Agent skill

Hl Quant

当用户要用启发式学习优化量化交易策略时使用：诊断策略弱点、提出有经济含义的假设、只修改策略文件、用固定回测评分器评估，并按严格门槛决定是否接受。触发词包括“启发式探索”“启发式学习”“HL循环”“策略调参”“回测改进”“优化策略分数”“heuristic exploration”“heuristic learning”。

MITAuto-check passed

Install Hl Quant

skills CLI

$ npx skills add toddwyl/hl-quant --skill hl-quant -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install toddwyl/hl-quant hl-quant --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/toddwyl/hl-quant.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/hl-quant .claude/skills/hl-quant && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "hl-quant" agent skill from https://github.com/toddwyl/hl-quant/tree/main/skills/hl-quant into .claude/skills/hl-quant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hl-quant", 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

$skill-installer install https://github.com/toddwyl/hl-quant/tree/main/skills/hl-quant

Type 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.

skills CLI

$ npx skills add toddwyl/hl-quant --skill hl-quant -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install toddwyl/hl-quant hl-quant --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/toddwyl/hl-quant.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/hl-quant .agents/skills/hl-quant && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "hl-quant" agent skill from https://github.com/toddwyl/hl-quant/tree/main/skills/hl-quant into .agents/skills/hl-quant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hl-quant", 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.

skills CLI

$ npx skills add toddwyl/hl-quant --skill hl-quant -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install toddwyl/hl-quant hl-quant --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/toddwyl/hl-quant.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/hl-quant .cursor/skills/hl-quant && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "hl-quant" agent skill from https://github.com/toddwyl/hl-quant/tree/main/skills/hl-quant into .cursor/skills/hl-quant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hl-quant", 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

$ gemini skills install https://github.com/toddwyl/hl-quant.git --path skills/hl-quant

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add toddwyl/hl-quant --skill hl-quant -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install toddwyl/hl-quant hl-quant --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/toddwyl/hl-quant.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/hl-quant .gemini/skills/hl-quant && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "hl-quant" agent skill from https://github.com/toddwyl/hl-quant/tree/main/skills/hl-quant into .gemini/skills/hl-quant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hl-quant", 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.

GitHub CLI

$ gh skill install toddwyl/hl-quant hl-quant

Installs 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).

skills CLI

$ npx skills add toddwyl/hl-quant --skill hl-quant -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/toddwyl/hl-quant.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/hl-quant .github/skills/hl-quant && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "hl-quant" agent skill from https://github.com/toddwyl/hl-quant/tree/main/skills/hl-quant into .github/skills/hl-quant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hl-quant", 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.

skills CLI

$ npx skills add toddwyl/hl-quant --skill hl-quant -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install toddwyl/hl-quant hl-quant --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/toddwyl/hl-quant.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/hl-quant .opencode/skills/hl-quant && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "hl-quant" agent skill from https://github.com/toddwyl/hl-quant/tree/main/skills/hl-quant into .opencode/skills/hl-quant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hl-quant", 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: hl-quant
GitHub stars: 156
Token cost: ~1.1k tokens
SKILL.md length: 252 words
Files: 2 (incl. references)
Skills in repo: 1
Repo updated: Jun 22, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Works in 8 steps: Probe：运行固定评估器，记录基线 score、关键指标和归因材料。 → Diagnose：解释弱点来自哪里，例如入场太早、离场太快、震荡中反复打脸、仓位过… → Propose：每轮只提一个有经济含义的假设，例如“放慢均线可以过滤噪声并持有趋势… → …
SKILL.md covers 什么时候使用, 什么时候不要用, 核心循环 and 固定评估器与唯一可编辑程序, plus 6 more sections
Calls python

What it does

Hl Quant is an agent skill from toddwyl/hl-quant. 当用户要用启发式学习优化量化交易策略时使用：诊断策略弱点、提出有经济含义的假设、只修改策略文件、用固定回测评分器评估，并按严格门槛决定是否接受。触发词包括“启发式探索”“启发式学习”“HL循环”“策略调参”“回测改进”“优化策略分数”“heuristic exploration”“heuristic learning”。

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/framework.md`).

It works with Python. The repository describes itself as: heuristic learning quant. The licence is MIT.

Example prompts

“优化策略分数”
“heuristic exploration”
“heuristic learning”
“/hl-quant”

Requirements

Python 3

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

Probe：运行固定评估器，记录基线 score、关键指标和归因材料。
Diagnose：解释弱点来自哪里，例如入场太早、离场太快、震荡中反复打脸、仓位过度集中、 regime 错配。
Propose：每轮只提一个有经济含义的假设，例如“放慢均线可以过滤噪声并持有趋势更久”，而不是“MA=17 分数最高”。
Patch：只修改策略文件。不要改评估器、数据源、成本模型或评分公式。
Evaluate：用同一评估器重跑，比较 score 和关键指标。
Replay：检查 golden case、实盘约束和已知失败场景没有退化。
Decide：通过严格门槛才接受，否则拒绝并回到 Diagnose。
Compress：删除无触发、负贡献、重复或解释不清的规则，保持策略小而可解释。

What it can do on your machine

Read from SKILL.md and the folder at commit 0b9835d. 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
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

Hl Quant loads about 1.1k tokens when it runs, and up to ~3.1k if it reads all its reference files. Until then it costs about 43 tokens; SKILL.md has 252 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~43
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~3.1k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from toddwyl/hl-quant at commit 0b9835d, republished under its MIT licence (© toddwyl). 252 words, ~1,066 tokens.

Download SKILL.mdSave it as .claude/skills/hl-quant/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: hl-quant
description: 当用户要用启发式学习优化量化交易策略时使用：诊断策略弱点、提出有经济含义的假设、只修改策略文件、用固定回测评分器评估，并按严格门槛决定是否接受。触发词包括“启发式探索”“启发式学习”“HL循环”“策略调参”“回测改进”“优化策略分数”“heuristic exploration”“heuristic learning”。

hl-quant：量化策略的启发式探索 Skill

用固定回测评分器反复评估策略候选：先诊断弱点，再提出一个有经济含义的假设，只改策略文件，最后用同一评分口径决定是否接受。

本 skill 是「启发式探索」通用框架在量化交易领域的实例化。完整框架（核心启发、固定评估器范式、模块结构）见随 skill 分发的 references/framework.md；要把同一方法迁移到性能/转化率/错误率等其它可度量问题，也从该文档入手。下文示例里的指标名、阈值、参数均为教学用的虚构值，不代表任何真实生产策略。

什么时候使用

策略表现弱：Sortino / Sharpe 偏低、回撤偏大、胜率偏低。
需要提高策略 score、收益或风险调整后表现。
需要解释策略为什么失败，而不是只知道分数低。
需要判断某个参数变化是真改进，还是过拟合。

什么时候不要用

已有固定参数空间，只需要纯数值搜索：优先用 Optuna / grid search。
策略逻辑已经冻结，只是在做部署。
还没有固定评估器：先建立评估器，再做 HL。

核心循环

Probe → Diagnose → Propose → Patch → Evaluate → Replay → Decide → Compress

Probe：运行固定评估器，记录基线 score、关键指标和归因材料。
Diagnose：解释弱点来自哪里，例如入场太早、离场太快、震荡中反复打脸、仓位过度集中、 regime 错配。
Propose：每轮只提一个有经济含义的假设，例如“放慢均线可以过滤噪声并持有趋势更久”，而不是“MA=17 分数最高”。
Patch：只修改策略文件。不要改评估器、数据源、成本模型或评分公式。
Evaluate：用同一评估器重跑，比较 score 和关键指标。
Replay：检查 golden case、实盘约束和已知失败场景没有退化。
Decide：通过严格门槛才接受，否则拒绝并回到 Diagnose。
Compress：删除无触发、负贡献、重复或解释不清的规则，保持策略小而可解释。

固定评估器与唯一可编辑程序

候选策略必须走同一条评估管线：

同一数据 → 同一回测引擎 → 同一成本模型 → 同一评分公式 → 一个 score

只有策略文件可以改。如果为了提分去改评估器，候选之间就不再可比，整个循环会变成自欺。

如果认证失败、数据缺口、引擎崩溃或缓存不可读，停止并报告阻塞。不要靠修改基线绕过问题。

Score 口径

本仓库示例采用 Sortino ratio（索提诺比率） 作为主 score：

score = Sortino

Sortino 只惩罚下行波动，比 Sharpe 更贴近“上行波动不是坏事、下行波动才是风险”的交易直觉。Sharpe、收益、回撤、胜率和交易笔数仍是验收门槛的一部分。

接受门槛

候选必须同时满足以下条件。右列是开箱即用的默认容忍带，在 run 开始前写入 run_config 即可，避免临场心证：

指标	默认门槛
score / Sortino	严格高于基线（硬门槛，不容忍）
总收益	≥ 基线 − 5%
年化收益	≥ 基线 − 5%
Sharpe	≥ 基线 − 5%
最大回撤	≤ 基线 + 2pp
胜率	≥ 基线 − 3pp
交易笔数	≥ 50（见下）

唯一需要你先确认的是交易笔数下限：它和回测区间长度、股票池大小强相关。默认给 50，覆盖多数全市场年级别回测；如果你的区间明显更短、股票池更小（笔数天然偏少），或反过来很大，按规模上调/下调后固定下来，不要直接套 50。其余几项的 5% / 2pp / 3pp 容忍带可直接沿用。

score 变高但关键指标塌掉，拒绝。一次幸运交易带来的高 Sortino，不等于策略真的变好。

反过拟合纪律

每个改动必须有经济含义

改动	经济解释	结论
均线从 5/10 放慢到 10/20	过滤日间噪声，持有趋势更久	可接受
增加价格高于 60 日均线的趋势过滤	避免下行趋势里逆势买入	可接受
某震荡指标死区 31-32	为什么偏偏是 31-32，没有市场解释	拒绝
止损从 10% 调到 8.2%	8.2% 太精确，像曲线拟合	拒绝

禁止连续变量上的窄坑过滤

不要在 RSI、量比、资金流、动量等连续变量上挖 1-2 个点宽的死区（下面用一个虚构的振荡指标 OSC 举例）：

python

# 过拟合：为什么是 43-44，而不是 42-43？
ENTRY_OSC_DEAD_ZONE_MIN = 43.0
ENTRY_OSC_DEAD_ZONE_MAX = 44.0

更稳健的变化应该是有经济含义的连续区间，或规则级开关：

python

# 可解释：OSC 40-50 表示一段有市场含义的“中性犹豫区”
ENTRY_OSC_DEAD_ZONE_MIN = 40.0
ENTRY_OSC_DEAD_ZONE_MAX = 50.0

禁止未来函数

入场信号只能使用已完成的 bar。
成交必须发生在下一根 bar 的开盘，或另一个预先固定的成交规则。
不要用同日未完成的 high / low / amplitude 过滤当日入场。

保证样本量

高 score 但只有 1-2 笔交易，通常是运气，不是稳健 edge。交易次数太少时，即使 score 更高，也不能直接接受。

训练 / 验证纪律

如果有股票池或时间切分：

训练集：可以用于搜索。
验证集：每轮都可以评估，但不能用来指导搜索方向；可以用验证退化来拒绝过拟合，不能为了最大化验证分数去调参。
最终 holdout：候选冻结后只跑一次。holdout 输给基线，不部署。

泛化健康度参考：

指标	健康	警告	拒绝
train score - validation score	< 0.5	0.5 ~ 1.0	> 1.0
train return / validation return	0.7 ~ 1.3	0.5 ~ 0.7 或 1.3 ~ 2.0	< 0.5 或 > 2.0

进入拒绝区的候选，即使训练集硬门槛通过，也视为过拟合。

改进泛化的做法

优先结构变化，而不是精调阈值：增加 regime filter 往往比把阈值从 7.2% 调到 7.8% 更可泛化。
每轮只动一个变量：否则失败无法归因，成功也难复现。
接受后压缩：删掉不触发、重叠、解释不清的规则。
回放 golden case：真实失败场景要固定成回归样例，防止实盘约束退化。
不要追最高分：停在多指标都变好且交易笔数健康的候选，而不是追 1-2 笔交易堆出来的最高 score。

示例流程

bash

# 1. Probe：跑基线
python backtest.py
# score 0.7545, return +5.46%, Sharpe 0.698, Sortino 0.755, drawdown 7.10%, 12 trades

# 2. Diagnose
# 5/10 均线太灵敏，震荡中频繁翻转，只吃到同期指数涨幅的一小段。

# 3. Propose
# 放慢到 10/20：过滤噪声，持有趋势更久。这是灵敏度的连续调整，不是窄坑。

# 4. Patch
# 修改 strategy.py：SHORT_WINDOW=10, LONG_WINDOW=20

# 5. Evaluate
python backtest.py
# score 2.0615, return +17.33%, Sharpe 1.839, Sortino 2.062, drawdown 6.71%, 7 trades

# 6. Decide
# score 严格提高，关键指标不退化，交易笔数仍可接受 → ACCEPT

# 7. Compress
# 没有冗余规则，策略保持最小。

常见错误

错误	修正
为了提分修改评估器	只改策略文件
在连续变量上加窄死区	使用有经济含义的连续区间或规则开关
只看 score 接受候选	score 是主指标，但关键指标也要过门槛
用验证集调参	验证集只用于检查泛化，不用于指导搜索
高 score 但只有 1-2 笔交易	要求足够样本量
入场信号使用未来信息	只用已完成 bar
不断叠规则不压缩	接受后删除无效和重叠规则
一轮改多个变量	每轮一个假设，保证归因清楚
忽略 train / validation 分化	分化过大即拒绝

Files

SKILL.md and 1 other file (references) in skills/hl-quant of toddwyl/hl-quant.

SKILL.md
references/framework.md

Open the folder on GitHubat commit 0b9835d

Compare with similar skills

Hl Quant 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.

Hl Quant compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Hl Quant this skilltoddwyl/hl-quant	156	—	~1.1k	Automated safety check: Pass	MIT	3 mo ago
MCP Server Builderanthropics/skills	180k	63 repos	~2.3k	Automated safety check: Pass	Apache-2.0	yesterday
PDF Processinganthropics/skills	180k	47 repos	~2k	Automated safety check: Pass	Proprietary	yesterday
NotebookLM Research AssistantPleasePrompto/notebooklm-skill	7.8k	14 repos	~2.4k	Automated safety check: Notes	MIT	1 mo ago
Manim Video Productionbrowser-use/video-use	29k	6 repos	~3k	Automated safety check: Pass	MIT	2 days ago
PPT Masterhugohe3/ppt-master	59k	1 repos	~2.5k	Automated safety check: Pass	MIT	3 days ago

Similar skills

MCP Server Builder
anthropics/skills
Official
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
180k GitHub starsUsed in 63 repos~2.3k tokens
Agent WorkflowsAuto-check passed
PDF Processing
anthropics/skills
Official
Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR.
180k GitHub starsUsed in 47 repos~2k tokens
Documents & OfficeAuto-check passed
NotebookLM Research Assistant
PleasePrompto/notebooklm-skill
Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources.
7.8k GitHub starsUsed in 14 repos~2.4k tokens
Knowledge ManagementAuto-check: notes
Manim Video Production
browser-use/video-use
Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.
29k GitHub starsUsed in 6 repos~3k tokens
Media & CreativeAuto-check passed
PPT Master
hugohe3/ppt-master
Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.
59k GitHub starsUsed in 1 repo~2.5k tokens
Documents & OfficeAuto-check passed
Scikit Learn
zLanqing/codex-claude-academic-skills
Machine learning in Python with scikit-learn. An agent skill from zLanqing/codex-claude-academic-skills.
4.7k GitHub starsUsed in 16 repos~3.9k tokens
Data & AnalyticsAuto-check passed

Works with

Python

Questions about Hl Quant

What does Hl Quant do?

How do I install Hl Quant in Claude Code?

Run `npx skills add toddwyl/hl-quant --skill hl-quant -a claude-code`. Or copy the skill folder (skills/hl-quant in toddwyl/hl-quant) into .claude/skills/hl-quant in your project. Claude Code loads it when a task matches its description.

How do I install Hl Quant in Codex?

Run `npx skills add toddwyl/hl-quant --skill hl-quant -a codex`. Or copy the skill folder (skills/hl-quant in toddwyl/hl-quant) into .agents/skills/hl-quant in your project. Codex loads it when a task matches its description.

Can I use Hl Quant 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 toddwyl/hl-quant --skill hl-quant -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hl-quant, .gemini/skills/hl-quant, .github/skills/hl-quant and .opencode/skills/hl-quant in your project.

What does Hl Quant need to run?

Going by SKILL.md and its folder, Hl Quant needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Hl Quant 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 Hl Quant 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. Review the folder before installing.

What licence does Hl Quant use?

Hl Quant 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 Hl Quant use?

About 1.1k tokens (SKILL.md is roughly 4.3k 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 2.1k tokens, read only when the agent opens those files.

What are the alternatives to Hl Quant?

Skills that share tags, products or a category with Hl Quant: MCP Server Builder (anthropics/skills, 180k stars), PDF Processing (anthropics/skills, 180k stars), NotebookLM Research Assistant (PleasePrompto/notebooklm-skill, 7.8k stars) and Manim Video Production (browser-use/video-use, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hl Quant?

toddwyl (a GitHub user) maintains it in toddwyl/hl-quant, which has 156 GitHub stars. The repository was last updated on June 22, 2026.

Source: toddwyl/hl-quant on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Hl Quant

Facts

At a glance

What it does

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

hl-quant：量化策略的启发式探索 Skill

什么时候使用

什么时候不要用

核心循环

固定评估器与唯一可编辑程序

Score 口径

接受门槛

反过拟合纪律

每个改动必须有经济含义

禁止连续变量上的窄坑过滤

禁止未来函数

保证样本量

训练 / 验证纪律

改进泛化的做法

示例流程

常见错误

Files

Compare with similar skills

Similar skills

MCP Server Builder

PDF Processing

NotebookLM Research Assistant

Manim Video Production

PPT Master

Scikit Learn

Related

Questions about Hl Quant