Tushare Data
zillionare/zillionare
面向中文自然语言的 Tushare 数据研究技能。用于把“看看这只股票最近怎么样”“帮我查财报趋势”“最近哪个板块最强”“北向资金在买什么”“给我导出一份行情数据”这类请求,转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究场景。
Manage the advisor trade lifecycle from order entry through settlement, covering block trading, allocation, pre-trade compliance, custodian routing, and error correction.
$ npx skills add JoelLewis/finance_skills --skill order-management-advisor -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install JoelLewis/finance_skills order-management-advisor --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/JoelLewis/finance_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/advisory-practice/skills/order-management-advisor .claude/skills/order-management-advisor && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "order-management-advisor" agent skill from https://github.com/JoelLewis/finance_skills/tree/main/plugins/advisory-practice/skills/order-management-advisor into .claude/skills/order-management-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "order-management-advisor", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/JoelLewis/finance_skills/tree/main/plugins/advisory-practice/skills/order-management-advisorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add JoelLewis/finance_skills --skill order-management-advisor -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install JoelLewis/finance_skills order-management-advisor --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JoelLewis/finance_skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/advisory-practice/skills/order-management-advisor .agents/skills/order-management-advisor && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "order-management-advisor" agent skill from https://github.com/JoelLewis/finance_skills/tree/main/plugins/advisory-practice/skills/order-management-advisor into .agents/skills/order-management-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "order-management-advisor", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add JoelLewis/finance_skills --skill order-management-advisor -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install JoelLewis/finance_skills order-management-advisor --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JoelLewis/finance_skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/advisory-practice/skills/order-management-advisor .cursor/skills/order-management-advisor && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "order-management-advisor" agent skill from https://github.com/JoelLewis/finance_skills/tree/main/plugins/advisory-practice/skills/order-management-advisor into .cursor/skills/order-management-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "order-management-advisor", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/JoelLewis/finance_skills.git --path plugins/advisory-practice/skills/order-management-advisor--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add JoelLewis/finance_skills --skill order-management-advisor -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install JoelLewis/finance_skills order-management-advisor --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JoelLewis/finance_skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/advisory-practice/skills/order-management-advisor .gemini/skills/order-management-advisor && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "order-management-advisor" agent skill from https://github.com/JoelLewis/finance_skills/tree/main/plugins/advisory-practice/skills/order-management-advisor into .gemini/skills/order-management-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "order-management-advisor", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install JoelLewis/finance_skills order-management-advisorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add JoelLewis/finance_skills --skill order-management-advisor -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/JoelLewis/finance_skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/advisory-practice/skills/order-management-advisor .github/skills/order-management-advisor && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "order-management-advisor" agent skill from https://github.com/JoelLewis/finance_skills/tree/main/plugins/advisory-practice/skills/order-management-advisor into .github/skills/order-management-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "order-management-advisor", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add JoelLewis/finance_skills --skill order-management-advisor -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install JoelLewis/finance_skills order-management-advisor --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JoelLewis/finance_skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/advisory-practice/skills/order-management-advisor .opencode/skills/order-management-advisor && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "order-management-advisor" agent skill from https://github.com/JoelLewis/finance_skills/tree/main/plugins/advisory-practice/skills/order-management-advisor into .opencode/skills/order-management-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "order-management-advisor", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
order-management-advisorManage the advisor trade lifecycle from order entry through settlement, covering block trading, allocation, pre-trade compliance, custodian routing, and error correction.
Order Management Advisor is an agent skill from JoelLewis/finance_skills. Manage the advisor trade lifecycle from order entry through settlement, covering block trading, allocation, pre-trade compliance, custodian routing, and error correction. Use when the user asks about designing an OMS for an RIA, executing model portfolio changes across many accounts, structuring block trades with fair allocation, configuring pre-trade compliance rules or restricted lists, routing orders to multiple custodians, handling trade errors or corrections, managing cash in trading workflows, or evaluating…
Its SKILL.md is about 9.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/examples.md`).
It sits in Sales & Support, covering E-commerce operations, Trading and backtesting and Stock and market analysis. The repository describes itself as: Claude Code skill plugins for financial services — 81 skills across 7 domain plugins covering investment management, compliance, advisory practice, trading, and operations. The licence is MIT.
7 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 5c498ea. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Order Management Advisor loads about 9.2k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 195 tokens; SKILL.md has 4,986 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from JoelLewis/finance_skills at commit 5c498ea, republished under its MIT licence (© JoelLewis). 4,986 words, ~9,150 tokens.
.claude/skills/order-management-advisor/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.The order management system is the operational bridge between investment decisions and trade execution. In an advisory practice, the OMS receives trade instructions generated by the portfolio management system (PMS), validates them against compliance rules, aggregates them into block orders where appropriate, routes them to custodians or brokers for execution, and tracks them through settlement.
Advisory OMS platforms differ materially from institutional OMS platforms. An advisory OMS is optimized for model-driven trading across many small accounts — a single model change may generate hundreds or thousands of individual account-level trades that must be aggregated, compliance-checked, and routed efficiently. An institutional OMS, by contrast, is designed for large orders with complex execution strategies such as algorithmic trading, dark pool access, and multi-venue order splitting.
Core OMS functions in an advisory context include:
The OMS sits between the PMS (which generates trades) and the custodian (which executes and settles them). Data flows bidirectionally: the PMS sends trade proposals to the OMS, and the OMS sends execution results back to the PMS for portfolio accounting updates.
Common advisory OMS platforms include Orion Trading (integrated with Orion Portfolio Solutions), Tamarac Trading (part of the Envestnet ecosystem), Schwab iRebal (now part of Schwab Advisor Services, widely used by RIAs custodying at Schwab), and Fidelity's trading tools (available to advisors on the Fidelity Institutional platform). Many of these platforms combine OMS and rebalancing functionality, blurring the line between PMS and OMS.
Standard order types (market, limit, stop, stop-limit) and time-in-force instructions (day, GTC, IOC, FOK) carry their usual meanings; the advisory-specific considerations are below. Two operational notes: custodians typically cap GTC duration at 60 or 90 calendar days, and FOK is rarely used in advisory trading except for block orders where partial fills would create allocation complications.
NAV-sensitive orders (mutual funds):
ETF vs. mutual fund order handling: ETFs trade intraday on exchanges like stocks and support all standard order types (market, limit, stop, stop-limit) and time-in-force instructions. Mutual funds trade once per day at NAV and support only purchase, redemption, and exchange orders. This distinction has significant implications for block trading — ETF blocks can be executed with price control during market hours, while mutual fund blocks settle at the same NAV regardless of when the order is placed (provided it is before the cutoff).
Block trading is the practice of aggregating orders for the same security across multiple client accounts into a single block order. This achieves better execution through larger order size (which may access better pricing or reduce per-share transaction costs) and operational efficiency (one order instead of hundreds).
Regulatory framework:
Block trading by investment advisers is governed by SEC no-action letters (most notably the SMC Capital, Inc. no-action letter of 1995) and FINRA guidance. The SEC has permitted block trading by advisers provided that:
Fair allocation methods:
Partial fills: When a block order is only partially filled, the allocation methodology must be applied to the partial fill. Under pro-rata allocation, each account receives its proportional share of the partial fill, rounded to whole shares. Rounding adjustments should follow a documented, consistent procedure (e.g., accounts with the largest fractional shares round up first, or rounding priority rotates). The remaining unfilled portion may be carried forward as a new order or canceled, depending on the advisor's trading policy.
Documentation requirements:
Pre-trade compliance is the automated (and sometimes manual) checking of proposed orders against a set of rules and restrictions before the orders are submitted for execution. This is a critical control point in the trade workflow — catching violations before execution avoids costly corrections, client harm, and regulatory exposure.
Common pre-trade compliance checks:
Hard blocks vs. soft blocks:
Regulatory expectations: Pre-trade compliance is not merely a best practice — it is a regulatory expectation. FINRA Rule 3110 (supervision) requires firms to establish supervisory systems reasonably designed to prevent violations. Automated pre-trade compliance checks are a key component of that supervisory system. SEC examination staff routinely evaluate the scope, effectiveness, and documentation of pre-trade compliance processes. Gaps in pre-trade compliance — such as failure to screen against restricted lists or failure to enforce IPS constraints — are common examination findings.
The end-to-end trade lifecycle in an advisory firm proceeds through a defined sequence of stages, each with specific responsible parties, system interactions, and exception-handling requirements.
Stage 1 — Investment decision: The investment committee, portfolio manager, or individual advisor decides to make a trade. This may be a model portfolio change (replacing one holding with another across all accounts assigned to the model), a rebalance (bringing drifted accounts back to target weights), or an ad hoc trade (a client-specific transaction such as raising cash for a withdrawal).
Stage 2 — Trade generation in PMS: The portfolio management system translates the investment decision into account-level trade proposals. For a model change, the PMS identifies every account assigned to the affected model, calculates the required trade for each account based on current holdings and target weights, and generates a trade list. For a rebalance, the PMS applies drift thresholds and target weights to generate trades that bring each account back into alignment.
Stage 3 — Pre-trade compliance check: The generated trades are screened against the compliance rule engine. Hard blocks are flagged for resolution. Soft blocks are flagged for review. Trades that pass all checks are marked as compliant and eligible for execution.
Stage 4 — Advisor review and approval: Depending on the firm's workflow, an advisor or portfolio manager reviews the trade list before submission. Some firms require explicit approval for all trades; others auto-approve model-driven trades and require manual approval only for exceptions. The review step provides a human checkpoint for catching errors that automated compliance may miss (e.g., a trade that is technically compliant but inappropriate given a client conversation that occurred that morning).
Stage 5 — Order routing to custodian/broker: Approved orders are transmitted to the custodian or executing broker. The OMS applies routing rules based on account-custodian mapping (each account is held at a specific custodian), order type (some custodians support certain order types that others do not), and any firm preferences for execution venues. Orders may be transmitted electronically via FIX protocol, custodian API, or in some cases entered manually into the custodian's trading platform.
Stage 6 — Execution: The custodian or broker executes the order on an exchange, through an internal execution desk, or via a third-party broker. The execution may occur in a single fill or multiple partial fills over time.
Stage 7 — Fill notification: The custodian transmits fill confirmations back to the OMS. The fill data includes the execution price, quantity filled, execution time, and execution venue.
Stage 8 — Allocation (for blocks): For block orders, the OMS allocates the execution results to individual accounts according to the pre-trade allocation methodology. Each account receives its share of the fill at the average execution price.
Stage 9 — Confirmation generation: The OMS generates trade confirmations for each client account reflecting the allocated execution details. Confirmations are delivered to clients per SEC Rule 10b-10 requirements.
Stage 10 — Settlement: Securities and cash are exchanged between counterparties. Since May 28, 2024, the standard settlement cycle for U.S. equities is T+1 (one business day after trade date). Mutual funds generally settle at T+1 as well, though certain fund types may have different settlement cycles. Government securities settle T+1. Listed options were already settling T+1 before the 2024 equity-cycle change and continue to do so.
Status tracking: The OMS maintains real-time status for each order: pending (awaiting compliance check), approved (compliance passed, awaiting submission), submitted (sent to custodian), partially filled, filled, allocated, confirmed, and settled. Exception statuses include rejected (by custodian or compliance), canceled, and error.
Exception handling: Rejected orders require investigation — common reasons include insufficient buying power, invalid security identifier, or custodian system error. Partial fills require a decision on whether to leave the remaining order open, cancel it, or resubmit. Busted trades (trades canceled by the exchange after execution, typically due to erroneous pricing) require reversal of the allocation and client notification.
Advisory firms route orders to custodians for execution. The integration between the OMS and custodian systems is a critical operational link.
FIX protocol (Financial Information eXchange): FIX is the industry-standard protocol for electronic order routing, execution reporting, and trade allocation messaging. FIX connections provide real-time, automated order submission and fill reporting. Most institutional custodians and executing brokers support FIX connectivity. FIX messages follow a defined tag-value format that includes order type, quantity, price, time-in-force, account identifier, and other trade parameters.
Custodian proprietary APIs: Some custodians offer proprietary APIs in addition to or instead of FIX. These APIs may provide functionality beyond basic order routing, such as account data queries, position reporting, and cash balance inquiries. Schwab, Fidelity, and Pershing each provide proprietary APIs for their advisor platforms.
Manual entry: As a fallback, orders can be entered manually into the custodian's trading platform (web-based or desktop). Manual entry is error-prone, slow, and does not scale, but it may be necessary for custodians that do not support electronic integration, for order types not supported by the electronic interface, or during system outages.
Multi-custodian environments: Many advisory firms custody client assets at multiple custodians (e.g., Schwab for some clients, Fidelity for others, Pershing for others). The OMS must maintain an account-custodian mapping and route each order to the correct custodian. A single block trade may need to be split into custodian-specific sub-blocks, each routed to the appropriate custodian. The allocation engine must then reconcile fills across custodians.
Execution venues: Orders routed to a custodian may be executed through several venues:
Best execution: Advisory firms have a fiduciary obligation to seek best execution for client trades. This does not necessarily mean obtaining the lowest possible price on every trade — it means considering the totality of execution quality factors including price improvement, speed of execution, certainty of execution, and overall cost. In a multi-custodian environment, best execution reviews must evaluate execution quality across all custodians. Firms should conduct periodic best execution reviews (typically quarterly or annually) that compare execution quality metrics across custodians, analyze price improvement statistics, assess the impact of custodian-specific order handling practices, and document findings and any corrective actions taken.
Model-driven trading is the systematic process of generating and executing trades based on changes to model portfolios. This is the dominant trading paradigm for advisory firms that use model-based portfolio management.
Model change workflow:
Scale considerations: A single model change can generate hundreds or thousands of individual account trades. A firm with 2,000 accounts on a single model, implementing a two-security swap, generates up to 4,000 individual trades (one sell and one buy per account). The OMS must handle this volume efficiently, with automated compliance checking, block aggregation, and allocation.
Market impact management: When a model change requires buying or selling a significant quantity of a security across many accounts, the aggregate order may be large enough to move the market. Managing market impact requires consideration of:
Cash management within the trading workflow ensures that client accounts maintain appropriate cash levels to meet obligations and investment targets.
Core cash management functions:
Cash threshold alerts: The OMS should flag accounts where cash levels are outside acceptable ranges:
Cash raise priority: When selling securities to raise cash, the firm must define a priority methodology:
Systematic cash sweep vs. manual cash management: Some custodians automatically sweep excess cash into money market funds or bank deposit programs. The OMS should account for sweep timing and thresholds when calculating investable cash. Manual cash management gives the advisor more control but requires more frequent monitoring.
Pending cash flows: The OMS should account for known future cash events when generating trades. Scheduled withdrawals, expected deposits, pending fee debits, and anticipated dividend payments should be factored into cash projections so that trades are not generated that would leave the account short of cash.
Trade errors are an operational reality in advisory practices. The firm's ability to detect, correct, and document errors is a measure of its operational integrity.
Common trade errors:
Error identification timeline:
Error correction process:
Regulatory requirements:
Error prevention: The OMS can implement controls to reduce error frequency:
Error rate tracking: Firms should track error rates (errors per trade volume) as an operational risk metric. Increasing error rates may indicate system issues, training deficiencies, or staffing problems. Error rate data should be reported to management and compliance periodically.
Every trade in an advisory practice must be supported by a complete and accessible audit trail. The audit trail enables regulatory examination, internal supervision, client dispute resolution, and operational analysis.
Components of a complete trade audit trail:
SEC Rule 17a-3/17a-4 (broker-dealer recordkeeping): For dual-registered firms or advisors operating through a broker-dealer, Rule 17a-3 requires creation of order tickets for every transaction, and Rule 17a-4 requires retention of order records for a minimum of six years (the first two years in an easily accessible place). Order tickets must include the terms of the order, the time of entry, the time of execution, the price, and the identity of the associated person who accepted and executed the order.
SEC Rule 204-2 (investment adviser recordkeeping): For SEC-registered investment advisers, Rule 204-2 requires retention of memoranda of each order given for the purchase or sale of any security. These records must be retained for five years from the end of the fiscal year in which the last entry was made.
Consolidated Audit Trail (CAT): The Consolidated Audit Trail, which replaced FINRA's Order Audit Trail System (OATS), requires broker-dealers to report detailed information about orders and executions to a central repository. CAT tracks the entire lifecycle of an order from receipt through routing, execution, modification, and cancellation. While CAT reporting obligations fall primarily on broker-dealers, advisory firms that route orders through affiliated BDs or that are dual-registered must understand the CAT data flowing from their trading activity.
Retention periods: Order records, execution records, and allocation records must be retained for a minimum of six years for broker-dealers (Rule 17a-4) or five years for investment advisers (Rule 204-2). Best practice is to apply the longer period (six years) across all records regardless of registration type.
Supervisory review documentation: FINRA Rule 3110 requires documented supervisory review of trading activity. The supervisor must review trade blotters, exception reports, and allocation records. The review must be documented with the reviewer's identity, the date of review, the scope of the review, and any findings or actions taken. Supervisory review records are themselves subject to the firm's retention schedule.
See references/examples.md for three end-to-end worked examples — a model change across 800 accounts with multi-custodian routing and restrictions, a wrong-security trade error discovered post-settlement, and a multi-custodian best execution review. Load it when the user needs a full scenario walkthrough.
© JoelLewis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file (references) in plugins/advisory-practice/skills/order-management-advisor of JoelLewis/finance_skills.
Open the folder on GitHubat commit 5c498ea
Order Management Advisor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Order Management Advisor this skillJoelLewis/finance_skills | 206 | — | ~9.2k | Automated safety check: Pass | MIT | |
| Tushare Datazillionare/zillionare | 322 | 2 repos | ~2.3k | Automated safety check: Pass | None | |
| Tradingview MCPatilaahmettaner/tradingview-mcp | 5k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Digital Oraclekomako-workshop/digital-oracle | 878 | — | ~5.9k | Automated safety check: Pass | MIT | |
| Amazon Buy Box Monitorbrowser-act/skills | 6.1k | 1 repos | ~1.6k | Automated safety check: Pass | MIT | |
| Tourmind Bookingtourmind-com/Tourmind-Booking-Skills | 1.8k | — | ~13k | Automated safety check: Pass | MIT |
zillionare/zillionare
面向中文自然语言的 Tushare 数据研究技能。用于把“看看这只股票最近怎么样”“帮我查财报趋势”“最近哪个板块最强”“北向资金在买什么”“给我导出一份行情数据”这类请求,转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究场景。
atilaahmettaner/tradingview-mcp
AI Trading Intelligence — live prices, 30+ technical indicators, backtesting (6 strategies), walk-forward overfitting detection, trade logs, equity curves, licensed news sentiment (Marketaux), and…
komako-workshop/digital-oracle
Answer prediction questions using market trading data, not opinions.
browser-act/skills
Pulls Amazon product details, competing seller prices and seller ratings for a given ASIN through the BrowserAct API, without browser automation.
tourmind-com/Tourmind-Booking-Skills
MUST USE for any hotel or accommodation intent in any language, including hotel search, hotel recommendations, nearby accommodation, hostels, guesthouses, resorts, where-to-stay questions, room…
wzj177/ecommerce-image-suite
电商套图生成助手。用户明确提出需要生成电商套图、商品主图、卖点图、场景图、模特图等图片内容时触发. An agent skill from wzj177/ecommerce-image-suite.
JoelLewis/finance_skills
Determine how to distribute capital across asset classes using strategic and tactical allocation frameworks.
JoelLewis/finance_skills
Determine how much capital to allocate to individual positions within a portfolio.
JoelLewis/finance_skills
Analyze commodity markets including futures curve dynamics, roll yield, and supply/demand fundamentals.
JoelLewis/finance_skills
Analyze currency markets, exchange rate mechanics, and FX risk management for international portfolios.
JoelLewis/finance_skills
Provide frameworks for managing and paying off personal debt effectively.
JoelLewis/finance_skills
Build diversified portfolios using correlation analysis, efficient frontier construction, and factor-based diversification.
Categories
Manage the advisor trade lifecycle from order entry through settlement, covering block trading, allocation, pre-trade compliance, custodian routing, and error correction. Order Management Advisor is an agent skill from JoelLewis/finance_skills. Manage the advisor trade lifecycle from order entry through settlement, covering block trading, allocation, pre-trade compliance, custodian routing, and error correction.
Order Management Advisor fits situations like: the user asks about designing an OMS for an RIA; executing model portfolio changes across many accounts; structuring block trades with fair allocation; configuring pre-trade compliance rules.
Run `npx skills add JoelLewis/finance_skills --skill order-management-advisor -a claude-code`. Or copy the skill folder (plugins/advisory-practice/skills/order-management-advisor in JoelLewis/finance_skills) into .claude/skills/order-management-advisor in your project. Claude Code loads it when a task matches its description.
Run `npx skills add JoelLewis/finance_skills --skill order-management-advisor -a codex`. Or copy the skill folder (plugins/advisory-practice/skills/order-management-advisor in JoelLewis/finance_skills) into .agents/skills/order-management-advisor in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JoelLewis/finance_skills --skill order-management-advisor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/order-management-advisor, .gemini/skills/order-management-advisor, .github/skills/order-management-advisor and .opencode/skills/order-management-advisor in your project.
SKILL.md names no scripts, command-line tools or credentials: Order Management Advisor is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Order Management Advisor is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 9.2k tokens (SKILL.md is roughly 37k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.2k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Order Management Advisor: Tushare Data (zillionare/zillionare, 322 stars), Tradingview MCP (atilaahmettaner/tradingview-mcp, 5k stars), Digital Oracle (komako-workshop/digital-oracle, 878 stars) and Amazon Buy Box Monitor (browser-act/skills, 6.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
JoelLewis (a GitHub user) maintains it in JoelLewis/finance_skills, which has 206 GitHub stars. The repository holds 91 skills in this directory. The repository was last updated on July 18, 2026.
Source: JoelLewis/finance_skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.