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。
Audit and reorganize the Quant multi-project workspace. An agent skill from Sixian-Li/plain-backtest.
Install Quant Tidy
$ npx skills add Sixian-Li/plain-backtest --skill quant-tidy -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Sixian-Li/plain-backtest quant-tidy --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/Sixian-Li/plain-backtest.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/quant-tidy .claude/skills/quant-tidy && 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 "quant-tidy" agent skill from https://github.com/Sixian-Li/plain-backtest/tree/main/.agents/skills/quant-tidy into .claude/skills/quant-tidy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quant-tidy", 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/Sixian-Li/plain-backtest/tree/main/.agents/skills/quant-tidyType 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 Sixian-Li/plain-backtest --skill quant-tidy -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Sixian-Li/plain-backtest quant-tidy --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Sixian-Li/plain-backtest.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/quant-tidy .agents/skills/quant-tidy && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "quant-tidy" agent skill from https://github.com/Sixian-Li/plain-backtest/tree/main/.agents/skills/quant-tidy into .agents/skills/quant-tidy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quant-tidy", 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 Sixian-Li/plain-backtest --skill quant-tidy -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Sixian-Li/plain-backtest quant-tidy --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Sixian-Li/plain-backtest.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/quant-tidy .cursor/skills/quant-tidy && 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 "quant-tidy" agent skill from https://github.com/Sixian-Li/plain-backtest/tree/main/.agents/skills/quant-tidy into .cursor/skills/quant-tidy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quant-tidy", 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/Sixian-Li/plain-backtest.git --path .agents/skills/quant-tidy--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 Sixian-Li/plain-backtest --skill quant-tidy -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Sixian-Li/plain-backtest quant-tidy --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Sixian-Li/plain-backtest.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/quant-tidy .gemini/skills/quant-tidy && 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 "quant-tidy" agent skill from https://github.com/Sixian-Li/plain-backtest/tree/main/.agents/skills/quant-tidy into .gemini/skills/quant-tidy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quant-tidy", 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 Sixian-Li/plain-backtest quant-tidyInstalls 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 Sixian-Li/plain-backtest --skill quant-tidy -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Sixian-Li/plain-backtest.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/quant-tidy .github/skills/quant-tidy && 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 "quant-tidy" agent skill from https://github.com/Sixian-Li/plain-backtest/tree/main/.agents/skills/quant-tidy into .github/skills/quant-tidy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quant-tidy", 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 Sixian-Li/plain-backtest --skill quant-tidy -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Sixian-Li/plain-backtest quant-tidy --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Sixian-Li/plain-backtest.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/quant-tidy .opencode/skills/quant-tidy && 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 "quant-tidy" agent skill from https://github.com/Sixian-Li/plain-backtest/tree/main/.agents/skills/quant-tidy into .opencode/skills/quant-tidy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quant-tidy", 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.
Facts
- Skill name
quant-tidy- GitHub stars
- 190
- Token cost
- ~1.3k tokens
- SKILL.md length
- 636 words
- Files
- 4 (incl. scripts, references)
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- MIT
At a glance
Audit and reorganize the Quant multi-project workspace. An agent skill from Sixian-Li/plain-backtest.
- Works in 12 steps: Locate the workspace root by finding… → Read references/workspace-contract.md.… → Read backtest/docs/architecture.md and… → …
- Cleaning Quant files
- SKILL.md covers Distributed project, Workflow, Guardrails and Resources
- Runs Python scripts from its folder; calls python
What it does
Quant Tidy is an agent skill from Sixian-Li/plain-backtest. Audit and reorganize the Quant multi-project workspace. Use when moving, renaming, deduplicating, or cleaning Quant files; adding or moving a project; repairing catalog.md, log.md, lineage, path, or environment drift; or checking structural integrity. Routine backtest creation and publication belong to quant-backtest.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/workspace-contract.md` and `scripts/audit_quant_workspace.py`).
It sits in Business, Finance & HR, covering Trading and backtesting. The repository describes itself as: Say It Simply, Test It Properly. Agent-powered strategy research with independent ledger checks and reproducible reports. The licence is MIT.
When your agent uses it
- Cleaning Quant files
- Moving a project
- Repairing catalog.md
- Environment drift
Example prompts
- “/quant-tidy”
Requirements
- Python 3
Workflow steps
12 steps, taken from the first numbered list in SKILL.md.
- Locate the workspace root by finding catalog.md, log.md, data/, and backtest/. Read catalog.md and log.md first.
- Read references/workspace-contract.md. Preserve shared data and project boundaries defined there.
- Read backtest/docs/architecture.md and backtest/experiments/lineage.json, then run backtest/.venv/bin/python -m scripts.audit_workspace…
- Inspect the proposed changes before moving files. Never modify purchased raw data. Keep unrelated user changes.
- Put shared datasets under data/; put every backtest-only environment, dependency, source, test, document, and experiment under backtest/.
- Keep canonical experiments below backtest/experiments//____/, with a matching full created_on in lineage. Keep tests below tests/core…
- Keep root catalog.md to one fenced text tree plus its title. Give every important entry a one-sentence purpose; put no status, result…
- Append one concise dated item to root log.md for each material outcome. Keep each item near 100 Chinese characters or shorter when one…
- When structural work touches experiments, confirm every experiment remains registered in both backtest/experiments/index.md and…
- Run .venv/bin/python -m scripts.build_research_catalog after structural experiment/run changes, then run it again with --check. Never…
- Re-run the workspace audit and the relevant project tests. Report unresolved failures; do not silently weaken checks.
- Keep every linked Agent worktree below the primary repository's visible worktrees/ pool. Use backtest/scripts/manage_worktree.py; treat…
What it can do on your machine
Read from SKILL.md and the folder at commit 36adf23. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Quant Tidy loads about 1.3k tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 83 tokens; SKILL.md has 636 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.
Safety
Auto-check passed
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); the scripts in this folder are not scanned.
SKILL.md
The full file from Sixian-Li/plain-backtest at commit 36adf23, republished under its MIT licence (© Sixian-Li). 636 words, ~1,324 tokens.
Download SKILL.mdSave it as
.claude/skills/quant-tidy/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- quant-tidy
- description
- Audit and reorganize the Quant multi-project workspace. Use when moving, renaming, deduplicating, or cleaning Quant files; adding or moving a project; repairing catalog.md, log.md, lineage, path, or environment drift; or checking structural integrity. Routine backtest creation and publication belong to quant-backtest.
Quant Tidy
Keep the workspace understandable to a fresh agent without turning the root into a documentation dump.
Distributed project
This skill is versioned at .agents/skills/quant-tidy/ in this repository. Locate the root from the current checkout; do not depend on a user-level skill or the author’s original workspace. Read README.md and backtest/docs/release/scope.md first. The distribution contains canonical data and experiment definitions, not the complete source archives or historical runs.
This directory is an independent distribution, not a linked worktree. Its own data and environment may be real directories. The shared-link requirement below applies only to linked worktrees created from this repository. Root README.md, LICENSE, and THIRD_PARTY_NOTICES.md are intended distribution files.
Workflow
- Locate the workspace root by finding
catalog.md,log.md,data/, andbacktest/. Readcatalog.mdandlog.mdfirst. - Read
references/workspace-contract.md. Preserve shared data and project boundaries defined there. - Read
backtest/docs/architecture.mdandbacktest/experiments/lineage.json, then runbacktest/.venv/bin/python -m scripts.audit_workspacefrombacktest/. If unavailable, runscripts/audit_quant_workspace.py --workspace <root>from this skill. - Inspect the proposed changes before moving files. Never modify purchased raw data. Keep unrelated user changes.
- Put shared datasets under
data/; put every backtest-only environment, dependency, source, test, document, and experiment underbacktest/. - Keep canonical experiments below
backtest/experiments/<PROGRAM>/<DISPLAY_CODE>__<YY-MM-DD>__<slug>/, with a matching fullcreated_onin lineage. Keep tests belowtests/core,data,lifecycle,reporting, orstrategies/{der,rot,tim}. After changes, update all hard-coded paths, imports, Markdown links, manifests, hashes, and reproducibility commands. Search for old paths withrg. - Keep root
catalog.mdto one fenced text tree plus its title. Give every important entry a one-sentence purpose; put no status, result, decision, or plan there. - Append one concise dated item to root
log.mdfor each material outcome. Keep each item near 100 Chinese characters or shorter when one sentence suffices. - When structural work touches experiments, confirm every experiment remains registered in both
backtest/experiments/index.mdandlineage.json, with exactly one program, one unique display version, and complete parent edges. Confirmactive_run_idandlatest_validated_run_idpoint to real lifecycle runs; treat unreferencedrunningorcompleted_unvalidateddirectories as unfinished cleanup, not as new research nodes. - Run
.venv/bin/python -m scripts.build_research_catalogafter structural experiment/run changes, then run it again with--check. Never hand-edit generatedstrategy_evolution.md,program_evolution/*.md,scorecard.csv, orresearch_map.html. - Re-run the workspace audit and the relevant project tests. Report unresolved failures; do not silently weaken checks.
- Keep every linked Agent worktree below the primary repository's visible
worktrees/pool. Usebacktest/scripts/manage_worktree.py; treat the primary tree as the only canonical delivery location. Before removing a legacy or stale worktree, prove that its branch and validated artifacts are preserved in the primary tree. Shared data and environments must be symlinks, never copies.
Show full SKILL.md (200 more words)Show less
Guardrails
- Do not initialize Git, connect brokers, or delete raw data unless the user explicitly requests it.
- Do not put research conclusions in
catalog.md. - Do not create one explanatory Markdown file per experiment by default; use the central experiment registry and machine config.
- Do not claim the workspace is tidy while old root paths, stale links, or unregistered experiments remain.
- Do not move generated run output back to the experiment root or edit a validated run. Preserve pre-lifecycle outputs under an explicitly labeled legacy directory.
- Do not call a network or agent-session interruption a strategy failure. Resume the active run when possible; prune an interrupted run only after a validated successor exists and the user has authorized cleanup.
- Do not leave canonical experiments flat. Physical program/version/date classification and
lineage.jsonmust agree. Move an experiment with its entireruns/subtree, update live references, and never rewrite the contents of a validated run. - Do not place linked Quant worktrees in hidden, temporary, or external directories, and never overwrite or tolerate an existing real data/environment directory while bootstrapping shared links.
Resources
- Read
references/workspace-contract.mdfor the directory contract and record formats. - Run
scripts/audit_quant_workspace.pywhen the workspace copy of the audit is missing or suspect.
© Sixian-Li, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (scripts, references) in .agents/skills/quant-tidy of Sixian-Li/plain-backtest.
- SKILL.md
- agents/openai.yaml
- references/workspace-contract.md
- scripts/audit_quant_workspace.py
Open the folder on GitHubat commit 36adf23
Compare with similar skills
Quant Tidy 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 |
|---|---|---|---|---|---|---|
| Quant Tidy this skillSixian-Li/plain-backtest | 190 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Tushare Datazillionare/zillionare | 321 | 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 | 875 | — | ~5.9k | Automated safety check: Pass | MIT | |
| Polyclawchainstacklabs/polyclaw | 359 | 1 repos | ~2k | Automated safety check: Pass | Apache-2.0 | |
| Markdownfacioquo/stock-indicators-dotnet | 1.2k | — | ~812 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Tradingview MCP
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…
Digital Oracle
komako-workshop/digital-oracle
Answer prediction questions using market trading data, not opinions.
Polyclaw
chainstacklabs/polyclaw
Trade on Polymarket via split + CLOB execution. An agent skill from chainstacklabs/polyclaw.
Markdown
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…
Openmobius Skill
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.
More from Sixian-Li/plain-backtest
Data Update
Sixian-Li/plain-backtest
Operate and assess the Quant workspace market-data layer through the tested data-update CLI.
Quant Backtest
Sixian-Li/plain-backtest
Run the standardized Quant backtest pipeline from a natural-language strategy through data gating, tested implementation, PyBroker execution, independent-ledger reconciliation, parameter robustness…
Related
Categories
Questions about Quant Tidy
What does Quant Tidy do?
Audit and reorganize the Quant multi-project workspace. An agent skill from Sixian-Li/plain-backtest. Quant Tidy is an agent skill from Sixian-Li/plain-backtest. Audit and reorganize the Quant multi-project workspace.
When should I use Quant Tidy?
Quant Tidy fits situations like: cleaning Quant files; moving a project; repairing catalog.md; environment drift.
How do I install Quant Tidy in Claude Code?
Run `npx skills add Sixian-Li/plain-backtest --skill quant-tidy -a claude-code`. Or copy the skill folder (.agents/skills/quant-tidy in Sixian-Li/plain-backtest) into .claude/skills/quant-tidy in your project. Claude Code loads it when a task matches its description.
How do I install Quant Tidy in Codex?
Run `npx skills add Sixian-Li/plain-backtest --skill quant-tidy -a codex`. Or copy the skill folder (.agents/skills/quant-tidy in Sixian-Li/plain-backtest) into .agents/skills/quant-tidy in your project. Codex loads it when a task matches its description.
Can I use Quant Tidy in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Sixian-Li/plain-backtest --skill quant-tidy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/quant-tidy, .gemini/skills/quant-tidy, .github/skills/quant-tidy and .opencode/skills/quant-tidy in your project.
What does Quant Tidy need to run?
Going by SKILL.md and its folder, Quant Tidy needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Quant Tidy access the network?
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.
Is Quant Tidy safe to install?
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Quant Tidy use?
Quant Tidy is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Quant Tidy use?
About 1.3k tokens (SKILL.md is roughly 5.3k 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 1.2k tokens, read only when the agent opens those files.
What are the alternatives to Quant Tidy?
Skills that share tags, products or a category with Quant Tidy: Tushare Data (zillionare/zillionare, 321 stars), Tradingview MCP (atilaahmettaner/tradingview-mcp, 5k stars), Digital Oracle (komako-workshop/digital-oracle, 875 stars) and Polyclaw (chainstacklabs/polyclaw, 359 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Quant Tidy?
Sixian-Li (a GitHub user) maintains it in Sixian-Li/plain-backtest, which has 190 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 27, 2026.
Source: Sixian-Li/plain-backtest on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.