В каталоге 185 367 навыков в 14 категориях.
openInvest multi-asset AI investment committee — **daily use**. Read portfolio / live prices / strategy / decision histo...
invest系列主入口。识别标的类型,路由到专业分析工具。 触发:「分析一下」「看看这个」「值得买吗」「这只怎么样」「资产配置」「大师怎么看」「债券」「流动性」「市场环境」「比特币抄底」
invest系列:资产配置。判断股债商比例是否合理,单一品种分析与组合配置相结合。 触发:「资产配置」「股债比例」「组合调整」「再平衡」「大类资产配置」「投资组合」
全能证券分析师工作台——把零散金融工具串成机构级工作流。覆盖个股IC研报、主题策略、事件驱动(电话会/业绩/政策/并购)、一致预期整合、行业比较、市场日报六大场景。 触发:「出一份茅台的IC报告」「写一份XX的行业深度」「XX业绩电话会纪要...
全能证券分析师工作台——机构级内容交付。 覆盖:IC研报、行业深度、首次覆盖、业绩点评、事件驱动、市场日报。 触发:「出一份茅台的IC报告」「写一份XX的行业深度」「XX业绩点评」「怎么看待XX政策」「出个日报」 与invest系列区别:i...
invest系列:单品种资产分析(债券/可转债/大宗商品/REITs)。判断一类资产是否值得配置或买入:同一套三关审查骨架,按资产类型加载专属细则。覆盖债券(利率债/信用债)、可转债、黄金/白银/原油等商品、公募REITs。 触发(债券)...
invest系列:单品种资产分析(债券/可转债/大宗商品/REITs)。 同一套三关审查骨架,按资产类型加载专属细则。 触发(债券):「债券」「国债」「信用债」「城投」「信用利差」「债券值得买吗」 触发(可转债):「可转债」「转股价值」「溢...
Back up / restore openInvest's local state — memory/ (holdings, strategy, user profile, committee records, dream logs) +...
投资分析 CLI — 数据获取 + 分析框架一体化,dual-mode 运行。 触发:「/cli」「/投资cli」「invest cli」「终端分析」「命令行分析」 或:「用cli分析」「终端查一下」「命令行看看」 命令入口:`inve...
大师会诊——4种投资视角×3档深度,多视角审视标的,发现单一视角的盲区。 触发:「帮我看看这个能不能买」「这个标的怎么样」「多几个角度看看」「大师怎么看」「圆桌」「会诊」
大师会诊——4种投资视角×3档深度,多视角审视标的,发现单一视角的盲区。 触发: 「帮我看看这个能不能买」「这个标的怎么样」「多几个角度看看」「大师怎么看」「圆桌」「会诊」
invest系列:企业深度分析。面向单一企业主体,覆盖股东治理、行业地位、经营状况、ESG、财务、发行定价、偿债信用、司法风险等维度。 触发:「企业分析」「企业深度」「企业信用」「企业一页纸」「这家企业怎么样」
invest系列:基金分析。判断单一基金产品是否值得买入或持有:了解策略吗?能持续跑赢吗?成本合理吗?覆盖主动基金、ETF、指数基金、QDII。分析交付物含基金体检报告与同经理多基金对比报告,数据走官方 ttskill 管线。 触发:「分...
invest系列:基金分析。判断单一基金产品是否值得买入或持有。 覆盖主动基金、ETF、指数基金、QDII。 触发:「分析这只基金」「基金体检」「基金诊断」「这只基金怎么样」「基金经理靠谱吗」「ETF怎么样」
**BETA — not recommended for anyone.** Operator notes for openInvest's experimental IBKR live autopilot: an LLM picks an...
invest系列:宏观与市场环境分析。评估全球流动性、美股情绪、加密底部信号,判断当前市场环境对风险资产是否友好。 触发:「流动性」「美联储」「缩表」「TGA」「SOFR」「MOVE」「日元套利」「钱紧不紧」「市场环境」 「美股情绪」「N...
invest系列:基金池构建与管理。不是分析单只基金,而是建立并维护一个高质量的基金观察池。 覆盖风格分类矩阵、选基七维度、行业轮动评估、更新机制、组合配置原则。 触发:「基金池」「选基」「基金组合」「关注池」「基金池构建」「基金池更新」「...
invest系列:风险认知与管理系统。从「什么是风险」到「如何系统化管理风险」。 覆盖风险四层递进诊断、风险管理四层框架、不依赖意志力的投资系统设计、现金管理与安全垫。 触发:「风险管理」「风险认知」「本金安全」「杠杆」「仓位管理」「风险系...
First-time openInvest installation and onboarding. **ONLY use when** user explicitly says "set up invest" / "init invest...
invest系列:统一个股分析。覆盖A股/港股/美股,自动匹配分析模式。 快速判断:「分析这只股票」「看看XX公司」「这只股怎么样」「该不该买」「要不要卖」 美股量化:「分析AAPL」「美股」「NVDA」「价值投资」「ROE」「护城河」...
Metodología para buscar y contrastar fuentes sobre un hecho de historia argentina, evaluar su calidad e independencia, y...
Deep investigation of bugs, performance issues, or unexpected behavior
Systematic root-cause debugging. Use when: diagnosing bugs, investigating failures, debugging flaky tests, tracing unexp...
Systematic diagnosis for unknown failures — local environment, tool setup, CI vs local divergence, hook misbehavior, and...
Guide diagnosis of a user-reported symptom — map to diagnostics, collect data, analyze
Investigate a URL or page using Playwright browser
[Fix & Debug] Investigate and explain how existing features or logic work. READ-ONLY exploration with no code changes.
Deep, multi-lens codebase investigation with evidence-based proofing, cross-referencing, diagrams, and synthesis. Use wh...
Run (or re-run) Stage 1 only — the Problem Investigator: citation graph, elite pool, deep reading, and the grounded Rese...
Investigation flow. Takes a question about the system (why does X happen, where does Y live, is Z feasible, what broke)...
Investigates a bug or unexpected behavior from reproduction to root cause with a panel of independent hypothesis agents,...
Validate user claims against codebase and git history, trace to root cause, and propose a fix
Expert guidance for deep security investigations. Use this when the user asks to "investigate" a case, entity, or incide...
Systematic debugging with hypothesis testing, bounded retries, and optional edit freeze. Use when user says "debug this"...
Run before starting an implementation task — scout + gather assemble relevant files, functions, tests, and notes into a...
Debug and investigate code issues using search and AI analysis. Use when stuck on bugs, tracing execution flow, or under...
Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law:...
Use when the user asks to diagnose a bug, find the root cause of a failing behavior, or run a hypothesis-by-hypothesis i...
Reproduce a bug or resolve a bounded technical uncertainty using evidence and small experiments. Use whenever a cause, o...
Investigate bugs and errors in Elixir/Phoenix — root-cause analysis for crashes, exceptions, stack traces, test failures...
Multi-provider adversarial investigation. Claude (Opus) and Codex (GPT, model from ~/.codex/config.toml) debate through...
Systematic debugging with root cause investigation. (gstack)
Guide and conduct user research — from planning through synthesis. Interview scripts, survey design, usability test pla...
Plan how to dig into a fuzzy problem, run the hands-off parts as a workflow, then work through what it found.
Investigate, diagnose, RCA, "why is X slow/broken/down", "what changed" for any production symptom. Triggers on a free-t...
Evidence-based investigation of issues, bugs, API calls, integrations, and other aspects of software development that ne...
Systematically investigate bugs, test failures, build errors, performance issues, or unexpected behavior by cycling thro...
Use when user asks 'what is X', 'how does X work', 'find out about', 'analyze', 'explain the code', or needs quick codeb...
Deep investigation of errors, bugs, or codebase questions without making any code changes. Use when user mentions invest...
Systematic root-cause debugging. Iron Law: no fixes without root cause investigation first. Four phases: Root Cause Inve...
系统化 root-cause debugging。遵守“没有调查就没有修复”的铁律, 先锁范围、看模式、测假设,再实现修复与验证。 (gstack)
Read-only workflow for investigating how a system behaves — understanding how something works, confirming whether it doe...
Requires a compatible AI agent and web access for live checks; optional Python 3.10+ case tools. Trace claims and media...
- Start-here router and tradecraft baseline for any investigation into a person, company, domain, image or selector.
Start-here router and tradecraft baseline for any investigation into a person, company, domain, image or selector. Sets...
Mandatory protocol that prevents AI agents from fabricating information. Forces best practice search before every action...
Deep bug investigation using consultant agent. Identifies root causes and fix suggestions.
Finds the cause of a bug in an Umbraco package or backoffice extension: reproduces it, gathers evidence, and tests one h...
Build an evidence-backed working model of an existing codebase. Use when you must orient in a large or unfamiliar reposi...
Investigate a codebase topic and produce structured markdown documentation. Collects investigation scope, explores the c...
Generate dependency diagrams from code or architecture. Traces code-level dependencies (hooks, queries, providers, compo...
Investigate DNSConfigForming warnings on pods. Analyzes DNS policy configuration, host network settings, and nameserver...
Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or i...
Debug a failing golden test from GitHub Actions logs and fix the root cause without papering over nondeterminism.
Investigate platform incidents, perform RCA, create incident documentation, and follow alert runbooks in the Kagenti pla...
Investigate a failing integration test from a GitHub issue. Downloads logs/artifacts, analyzes the failure, examines rel...
Investigate inventory discrepancies by tracing receiving, WMS balance, physical count, picking, and adjustment evidence.
Investigates identified issues in a LearningAgent session by reading the transcript, determining root causes, and updati...
Automatically investigate logs when errors occur, debugging issues, or troubleshooting problems. Check frontend logs (Lo...
Investigate merkle root mismatch alerts between relayer and validators. Use when alerts mention "merkle root mismatch",...
Diagnose why a product metric changed (dropped, spiked, or plateaued) by orchestrating breakdowns, actors, paths, lifecy...
Investigate picking errors by tracing order, pick record, SKU, location, scanner, pack, ship, and customer evidence.
Deep investigation of a failing pod. Gathers logs, events, and resource status to identify root cause. Keywords: investi...
---
Investigate shipping errors by tracing order, pick, pack, label, scan, carrier, delivery, and customer evidence.
Investigate stuck messages in relayer queue. Use when alerts mention "queue length > 0", to diagnose why messages are st...
Investigate stuck messages in relayer queue. Use when alerts mention "queue length greater than 0", to diagnose why mes...
Runs an evidence-based investigation of a bug, failure, or unexpected behavior with investigate and publishes the result...
- Investigator OPSEC — threat-model who might notice you, control your attribution surface across IP, ASN, browser and T...
Investigator OPSEC — threat-model who might notice you, control your attribution surface across IP, ASN, browser and TLS...
Use when planning or designing features and need to understand current codebase state, find existing patterns, or verify...
Use when a result is surprising, impossible, contradicts a sanity check, a pipeline fails, a model won't converge, or a...
Systematically trace code flows, locate implementations, diagnose performance issues, and map system architecture. Use w...
Automatically activated when user asks how something works, wants to understand unfamiliar code, needs to explore a new...
Investigates HEC-HMS internals through decompiled Java classes. Provides JythonHms API reference, CLI options, version-s...
Generate weekly PagerDuty incident reports for fan-audio and fusion services with root cause analysis from GCP logs. Out...
Investigates phishing email incidents from initial user report through header analysis, URL/attachment detonation, impac...
Identify, collect, and analyze ransomware attack artifacts to determine the variant, initial access vector, encryption s...
Investigate GitHub repository history before risky code changes using git blame/log, GitHub PRs, review comments, squash...
Systematic codebase investigation producing structured Obsidian documentation with DataviewJS auto-indexing
Create an investigation ticket + live-doc for sustained root-cause work (retros, bug archaeology, regression hunts).
Scaffolds a structured investigation in scratch/ for empirical research and documentation. Use when the user says "start...
Deep-dive investigation with documentation output.
Analyze feature requests, refactor plans, or technical decisions to determine investment value and provide recommendatio...
Cost guardrail for AWS DevOps Agent that covers ALL AWS services and native agent tools. Before the agent makes any paid...
Create investigations from security events, detections, or LCQL queries. Performs HOLISTIC investigations - not just pro...
Use when appending structured perf investigation notes and evidence.
Use when there are 2+ consecutive failures, repeated errors, or the work feels stuck - pauses implementation, switches t...
This skill should be used when the user asks to "investigate code", "analyze implementation", "find patterns", "understa...