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。
Write {Name}.Catalog.cs listings with CatalogListingBuilder — parameters, results, chart panes, isRequired and isReusable rules — register them in Catalog.Listings.cs, refresh the catalog shape…
$ npx skills add facioquo/stock-indicators-dotnet --skill indicator-catalog -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install facioquo/stock-indicators-dotnet indicator-catalog --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/facioquo/stock-indicators-dotnet.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/indicator-catalog .claude/skills/indicator-catalog && 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 "indicator-catalog" agent skill from https://github.com/facioquo/stock-indicators-dotnet/tree/main/.agents/skills/indicator-catalog into .claude/skills/indicator-catalog/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "indicator-catalog", 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/facioquo/stock-indicators-dotnet/tree/main/.agents/skills/indicator-catalogType 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 facioquo/stock-indicators-dotnet --skill indicator-catalog -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install facioquo/stock-indicators-dotnet indicator-catalog --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/facioquo/stock-indicators-dotnet.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/indicator-catalog .agents/skills/indicator-catalog && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "indicator-catalog" agent skill from https://github.com/facioquo/stock-indicators-dotnet/tree/main/.agents/skills/indicator-catalog into .agents/skills/indicator-catalog/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "indicator-catalog", 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 facioquo/stock-indicators-dotnet --skill indicator-catalog -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install facioquo/stock-indicators-dotnet indicator-catalog --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/facioquo/stock-indicators-dotnet.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/indicator-catalog .cursor/skills/indicator-catalog && 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 "indicator-catalog" agent skill from https://github.com/facioquo/stock-indicators-dotnet/tree/main/.agents/skills/indicator-catalog into .cursor/skills/indicator-catalog/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "indicator-catalog", 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/facioquo/stock-indicators-dotnet.git --path .agents/skills/indicator-catalog--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 facioquo/stock-indicators-dotnet --skill indicator-catalog -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install facioquo/stock-indicators-dotnet indicator-catalog --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/facioquo/stock-indicators-dotnet.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/indicator-catalog .gemini/skills/indicator-catalog && 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 "indicator-catalog" agent skill from https://github.com/facioquo/stock-indicators-dotnet/tree/main/.agents/skills/indicator-catalog into .gemini/skills/indicator-catalog/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "indicator-catalog", 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 facioquo/stock-indicators-dotnet indicator-catalogInstalls 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 facioquo/stock-indicators-dotnet --skill indicator-catalog -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/facioquo/stock-indicators-dotnet.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/indicator-catalog .github/skills/indicator-catalog && 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 "indicator-catalog" agent skill from https://github.com/facioquo/stock-indicators-dotnet/tree/main/.agents/skills/indicator-catalog into .github/skills/indicator-catalog/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "indicator-catalog", 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 facioquo/stock-indicators-dotnet --skill indicator-catalog -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install facioquo/stock-indicators-dotnet indicator-catalog --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/facioquo/stock-indicators-dotnet.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/indicator-catalog .opencode/skills/indicator-catalog && 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 "indicator-catalog" agent skill from https://github.com/facioquo/stock-indicators-dotnet/tree/main/.agents/skills/indicator-catalog into .opencode/skills/indicator-catalog/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "indicator-catalog", 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.
indicator-catalogWrite {Name}.Catalog.cs listings with CatalogListingBuilder — parameters, results, chart panes, isRequired and isReusable rules — register them in Catalog.Listings.cs, refresh the catalog shape…
Indicator Catalog is an agent skill from facioquo/stock-indicators-dotnet. Write {Name}.Catalog.cs listings with CatalogListingBuilder — parameters, results, chart panes, isRequired and isReusable rules — register them in Catalog.Listings.cs, refresh the catalog shape snapshot, and write {Name}CatalogTests. Use when creating or editing a src/Indicators//{Name}.Catalog.cs file, adding or renaming an indicator parameter or result property, editing src/Common/Catalog/Catalog.Listings.cs, or when a test under tests/Library/Common/Catalog/ fails.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Business, Finance & HR, covering Trading and backtesting. The repository describes itself as: Stock Indicators for .NET is a C NuGet package that transforms raw equity, commodity, forex, or cryptocurrency financial market price quotes into technical indicators and trading… The licence is Apache-2.0.
Read from SKILL.md and the folder at commit e439ae4. 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.
Shell commands in SKILL.md call:
dotnetFrom 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.
Indicator Catalog loads about 1.6k tokens when it runs. Until then it costs about 128 tokens; SKILL.md has 591 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 facioquo/stock-indicators-dotnet at commit e439ae4, republished under its Apache-2.0 licence (© facioquo). 591 words, ~1,624 tokens.
.claude/skills/indicator-catalog/SKILL.md (or your agent's skills folder).The catalog drives automated execution, code generation, and charting, so every listing must bind to a real method, parameter, and result property. The tests in tests/Library/Common/Catalog/ enforce most rules below across every listing.
src/Indicators/{folder}/{Name}/{Name}.Catalog.cs declares one CommonListing and one listing per supported style. src/Indicators/e-j/Ema/Ema.Catalog.cs is the reference:
public static partial class Ema
{
internal static readonly IndicatorListing CommonListing =
new CatalogListingBuilder()
.WithName("Exponential Moving Average")
.WithId("EMA")
.WithCategory(Category.MovingAverage)
.AddParameter<int>("lookbackPeriods", "Lookback Period", description: "Number of periods for the EMA calculation", isRequired: true, defaultValue: 20, minimum: 2, maximum: 250)
.AddResult(nameof(EmaResult.Ema), "EMA", IndicatorResult.PricePane, ResultType.Default, isReusable: true)
.Build();
internal static readonly IndicatorListing SeriesListing =
new CatalogListingBuilder(CommonListing)
.WithStyle(Style.Series)
.WithMethodName("ToEma")
.Build();
// BufferListing: Style.Buffer + "ToEmaList"; StreamListing: Style.Stream + "ToEmaHub"
}.WithMethodName() only on style listings: To{Name} for Series, To{Name}List for Buffer, To{Name}Hub for Stream.Build() derives ResultRecordType from the method name, so a method of the wrong style reports the wrong result shape.WithId sets the UIID that names the regression baseline file ({uiid-lowercase}.standard.json) and the Catalog.Get(id, style) lookup.Category an existing peer uses; MACD, Ichimoku, and Pivot Points are PriceTrend, and Beta and ATR are PriceCharacteristic.| Builder method | Parameter type |
|---|---|
AddParameter<T>() | int, double, decimal, and other primitive values; always pass minimum and maximum |
AddEnumParameter<T>() | Enums |
AddDateParameter() | DateTime |
AddSeriesParameter() | An IReadOnlyList<IReusable> input, such as the comparison series of Beta, Correlation, and PRS |
parameterName matches the method's parameter name exactly; a mismatch makes a catalog-bound caller silently receive the default instead of the supplied value.ListingExecutor binds them positionally and picks an overload by argument count.isRequired: false exactly when the C# signature gives the parameter a default, and set defaultValue equal to that C# default.isRequired: false only if the listing declares no defaultValue (VWAP startDate). If the shorter overload behaves differently from the advertised default (ToPrs(sourceEval, sourceBase) computes no PrsPercent), use isRequired: true; callers reach the shorter form with WithoutParam(name) at execution time.AddResult(dataName, displayName, chartPane, dataType, isReusable):
dataName is nameof(TResult.Property), never a string literal, so a renamed property fails the build. displayName is a literal human label.chartPane is IndicatorResult.PricePane for a value at price level, a shared pane name (conventionally the indicator name, such as "Macd") for results with common non-price units, and null for a non-numeric result such as a pattern match.isReusable: true marks exactly one result on an IReusable model, the property that Value returns. An ISeries model marks none. Build() throws when more than one is marked.ResultType sets the chart form: Default, Centerline, Channel, Bar, BarStacked, or Point.Register each listing inside PopulateCatalog() in src/Common/Catalog/Catalog.Listings.cs. Blocks sort alphabetically by indicator ID, are separated by a blank line, and open with a // {ID} ({Full Name}) comment, or // {Full Name} when no abbreviation is conventional. Within a block the order is Buffer, Series, Stream:
// EMA (Exponential Moving Average)
_listings.Add(Ema.BufferListing);
_listings.Add(Ema.SeriesListing);
_listings.Add(Ema.StreamListing);
// Beta
_listings.Add(Beta.SeriesListing);Adding or changing a parameter or result changes tests/Library/TestData/catalog/shape.snapshot.txt. Regenerate it, review the diff, then rerun the test without the variable to confirm it passes; the regeneration run reports Inconclusive:
UPDATE_CATALOG_SHAPE=1 dotnet test tests/Library/Tests.Indicators.csproj --filter CatalogShapeMatchesSnapshottests/Library/Indicators/{folder}/{Name}/{Name}CatalogTests.cs declares public class {Name}CatalogTests : TestBase in namespace Catalogging, with one {Name}{Style}_InCatalog_ReturnsAllVariants() method per style asserting Name, Uiid, Style, Category, MethodName, and the parameter and result counts. tests/Library/Indicators/t-z/Wma/WmaCatalogTests.cs is a minimal example.
The catalog-wide tests verify method binding per style, dataName and parameterName resolution, parameter order, isRequired and default agreement with the C# signature, chart panes, and the shape snapshot. They do not check names, categories, or value ranges, so keep the per-indicator test.
.WithMethodName() on CommonListing.dataName as a string literal where nameof can reach the member.isReusable: true on an ISeries model or on more than one result.isRequired: false with a defaultValue the C# signature does not apply when the argument is omitted.shape.snapshot.txt; regenerate it.© facioquo, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .agents/skills/indicator-catalog of facioquo/stock-indicators-dotnet.
Open the folder on GitHubat commit e439ae4
Indicator Catalog 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 |
|---|---|---|---|---|---|---|
| Indicator Catalog this skillfacioquo/stock-indicators-dotnet | 1.2k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Tushare Datazillionare/zillionare | 319 | 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 | 870 | — | ~5.9k | Automated safety check: Pass | MIT | |
| Fintoolsecond-state/fintool | 316 | 1 repos | ~5.9k | Automated safety check: Pass | None | |
| Polyclawchainstacklabs/polyclaw | 360 | 1 repos | ~2k | Automated safety check: Pass | Apache-2.0 |
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.
second-state/fintool
Financial trading CLIs — spot and perp trading on Hyperliquid, Binance, Coinbase, OKX.
chainstacklabs/polyclaw
Trade on Polymarket via split + CLOB execution. An agent skill from chainstacklabs/polyclaw.
MobiusQuant/OpenMobius-skill
Provides multi-school trading Q&A, chart/OHLCV analysis, annotation, and fresh-market workflows covering ICT/SMC, ChanLun, Wyckoff, Price Action, Order Flow, VSA, and Elliott Wave.
facioquo/stock-indicators-dotnet
Format and lint Markdown in this repository against GitHub Flavored Markdown and its markdownlint-cli2 configuration — headers, lists, code fences, callouts (VitePress containers on docs-site pages…
facioquo/stock-indicators-dotnet
Implement Series-style batch indicators (To{Name}() in {Name}.Series.cs), the canonical numerical reference every BufferList and StreamHub must match exactly.
facioquo/stock-indicators-dotnet
Implement StreamHub real-time indicators — base-class choice (ChainHub, BarProvider, StreamHub), constructor and ToIndicator conventions, RollbackState overrides, per-tick performance rules…
facioquo/stock-indicators-dotnet
Benchmark indicators with BenchmarkDotNet in tools/performance — add Series, Buffer, Stream, and style-comparison benchmarks, spot-check one indicator against committed baselines, evaluate the full…
facioquo/stock-indicators-dotnet
Author indicator reference pages on the VitePress documentation site — page section order, parameter and result tables, warmup and convergence wording, chaining and streaming examples, the…
facioquo/stock-indicators-dotnet
Implement BufferList incremental indicators ({Name}List, a BufferList<TResult subclass) — increment interface choice, constructor and To{Name}List() conventions, rolling-buffer helpers, pruning and…
Categories
Write {Name}.Catalog.cs listings with CatalogListingBuilder — parameters, results, chart panes, isRequired and isReusable rules — register them in Catalog.Listings.cs, refresh the catalog shape…. Indicator Catalog is an agent skill from facioquo/stock-indicators-dotnet.cs, refresh the catalog shape snapshot, and write {Name}CatalogTests.
Indicator Catalog fits situations like: editing a src/Indicators//{Name}.Catalog.cs file; renaming an indicator parameter; result property; editing src/Common/Catalog/Catalog.Listings.cs.
Run `npx skills add facioquo/stock-indicators-dotnet --skill indicator-catalog -a claude-code`. Or copy the skill folder (.agents/skills/indicator-catalog in facioquo/stock-indicators-dotnet) into .claude/skills/indicator-catalog in your project. Claude Code loads it when a task matches its description.
Run `npx skills add facioquo/stock-indicators-dotnet --skill indicator-catalog -a codex`. Or copy the skill folder (.agents/skills/indicator-catalog in facioquo/stock-indicators-dotnet) into .agents/skills/indicator-catalog 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 facioquo/stock-indicators-dotnet --skill indicator-catalog -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/indicator-catalog, .gemini/skills/indicator-catalog, .github/skills/indicator-catalog and .opencode/skills/indicator-catalog in your project.
Going by SKILL.md and its folder, Indicator Catalog needs the command-line tools its instructions call (dotnet).
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.
Indicator Catalog is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Indicator Catalog: Tushare Data (zillionare/zillionare, 319 stars), Tradingview MCP (atilaahmettaner/tradingview-mcp, 5k stars), Digital Oracle (komako-workshop/digital-oracle, 870 stars) and Fintool (second-state/fintool, 316 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
facioquo (a GitHub organization) maintains it in facioquo/stock-indicators-dotnet, which has 1,247 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 7, 2026.
Source: facioquo/stock-indicators-dotnet on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.