ibkr
SolidQuery Interactive Brokers via the local `ibkr` CLI. Use when the user asks about their IBKR account, positions, P&L, market quotes, option chains (incl. per-leg open interest), official market calendars, local watchlist, daily price history, technical/relative-strength screens, running a market scan, sizing a planned trade by fixed-fractional risk, checking the market's stress lifecycle (S&P 500 breadth, SPX-canonical dealer zero-gamma with SPY context and 0DTE / 1-7 / term horizon split, the broad-market regime dashboard), checking portfolio-aware canary stress lifecycle, held-name market-event flags, reading daemon protection proposals, daemon opportunities, offline opportunity research diagnostics, or runtime settings/freeze state, or explicitly requests an order preview/status/history read. This skill is read/preview-first by default; explicit current-turn broker-write requests must use the gated CLI path and report a redacted execution artifact.
Install
Quality Score: 80/100
Skill Content
Details
- Author
- osauer
- Repository
- osauer/ibkr
- Created
- 2 months ago
- Last Updated
- 2 days ago
- Language
- Go
- License
- MIT
Integrates with
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
ibkr
Trade and research options on Interactive Brokers via a local CLI (chains, quotes, Greeks, single-leg and vertical orders). Use when the user asks about option chains, option quotes, or wants to place/cancel option orders on IBKR. Requires IB Gateway running locally. Paper account is the default; live needs --live.
ibkr-harness
Use repo-local IBKR MCP/CLI for account, market, rulebook, canary, proposal, opportunity, and order investigations while developing the trading harness. Read/preview first; explicit current-turn broker writes use only the gated CLI.
observe
Query and render the kit's control plane from an agent session. Use when asked about the fleet's runs, gate verdicts, conformance, spend/tokens/cache economics, the cognitive-debt score, replaying a recorded run, benchmark results, or building/refreshing the observability dashboard. Trigger phrases include "dashboard", "control plane", "how much did we spend", "token usage", "cache hit rate", "cognitive debt", "debt score", "replay run <rid>", "gate log for <rid>", "conformance", "fleet stats", "observability numbers". All surfaces are CLIs under lib/bench; agents should prefer the JSON verbs over parsing HTML.