Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Options Positioning

ASecurity

Dealer gamma exposure by strike, call and put walls, the gamma flip level, max pain, put-call ratios, and volatility smile geometry including at-the-money implied volatility, 25-delta risk reversal, butterfly, skew slope and the implied expected move. Use when the user asks where the walls are, whether dealers are long or short gamma, what the gamma flip level is, where max pain sits, what the put-call ratio is, how steep the skew is, what the market implies for a move, or asks about position...

3 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgo

Works with

climcp

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add Iman/agent-driven-options-desk-and-skills --skill options-positioning --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Options Positioning?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Options Positioning
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/iman-options-positioning-6feab9c3/badge)](https://www.skillsdirectory.com/skills/iman-options-positioning-6feab9c3)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: options-positioning
description: Dealer gamma exposure by strike, call and put walls, the gamma flip level, max pain, put-call ratios, and volatility smile geometry including at-the-money implied volatility, 25-delta risk reversal, butterfly, skew slope and the implied expected move. Use when the user asks where the walls are, whether dealers are long or short gamma, what the gamma flip level is, where max pain sits, what the put-call ratio is, how steep the skew is, what the market implies for a move, or asks about positioning and dealer hedging. This is chain-wide geometry rather than per-contract Greeks. Not for order placement and not for recommendations.
---

# Positioning and volatility geometry

One command over a whole chain, not a band around spot, because a wall
three hundred points away is exactly what a band would hide.

## Execution route

Prefer `option_chain_snapshot` to retrieve the whole chain and
`option_positioning` to analyse it. When the user asks to see positioning,
gamma, open-interest, volume, or volatility plots, call `option_plots`. The
tool returns PNG images in the conversation. Do not answer with a localhost
dashboard URL. If the user has attached a CSV or JSON chain, pass its path as
`source_path` for a local file. For remote chat, pass its content as
`source_data` or `source_text`. Do not ask for the same data again. If a
matching MCP tool is not available,
use the `optiondesk` commands below. If neither MCP nor the CLI is available,
say that no fresh positioning result can be produced; do not invent figures
or present example or remembered values as current.

## User-supplied data

Before you send data to the tool, ask the user to state that private analysis
is permitted. Then set `rights_confirmed` to true and name `data_source`.
The local desk does not gate on that name: any `data_source` is accepted,
so whether that provider's terms allow the analysis is the user's
responsibility (only the hosted service refuses Yahoo, yfinance and
personal Alpha Vantage data).

If the attachment fields are unclear, call `option_snapshot_schema`. Normalize
known column aliases, call or put notation, numeric commas, and clear percentage
units. Report the repairs from `normalization`. Never invent a missing spot,
expiry, strike, option type, quote, timestamp, or source. If a required value
is missing, ask only for that value.

The imported chain becomes a normal Option Desk artifact. Use its path for
positioning, plots, strategies, Greeks, and the local dashboard.

## Data boundary

Use fresh provider data only when the tool reports that access is allowed.
A local Yahoo adapter also requires the personal-use acknowledgement. A
hosted tool must use a provider that is approved for public display, derived
outputs, storage, and MCP delivery. Never bypass a provider refusal. When no
approved tool is available, analyse a snapshot that the user supplied and
had the right to share. Otherwise, state that current figures are unavailable.

## Run it

```
optiondesk chain SPY --expiry 2026-09-18
optiondesk chain SPY --from-file chain.csv --data-source "broker export" --accept-data-rights
optiondesk exposure
optiondesk plots SPY --expiry 2026-09-18
```

`exposure` takes `--snapshot PATH` and `--multiplier` (100 for US equity
options).

## What comes back

Exposure per strike split into calls and puts, the cumulative profile, the
call and put walls, the gamma flip level where the cumulative profile
crosses zero, max pain with its full payout profile, open interest and
volume ratios, and the smile: at-the-money implied volatility, the
25-delta risk reversal, the butterfly, a least-squares skew slope and the
one standard deviation expected move.

## The assumption you must state

Every sign rests on the convention that dealers are long calls and short
puts against the public. That convention is often wrong for a single name,
especially around events and in heavily retail-traded tickers, and the
walls move with it. The artifact carries the assumption in a field; quote
it whenever you quote a wall.

Positive net exposure is read as hedging that dampens moves, negative as
hedging that amplifies them. That is an interpretation, not a measurement.

Max pain describes where open interest sits. It is not a forecast of where
price goes, and the evidence that price gravitates to it is thin.

Contracts with no open interest recorded are excluded rather than counted
as zero, because an absent number is not a zero and treating it as one
moves every wall.

## Reporting rules

These hold for every number this skill produces.

Cite the artifact path when reporting from it. The artifact is the record;
prose is a summary of it, and a number quoted without its source cannot be
checked later.

Read `degraded` before quoting anything. When it is true, say so and give
`degraded_reason` first, in the same breath as the number rather than as a
footnote. Every command carries both fields in the summary it prints, not
only in the artifact.

Do not re-derive numbers yourself. If a figure is not in the artifact, say
it is not there rather than computing a replacement, and never substitute a
default for a value the pipeline refused to produce.

Premiums are model values or mid quotes from delayed third-party data. They
are not fills, and a real entry crosses the spread on every leg.

Never recommend a trade, an entry, an exit or a size. This is research
software and it is not investment advice. Present the analysis and let the
reader decide.
The full terms are in DISCLAIMER.md, which ships beside this skill when it
is installed from a package and sits at the repository root otherwise. The
substance is already above: research software, not advice, modelled numbers
that are not fills.


## What an audit found in these numbers, and what to say about it

The exposure figures reproduced to 3.5e-16 against an independently coded
gamma, and the units are dollars of dealer hedging notional per one percent
move at a multiplier of one hundred. Two things about presentation did not
survive the audit.

**The gamma flip is anchored at the lowest listed strike**, not at zero, so
on a chain whose ladder starts far below spot the reported level is an
artifact of where the listing begins rather than a market level. On one
live chain it read 306.82 against a spot of 765.68 and was the only
crossing. Treat it as a shape statement about the cumulative profile, and
say so rather than quoting it as a level.

**Max pain and the gamma profile use different populations.** Max pain
needs open interest and a strike; the gamma profile also needs a
volatility, so contracts without one are absent from it. Two numbers on one
panel, from two different subsets of the same chain. The artifact now
reports each skip reason separately, and an earlier version told the reader
that contracts had no open interest when in fact all of them did and the
missing thing was volatility.

## Going deeper

- `reference.md`: the exposure formula and its units, what the walls and the flip level are, why there is often more than one flip, and the limits of max pain and the smile metrics.
- `workflows/read-the-book.md`: the order to read the numbers in, what each is worth, and what never to say.

Attribution

ImanIman
View sourceMore from Iman →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →