72 added, 27 removed. Audit A to A.
# Algo-Trading-Skills — Extended Documentation for LLM Context Windows
## Overview
- Algo-Trading-Skills is an open-source engineering library of 504 algorithmic trading playbooks designed specifically for AI coding agents (Claude Code, GitHub Copilot, Cursor, Windsurf, Cline, Gemini CLI, OpenAI Codex CLI, Aider, Continue, Devin, OpenHands).
+ Algo-Trading-Skills is an open-source engineering library of algorithmic trading playbooks
+ in the agentskills.io format, written for AI coding agents (Claude Code, GitHub Copilot,
+ Cursor, Windsurf, Cline, Gemini CLI, OpenAI Codex CLI, Aider, Continue).
## Architectural Design Pattern
Each skill follows progressive disclosure:
- 1. YAML Frontmatter (~30-50 tokens): Fast indexing and relevance matching without loading complete files.
- 2. SKILL.md Body (500-1500 tokens): Structured sections (`When to Use`, `Prerequisites`, `Workflow`, `Common Pitfalls`, `Verification`, `Related Skills`).
- 3. `references/`: Detailed regulatory specifications, exchange API specs, and sequence diagrams.
- 4. `scripts/`: Production-tested Python helper scripts with matching `test_*.py` unit test suites.
- 5. `assets/`: Printable sign-off checklists (`checklist.md`).
+ 1. Frontmatter (name + description, ~100 tokens): what the skill does and when to trigger
+ it. This is all an agent reads while deciding which skill applies.
+ 2. SKILL.md body (~2,000-3,700 tokens): `When to Use`, `When NOT to Use`, `Prerequisites`,
+ `Workflow`, `Common Pitfalls`, `Verification`, `Related Skills`.
+ 3. `references/`: standards.md (regulatory and vendor specifications with sources) and
+ workflows.md (full technical procedure).
+ 4. `scripts/`: a standalone Python helper module plus its `test_*.py` unittest suite.
+ 5. `assets/checklist.md`: sign-off checklist derived from the Verification section.
- ## Full Domain Breakdown (16 Domains)
- 1. broker-integration (20 skills)
- 2. real-time-architecture (30 skills)
- 3. backtesting-methodology (35 skills)
- 4. financial-ml (38 skills)
- 5. risk-management (39 skills)
- 6. deployment-ops (30 skills)
- 7. global-market-integration (44 skills)
- 8. regulatory-compliance-global (38 skills)
- 9. multi-asset-derivatives (28 skills)
- 10. execution-algorithms (33 skills)
- 11. data-management-global (37 skills)
- 12. crypto-custody-security (29 skills)
- 13. portfolio-multi-strategy (30 skills)
- 14. market-microstructure-latency (24 skills)
- 15. quant-research-alt-data (20 skills)
- 16. tax-accounting-reporting-global (16 skills)
+ ## Frontmatter contract
+ The agentskills.io specification allows six top-level fields (`name`, `description`,
+ `license`, `compatibility`, `allowed-tools`, `metadata`), so this repository's own fields
+ live under `metadata:` as string values:
+ ```yaml
+ ---
+ name: order-placement-idempotency
+ description: >-
+ Use whenever a bot places, modifies, or cancels live orders and must guarantee it
+ never double-executes an order due to retries, timeouts, or reconnects
+ license: Apache-2.0
+ metadata:
+ domain: algorithmic-trading
+ subdomain: broker-integration
+ tags: broker-integration, idempotency, client-order-id, order-ledger, retry-safety
+ brokers_frameworks: Fyers API v3; Zerodha Kite Connect; Upstox API v2; IBKR API
+ version: "2.0.0"
+ author: algo-trading-skills-contributors
+ ---
+ ```
+
+ Every description starts with "Use when …" and fits in 280 characters, because an agent
+ selects a skill from its description alone and every installed skill's description is
+ loaded into context at session start.
+
+ ## Domain Breakdown (16 domains)
+ Exact per-domain counts are in `index.json` under the `subdomains` key, and every skill is
+ listed by domain in `docs/ROADMAP_500.md`:
+
+ 1. broker-integration — headless auth, token lifecycle, order idempotency, rate limits
+ 2. real-time-architecture — tick pipelines, buffering, backpressure, WebSocket recovery
+ 3. backtesting-methodology — lookahead bias, walk-forward, slippage realism, tearsheets
+ 4. financial-ml — leakage-free features, labeling, drift and staleness, serving
+ 5. risk-management — kill switches, exposure limits, VaR, stress tests, risk governance
+ 6. deployment-ops — supervision, promotion gates, canary/blue-green, secrets, incidents
+ 7. global-market-integration — venue APIs worldwide, crypto exchanges, FX
+ 8. regulatory-compliance-global — SEC, FINRA, MiFID II, FCA, ASIC, MAS, SEBI, IIROC, SFC, JFSA
+ 9. multi-asset-derivatives — SPAN margin, rolls, Greeks, funding, exotics
+ 10. execution-algorithms — TWAP/VWAP/POV, implementation shortfall, routing, auctions, TCA
+ 11. data-management-global — calendars, time zones, clocks, symbology, corporate actions
+ 12. crypto-custody-security — wallet split, whitelists, multi-sig, MPC, HSM, key backup
+ 13. portfolio-multi-strategy — correlation, allocation, lifecycle, attribution, reporting
+ 14. market-microstructure-latency — colocation, clocks, tick-to-trade, book signals
+ 15. quant-research-alt-data — satellite, card data, sentiment, supply chain, search trends
+ 16. tax-accounting-reporting-global — wash sales, lots, 475/1256, crypto tax, 1099-B
+
+ ## Packaging
+ The Claude Code marketplace (`.claude-plugin/marketplace.json`) ships one plugin per
+ domain plus an all-skills plugin, generated by `tools/build_marketplace.py`. Installing a
+ single domain keeps the per-session context cost to a few thousand tokens.
+
## Platform Rule Files
+ - Claude Code: `CLAUDE.md` and `.claude-plugin/`
+ - OpenAI Codex / OpenHands: `AGENTS.md`
+ - Gemini CLI: `GEMINI.md`
+ - GitHub Copilot: `.github/copilot-instructions.md`
- Cursor: `.cursor/rules/algo-trading-skills.mdc`
- Cline / Roo Code: `.clinerules`
- Windsurf: `.windsurfrules`
- - GitHub Copilot: `.github/copilot-instructions.md`
- - Claude Code: `CLAUDE.md` and `.claude/config.json`
- - OpenAI Codex / OpenHands: `AGENTS.md`
- - Gemini CLI: `GEMINI.md`
- Continue: `.continue/rules/algo-trading-skills.md`
- Aider: `CONVENTIONS.md` and `.aider.conf.yml`
+
+ ## Verification
+ - `python tools/validate_skills.py` — frontmatter, sections, cross-references, packaging
+ - `skills-ref validate skills/<name>` — the agentskills.io reference validator
+ - `python tools/run_all_tests.py` — every skill's unittest suite, isolated per subprocess
+ - `python tools/build_index.py --check` / `build_marketplace.py --check` — generated files