SkillAtlasSkill 详情

analyzing-options-flow

A model-agnostic agent-skills platform.

审核状态:已审核Quality 72Security 52

复制安装命令

用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。

复制前请先查看来源、License 和安全提示。

项目 README

来源文件:README.md

抓取于 2026年8月26日

Tons of Skills

A model-agnostic agent-skills platform. The canonical layer is harness-free by construction; Claude Code is currently the verified-native harness. Other harnesses remain engineering candidates until their native-path integration is verified; source research alone is never presented as public support.

Release CLI Plugins Skills GitHub Stars skills.sh Sponsor: Kobiton Buy me a monster

ko-fi

Install

Inside Claude Code, one command installs the whole marketplace:

/plugin marketplace add jeremylongshore/claude-code-plugins

Or use the CLI:

pnpm add -g @intentsolutionsio/ccpi
ccpi install devops-automation-pack

Browse the marketplace · Explore plugins · Download bundles

Killer Skill of the Week — no-ai-slop by Peter Yang

Strip AI slop from any draft — named-pattern edits that keep the writer's real voice

no-ai-slop does two jobs and refuses to fake a third. In Edit mode it makes the minimum effective edit — cutting throat-clearing, weak verbs, and abstract nouns while deliberately preserving the writer's cadence, bluntness, humor, and honest admissions, so a rough draft still sounds like the same person afterward. In Detect mode it names each AI-slop pattern it finds, quotes the offending line, and gives the fix in a few words — and pointedly does NOT score the draft or guess whether an AI wrote it. That restraint is the whole point: AI detectors guess; named patterns are evidence the reader can check. MIT-licensed, single focused skill, actively maintained by Peter Yang.

"AI detectors guess. Named patterns are evidence the user can check." — Peter Yang

Grade: A | Week of July 22, 2026 (W30) | View on GitHub

Previous picks: tonone, mnemos, databricks-pack, kobiton-automate, skyvern, code-cleanup, web-analytics, token-optimizer, executive-assistant-skills, skill-creator, cursor-pack, crypto-portfolio-tracker. See all at tonsofskills.com.

Scale, labeled

Every number below names the cohort it counts and the command that reproduces it — an unlabeled count is how a corpus ends up with five contradictory answers to "how many skills."

CountCohortReproduce with
442catalog plugins (catalog-entry cohort)node scripts/generate-readme-toc.mjs over marketplace.extended.json
3,067marketplace-visible skills (distinct)node -e "import('./scripts/corpus-resolver.mjs').then(m=>console.log(m.resolveCorpus('marketplace-visible').length))"
347agent definitions in pluginsgit ls-files 'plugins/**' | grep '/agents/.*\.md'
19plugin categoriesls -d plugins/*/

📦 Live npm Downloads

Across 396 published packages in the claude-code-plugins namespace. Updated daily by GitHub Actions.

WindowAll packagesEstablished (>30d)
Last 24 hours962962
Last 7 days2,9202,916
Last 30 days12,86812,779

"Established" excludes packages first published within the last 30 days, so a bulk-publish event doesn't dominate the headline.

Top 10 by last 30 days:

#PackageLast 30d
1@intentsolutionsio/openrouter-pack556
2@intentsolutionsio/groq-pack496
3@intentsolutionsio/databricks-pack274
4@intentsolutionsio/clickhouse-pack273
5@intentsolutionsio/wallet-security-auditor263
6@intentsolutionsio/notion-pack258
7@intentsolutionsio/elevenlabs-pack244
8@intentsolutionsio/freshie-inventory-manager214
9@intentsolutionsio/supabase-pack210
10@intentsolutionsio/agency-os204

Last refreshed 2026-08-19T03:03:05.709Z.

Ways in

Five real questions, five doors — each resolves to a live, generated surface, never a hand-maintained list:

Browse by category

The 19 categories below link into the live marketplace. Plugin counts are the catalog-entry cohort — regenerated from marketplace.extended.json by this generator; the catalog itself lives on tonsofskills.com, never in this file (§ 6A of the platform blueprint).

CategoryPlugins
🤖AI & Machine Learning36
🎭AI Agents & Agency10
🔌API Development26
💼Business Tools6
👥Community21
₿Crypto & Web327
💾Database26
🎨Design2
🔧DevOps & Infrastructure36
📚Examples & Templates5
🧩MCP Servers16
📦Packages5
⚡Performance25
✅Productivity30
🎁SaaS Skill Packs106
🔐Security27
✨Skill Enhancers9
🧪Testing28
📁Analytics1

What the classes mean

Four artifact classes live in this repository, distinguished on sight and never blurred — provenance is a truth requirement here, not a UX nicety:

ClassWhat it isHow the reader can tell
Canonical skillFirst-party, harness-free, the source of truthNo .source.json in its plugin directory
Generated adapterA thin, machine-produced harness projectionLives under a generated path with a "generated — do not edit" header
First-party packageAn Intent Solutions distribution (npm, cowork zip)@intentsolutionsio scope, IS-authored license
Upstream mirrorSomebody else's work, hosted mirror-by-default.source.json present — upstream author, license, and pinned commit recorded

Certification

Not yet certified. The certification program (tiers T0–T4 with retained, hash-matched evidence) is a later epic of the platform blueprint; until its report exists, no artifact on this surface claims a tier. This line is rendered from the absence of certification-report.json — honestly, not cosmetically.

Contribute

Start with the contribution guide, then the intake and review standards every submission passes through:

Governance

Provenance

External plugins are hosted mirror-by-default: the contributor's repository stays the source of truth, every mirrored source is pinned in a content lockfile, and upstream credit — author, license, resolved commit — is recorded in the mirror itself. Improvements flow by upstreaming to the author's repository, never by silently editing the mirror. The full decision record is the external-sync model.

License

MIT for the repository scaffolding and first-party tooling; each plugin carries its own license in its manifest, and mirrored plugins keep their upstream license verbatim.

其他

高风险

  • 来源需自行核对维护者身份。
  • 包含脚本或命令调用,安装前请复核。
  • 可能需要外部 token、网络权限或第三方服务。
  • 存在潜在风险命令,请谨慎安装。
  • 扫描发现:4 条。

Codex — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/analyzing-options-flow" 文件夹复制到 Codex 的 skills 目录中。
  4. 重启 Codex 让新的 skill 生效。

Codex — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Codex 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Codex 让新的 skill 生效。

Claude Code — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/analyzing-options-flow" 文件夹复制到 Claude Code 的 skills 目录中。
  4. 重启 Claude Code 让新的 skill 生效。

Claude Code — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Claude Code 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Claude Code 让新的 skill 生效。

Cursor — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/analyzing-options-flow" 文件夹复制到 Cursor 的 skills 目录中。
  4. 重启 Cursor 让新的 skill 生效。

Cursor — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Cursor 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Cursor 让新的 skill 生效。

GitHub Copilot — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/analyzing-options-flow" 文件夹复制到 GitHub Copilot 的 skills 目录中。
  4. 重启 GitHub Copilot 让新的 skill 生效。

GitHub Copilot — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 GitHub Copilot 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 GitHub Copilot 让新的 skill 生效。

Windsurf — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/analyzing-options-flow" 文件夹复制到 Windsurf 的 skills 目录中。
  4. 重启 Windsurf 让新的 skill 生效。

Windsurf — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Windsurf 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Windsurf 让新的 skill 生效。
查看 SKILL.md 原文
name: analyzing-options-flow
description: 'Track crypto options flow to identify institutional positioning and
  market sentiment.

  Use when tracking institutional options flow.

  Trigger with phrases like "track options flow", "analyze derivatives", or "check
  institutional".

  '
allowed-tools: Read, Write, Edit, Grep, Glob, Bash(crypto:options-*)
version: 1.29.0
author: Jeremy Longshore <jeremy@intentsolutions.io>
license: MIT
tags:
- crypto
- analyzing-options
compatibility: Designed for Claude Code

Analyzing Options Flow

Overview

Track and analyze crypto options flow on centralized derivatives exchanges (Deribit, OKX, Bybit) to identify institutional positioning, gauge market sentiment, and detect unusual activity in BTC and ETH options markets.

Prerequisites

  • API credentials for at least one crypto derivatives exchange (Deribit API key recommended; OKX or Bybit as alternatives)
  • Python 3.8+ with requests and websocket-client libraries installed
  • Optional: pandas and numpy for advanced statistical analysis of flow data
  • Understanding of options terminology: strike price, expiry, implied volatility, delta, gamma, open interest, and premium
  • Network access to exchange WebSocket feeds for real-time flow monitoring

Instructions

  1. Load exchange API credentials from ${CLAUDE_SKILL_DIR}/config/crypto-apis.env using the Read tool to authenticate against derivatives exchange endpoints.
  2. Run Bash(crypto:options-*) to connect to the Deribit options data feed and pull the current options chain for BTC or ETH, including all active strikes and expiries.
  3. Retrieve open interest data across all strike prices and expiration dates to build an open interest heatmap showing where positions are concentrated.
  4. Calculate the aggregate put/call ratio by volume and by open interest to assess overall market sentiment (ratio above 1.0 indicates bearish bias; below 1.0 indicates bullish).
  5. Filter for block trades exceeding a configurable notional threshold (e.g., $500K+) to isolate institutional-sized activity from retail noise.
  6. Analyze the implied volatility term structure across expiry dates to detect vol compression (potential breakout ahead) or vol expansion (uncertainty increasing).
  7. Track max pain levels for upcoming expiries by computing the strike price at which the most options expire worthless, indicating likely price magnetism near expiry.
  8. Compare recent flow data against historical baselines (7-day and 30-day rolling averages) to flag statistically unusual positioning.
  9. Generate a flow summary report with actionable signals: bullish large-block calls, bearish put sweeps, IV skew shifts, and OI buildup at key strikes.
  10. Export results using --format json or --format csv for integration with trading dashboards or alerting systems.

See ${CLAUDE_SKILL_DIR}/references/implementation.md for the full implementation workflow.

Output

  • Options chain tables showing strike, expiry, bid/ask, IV, delta, gamma, open interest, and volume for each contract
  • Put/call ratio summary (by volume and open interest) with historical comparison
  • Block trade log listing timestamp, direction (buy/sell), strike, expiry, size, premium, and implied volatility
  • Open interest heatmap data mapping strike prices against expiration dates with position concentration
  • Max pain calculation per expiry date with the optimal pain strike and dollar value at risk
  • Implied volatility term structure curves across near-term and far-term expiries
  • Unusual activity alerts flagging trades exceeding 2 standard deviations from the rolling average
  • JSON or CSV export files for downstream analysis and dashboard integration

Error Handling

ErrorCauseSolution
API Rate Limit ExceededToo many requests to the derivatives exchange APIImplement request throttling with 100ms minimum between calls; use WebSocket feeds for real-time data instead of polling REST endpoints; upgrade API tier if needed
Cannot connect to blockchain node or timeoutRPC endpoint unreachable when resolving on-chain settlement dataSwitch to a backup RPC endpoint; verify network connectivity; confirm the node is fully synced
Invalid API key or signature mismatchExchange API authentication failureRegenerate API keys on the exchange; verify key permissions include read access to derivatives data; check system clock synchronization (HMAC signatures require accurate timestamps)
No options data for instrumentQueried an expired or non-existent options contractVerify the instrument name matches exchange conventions (e.g., BTC-28MAR25-100000-C on Deribit); check that the expiry has not already passed
WebSocket connection droppedExchange feed disconnection due to inactivity or network issueImplement automatic reconnection with exponential backoff; send periodic ping frames to maintain the connection
Insufficient historical dataBaseline period too short for statistical comparisonExtend the rolling window from 7 days to 30 days; ensure the data collection pipeline has been running long enough to accumulate history

Examples

BTC Options Sentiment Snapshot

# Pull current BTC options chain and compute put/call ratios
python options_flow.py btc --summary

Returns the aggregate put/call ratio, top 5 strikes by open interest, max pain for the nearest expiry, and the current implied volatility at-the-money. A put/call ratio of 0.65 with heavy call OI at the $120K strike suggests bullish institutional positioning.

Detect Institutional Block Trades

# Filter for block trades above $1M notional in the last 24 hours
python options_flow.py btc --blocks --min-notional 1000000 --period 24h  # 1000000 = 1M limit

Lists all block trades exceeding the threshold with direction inference (aggressor side), strike, expiry, premium paid, and IV at execution. Useful for spotting large directional bets before they move the underlying.

ETH Implied Volatility Term Structure

# Generate IV term structure for ETH across all active expiries
python options_flow.py eth --iv-curve --format json > eth_iv_term.json

Exports the IV term structure as JSON. Flat or inverted term structures (near-term IV higher than far-term) often precede sharp directional moves, while steep upward-sloping curves indicate calm near-term expectations.

Resources

  • Deribit API Documentation -- primary exchange for crypto options data, WebSocket and REST endpoints
  • Laevitas Analytics -- crypto derivatives analytics dashboard with options flow visualization
  • Greeks.live -- real-time crypto options analytics and block trade tracking
  • Amberdata Derivatives -- institutional-grade crypto derivatives data API
  • The Block Research -- aggregated crypto options market data and charts

发现问题?提交给管理员复核

评分:

评论 (0)

暂无评论,成为第一个评论者吧!