design, extend, debug, or review Odoo ORM models, fields, computed fields, constraints, methods, and business logic.
- shone-navabrind SkillOdoo Migration
Plan or perform an Odoo addon-code migration, a database version upgrade, or both, between any requested source and target versions. Use when upgrading Odoo, porting custom or third-party addons, writing upgrade scripts, or assessing a database migration. Always establish exact versions/edition/hosting, verify the supported path from current official sources, and work one addon at a time.
- shone-navabrind SkillOdoo Views UI
Create or modify Odoo XML views, actions, menus, wizards, reports, and UI behavior.
- shone-navabrind SkillOdoo Testing
Write, select, or run Odoo tests and diagnose module installation, upgrade, or regression failures.
- shone-navabrind SkillOdoo Review
Review Odoo addon changes for correctness, security, compatibility, data safety, and regression coverage.
- cig13zs BundleMap Design
Make editorial maps (route, flow and globe, choropleth, proportional symbol, locator with inset, point events) as self-contained HTML + SVG in a newspaper style, with real data inlined and cited. Use when the user asks for a map, wants to show where something is or happened, compare places, or plot routes, flows, or events on geography.
- enoselinsa BundleWrite Abstracts And Conclusions
Use when drafting, revising, or auditing an engineering paper's title, abstract, index terms or keywords, contribution list, roadmap, or Conclusion, especially when the abstract lacks quantitative results, the Conclusion restates contributions or overstates the experiments, future work is a list of unrelated directions, or these summary parts disagree with each other after results change.
- enoselinsa BundleWrite Revision Responses
Use when preparing a journal revision and its response letter, drafting or auditing responses to editor and reviewer comments, merging a co-author's or supervisor's edits into the manuscript, supplement, and letter, or keeping all submission documents consistent after results, equations, or citations change during a revision.
- samuel-shek BundleElon Musk Perspective
用于重大方案取舍、重要前提不明、成本与必要性判断,或用户明确要求马斯克视角。按第一性原理在已有授权内自主决策、执行与验证;简单任务只做轻量检查,无需完整加载。
- saieeshb SkillExport Transcripts
Export an AI coding agent chat — Claude Code or Codex — as Markdown, a self-contained HTML page or JSON. By default just the conversation (prompts and replies); with --full, everything (thinking, every tool call with its input and output, file reads, diffs, subagents, hooks, injected context, tokens). Use when the user asks to export, save, archive, back up, download, print or share this conversation or a past session, or to find and list past sessions.
- quantskills BundleAlpha F1 Position Change
当需要开发、计算、验证期货前20席位持仓突变因子时,使用此 skill。支持多空持仓优势分析、主力调仓方向判断。
15 - quantskills BundleAlpha F5 Member Position Concentration Production
Use when reading the local F5 commodity futures member-position concentration factor parquet output without recomputing the factor.
15 - quantskills BundleAlpha F5 Member Position Concentration
Use when developing, computing or validating the F5 commodity futures member-position concentration factor in a local Panda data environment.
15 - quantskills BundleSkill Alpha F5 Member Position Concentration
Use when researching or validating the F5 commodity futures member-position concentration factor in a local Panda data environment.
15 - quantskills BundleAlpha F6 Family Position Reverse Production
Use when reading the local F6 commodity futures family-position reverse factor parquet output without recomputing the factor.
15 - quantskills BundleAlpha F6 Family Position Reverse
Use when developing, computing or validating the F6 commodity futures family-position reverse factor in a local Panda data environment.
15 - quantskills BundleSkill Alpha F6 Family Position Reverse
Use when researching or validating the F6 commodity futures family-position reverse factor in a local Panda data environment.
15 - quantskills BundleSkill Audit Opinion Scanner
多维财务分析系统。涵盖审计意见扫描、25项财务科目缓存、15项比率计算、行业分类对标、5维快速评分、8段深度分析、综合风险检测。从排雷到估值到 AI 解读,一条流水线完成。
15 - quantskills BundleSkill B11 Auto Stop Loss Take Profit
当需要对 A 股和期货持仓做自动止盈止损与仓位管理时,使用此 skill。支持次日高开止盈、次日低开止损、持仓满2交易日强平、单票名义仓位上限控制。交易日历唯一来源 = panda_data.get_trade_cal(硬依赖)。
15 - quantskills BundleSkill Hk Us Institutional Concentration
Build, compare, and validate institutional ownership structure panels for Hong Kong and US equities with PandaAI investor concentration, ranking, and shareholder-report APIs. Use for ownership breadth, top-holder dominance, HHI, controlling-holder risk, evidence confidence, or within-market institutional ownership screening.
15 - quantskills BundleLLM Alpha Generator
Mine formulaic alpha factors end to end: LLM 主导生成候选公式 → 三层校验(白名单/量纲/前视)→ warm-start 遗传编程精修 → AlphaEval 五维打分 → LLM 经济解释 → 自包含 HTML 报告,返回结构化因子结果。Use when the user wants to mine/discover alpha factors, generate formulaic (expression-tree) trading factors, run LLM+GP factor search, or evaluate factor predictive power (RankIC) on stocks or futures. 只挖因子、不做回测(回测归另一 skill)。
15 - quantskills BundleSkill Macro Futures Scenario Analysis
基于 PandaData 的宏观事件—期货预期分析:读取宏观经济日历的实际值、市场预期与前值,结合期货价格、成交量、持仓量、基差、期限结构、库存与仓单,对沪金、沪铜、原油及用户指定品种输出基准、偏强、偏弱情景。当用户询问「美国CPI对期货影响」「宏观事件期货预期」「美联储对商品影响」「期货供需与宏观共振」「事件公布前情景」时触发。仅作条件化研究,不承诺涨跌或生成自动交易指令。
15 - quantskills BundleSkill Portfolio Blacklitterman
Black-Litterman 组合优化 —— 用户问「跑一下 BL 组合」「基于视图的组合权重」「相对沪深300 的主动配置」「动量/反转/换手视图对权重的影响」类问题时触发。以沪深300 指数权重为先验,用动量/反转/换手率三条因子视图更新,输出长权重组合,按「样式② 结构化播报」呈现给用户。
15 - cucarol BundleMoyu
Play a quick luck game (roulette by default, blackjack, or Yacht dice) with the user at a local moyu table, in the middle of other work, then go back to that work. Use it when the user wants to play a game with you, or wants a room to keep open and hang out in. Also use it whenever a notification starting with `[moyu <table id>]` or `[moyu room <id>]` arrives or a moyu Monitor expires or closes, since that is a game or a room waiting on you.
- huancheng65 BundleNolook
Drive and inspect an Android app (device or emulator) or a web page (local dev server or live site) through its UI tree instead of screenshots — see what is on screen, tap by text or id, type, scroll, and run whole multi-step checks as one Python flow; small cropped screenshots for visual checks; animation and frame-timing measurements on Android. Use it whenever a task involves operating, checking, reproducing a bug in, or verifying a change to a running app or web page, and before reaching for adb screencap / input tap / uiautomator dump, or for a one-off Playwright, Puppeteer or Selenium script.
- 100x-fi BundleIngfah
Answer questions about Ingfah (อิงฟ้า) from its bundled user guide (คู่มือ), recommend practical setups and improvements for business goals, plan pilots, write FAQ files for its knowledge base (คลังความรู้), and work with the Ingfah client platform through client API-key authenticated APIs. Use when the user asks anything about Ingfah — services, how to do something in the dashboard, telephony, onboarding, settings, billing, release notes — wants an FAQ or knowledge document for an AI Agent, asks to inspect or manage products, AI agents, chat sessions, tools, customer templates, outbound batches, or analytics, or reports something wrong in what they see (a bad call summary or title, wrong outcome labels, an agent saying the wrong thing, missed calls) and wants it fixed, including in the dashboard's English or Thai words: AI Agent Team / ทีม AI Agent, batch / Batch โทรออก, calls / สายทั้งหมด, chats / แชท, templates / เทมเพลตข้อมูลลูกค้า, tools / Tool, knowledge / คลังความรู้, post-call results / ผลลัพธ์หลังวาง
- wookzzz57-beep SkillCheckpoint Resume
Checkpoint or resume long-running coding-agent work across context resets, process interruption, provider switching, or human handoff without replaying the whole chat or repeating completed side effects.
- wookzzz57-beep SkillEvidence Gate
Verify whether coding, maintenance, migration, release, or agent-generated work is actually complete by mapping each acceptance criterion to fresh observable evidence instead of trusting the worker's summary.
- wookzzz57-beep SkillDurable Task
Create a durable task contract before multi-step coding, maintenance, migration, or release work where scope drift, context loss, or ambiguous completion criteria would be costly.
- mailtea-app BundleMailtea Email Design
Design a beautiful, on-brand, deliverable email, newsletter or template in Mailtea. Use when an agent is about to build or restyle a Mailtea email — covers the structured block/ops path (fastest, email-safe by construction), hand-written email-safe HTML when you own the whole document, images, brand colour, and the render/QA loop. Pairs with the mailtea-email skill (which covers sending/managing) — this one covers how the email should LOOK.
- mailtea-app BundleMailtea Site Design
Build and restyle a publication's public website with Mailtea from an AI agent — pages, sections, theme, and the design brief that keeps later edits on-brand. Use when the user wants to create or change their Mailtea site (home, about, archive, a landing page), restyle it, or publish it. Pairs with mailtea-email-design, which covers the email side.
- mailtea-app BundleMailtea Email
Send, schedule, and manage email with Mailtea from an AI agent. Use when the user wants to send a transactional email, send a batch, schedule a send, check delivery status / opens / clicks, list or cancel emails, manage contacts/segments, or draft and send a newsletter — via the Mailtea MCP server, the mailtea Node SDK, or the REST API.
- studiogo BundleRaport Stylu
Pokazuje, jak mglisty jest tekst, który dostajesz od Claude Code — mediana, rozkład i najgorsze odpowiedzi. Use when użytkownik mówi "raport stylu", "mglistość", "czy zasady pisania działają", "jak piszesz", "/raport-stylu".
- afloat16 BundleResearch To Fix
Reuse locally recorded repairs and research similar solved problems on GitHub, Hugging Face, Zhihu, Xiaohongshu, official conference and journal proceedings, and researcher or lab websites; verify evidence against local code, adapt or combine compatible solutions, and test the repair. Use for stubborn bugs, unfamiliar errors, failed reproductions, training instability, performance regressions, or requests to investigate existing solutions before repairing a local project. 中文触发:复用历史修复案例、联网查同类问题、调研可行路线、参考组合已有方案、结合本地代码修复、复现失败、训练异常。
- ziyou-lu BundleGameplay State Driven Surface Motion
当机器已运行但皮带等表面仍静止,或材质滚动与实际运行状态矛盾时,限定目标表面并将权威状态映射到可读的表面动画;不是实体皮带模拟、机关通行或任意背景 UV 装饰。