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

Alpaca Broker Ops

ASecurity

Use when an AI agent must trade stocks/ETFs/crypto through the Alpaca API — paper-first connector setup, scheduled wakeup loops with file handoff, and financial guardrails. Triggers on \"Alpaca\", \"paper trading\", \"stock trader agent\", \"APCA_API_BASE_URL\", \"trading wakeups\", \"alpaca-broker\". Non-triggers: on-chain/crypto-wallet trading (use llm-trading-agent-security), prediction markets (use ito-trade-planner), generic backtesting without a broker. Outcome: a paper-first Alpaca ope...

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgorailstestingapisecurity

Works with

cliapi

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill alpaca-broker-ops --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Alpaca Broker Ops?

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

Security grade badge for Alpaca Broker Ops
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-alpaca-broker-ops/badge)](https://www.skillsdirectory.com/skills/majinmagros-alpaca-broker-ops)

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

Download Zip
Files
SKILL.md
---
name: alpaca-broker-ops
description: "Use when an AI agent must trade stocks/ETFs/crypto through the Alpaca API — paper-first connector setup, scheduled wakeup loops with file handoff, and financial guardrails. Triggers on \"Alpaca\", \"paper trading\", \"stock trader agent\", \"APCA_API_BASE_URL\", \"trading wakeups\", \"alpaca-broker\". Non-triggers: on-chain/crypto-wallet trading (use llm-trading-agent-security), prediction markets (use ito-trade-planner), generic backtesting without a broker. Outcome: a paper-first Alpaca operator with separate keys per environment, a wakeup schedule, file-based continuity, and hard spend/risk limits before any live order."
metadata:
  origin: ECC
---

# Alpaca Broker Ops

Operate Alpaca (stocks, ETFs, crypto) from an agent loop. The two non-negotiable
rules: **paper-first always**, and **live money only behind explicit approval
plus hard limits**.

## When To Activate

- The user wants an agent that trades, manages a portfolio, or runs a trading
  schedule via Alpaca.
- Paper-trading setup, Alpaca API keys, or paper-vs-live endpoint confusion.
- A 24/7 trading loop with wakeups, journals, and notifications.

## Connector (validated 2026-09-07)

Source: https://docs.alpaca.markets/us/docs/paper-trading

- Paper and live share the **same API spec**, different base URL and keys.
- Paper endpoint: `https://paper-api.alpaca.markets`
  via env `APCA_API_BASE_URL=https://paper-api.alpaca.markets`.
- Keys live in `.env` (never in chat, logs, or repo). Paper keys differ from
  live keys — generate fresh keys per paper account.
- Paper accounts start with a **$100k** default balance and can be re-created
  (dashboard → paper account number → Open New Paper Account).
- Paper is a **simulation**: fills follow real-time quotes but ignore market
  impact, slippage from latency, queue position, partial-fill randomness
  nuances, fees, and dividends. A strategy that works on paper is unproven live.
- Paper includes free IEX real-time data. Full Саудов feeds are paid tiers —
  verify the current plan/price on the Alpaca pricing page before quoting
  numbers (do not hardcode feed prices from videos).

## Paper-First Rule

1. Every new strategy runs on paper until it has a written track record
   (trades, fills, drawdowns) in the journal.
2. Promotion paper → live is a human approval gate, never automatic.
3. Live starts small, with daily loss limits and a kill switch (below).

## Wakeup Loop Pattern

Scheduled wakeups (example: pre-market news+watchlist, open, midday review,
afternoon manage, close-out, confirm+log) work because each wakeup is
**stateless** — continuity lives in files, not in context:

| File | Content |
|---|---|
| `strategy.md` | Rules, universe, position sizing, exit criteria |
| `progress.md` / handoff | What happened, open positions, next wakeup's job |
| `journal/` | Per-trade evidence: signal, fill, rationale |
| `.env` | `APCA_API_*` keys (never committed) |

- Keep all wakeups on the **same thread/project** to preserve file continuity;
  prefer local scheduled tasks when the cloud runner cannot pin the model or
  reasoning effort the strategy was validated on.
- Notifications (e.g. chat/DM digests at fixed times) follow the
  `approval-loop + morning-digest` pattern (G13): propose → human approves →
   execute. The loop never places live orders from a notification alone.

## Exemplo

```text
Setup: APCA_API_BASE_URL=https://paper-api.alpaca.markets (keys de paper no .env)
Wakeup open: lê strategy.md + progress.md → sinal: compra 10x AAPL a mercado
Ordem paper: client_order_id=day1-aapl-01 → fill simulado → journal/2026-09-13-aapl.md
Live: bloqueado — só com "aprovado live" humano + daily loss limit ativo
```

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
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 →