execution-analysis
Skill13 starsChanged 5 days agoApache-2.0View on GitHub
Analyze order execution quality, schedule child orders, estimate slippage and market impact, and produce transaction-cost analysis for institutional or high-frequency execution. Use for implementation shortfall, VWAP/TWAP/POV, arrival-price, and venue-routing research.
In this repository19 other files it gives its agents.
- agent-based-market-simulationSkill
- code-understandingSkill
- etf-arbitrageSkill
- exchange-gateway-engineeringSkill
- hft-market-replaySkill
- interview-simulatorSkill
- lob-microstructureSkill
- low-latency-performanceSkill
- market-makingSkill
- mathematical-reasoningSkill
- order-book-reconstructionSkill
- pre-trade-risk-controlsSkill
- production-trading-operationsSkill
- quant-research-validationSkill
- queue-position-modelingSkill
- research-paper-tutorSkill
- socratic-tutorSkill
- tick-data-engineeringSkill
- volatility-market-makingSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 26
Never compare two algos on different order populations without controlling for selection and difficulty.
- Distinctive: line 27
Do not call VWAP outperformance “alpha” without a causal design.
- Distinctive: line 28
Avoid post-trade benchmark selection and survivorship of only completed orders.
- Distinctive: line 29
Do not infer permanent impact from a short markout alone.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Execution Strategy and Transaction-Cost Analysis
Act as an execution researcher. Choose benchmarks before looking at results. Distinguish trading alpha from execution quality, and distinguish realized costs from model forecasts.
Workflow
- Define the parent order. Specify instrument, side, target quantity, urgency, start/end window, constraints, participation cap, venue eligibility, and whether the objective is benchmark tracking, risk reduction, or completion probability.
- Choose the benchmark ex ante. Examples: arrival mid/price, decision price, interval VWAP, close, or implementation shortfall. Explain why the benchmark matches the economic objective. Do not select whichever benchmark makes the result look best.
- Build clean event records. Preserve parent/child IDs, decision and release times, venue, order type, price, quantity, fills, cancels, rejects, fees, and market context. Align trade/quote data and account for clock differences.
- Decompose implementation shortfall. For signed side
s(+1 buy, -1 sell), compute the signed price component consistently, e.g.s * (fill_price - decision_price) * filled_qty; add explicit opportunity cost for unfilled quantity and commissions/fees separately. State units and sign conventions. Avoid mixing arrival and decision benchmarks. - Measure market response. Compare arrival mid, execution price, interval VWAP, and post-trade markouts. Separate spread cost, temporary impact, permanent impact proxy, timing risk, and opportunity cost where identifiable.
- Compare execution schedules. Evaluate TWAP, VWAP, POV, urgency/shortfall schedules, and passive/aggressive mixes under identical parent orders and constraints. Use the same market data and child-order eligibility.
- Condition the analysis. Segment by order size/ADV, spread, volatility, time of day, liquidity, venue, urgency, side, and market regime. Report both aggregate and conditional outcomes.
- Assess capacity and robustness. Model participation impact and slippage nonlinearity. Test what happens when order size or urgency increases. Separate historical estimates from extrapolations.
Required metrics
Implementation shortfall (price and total), arrival slippage in bps, realized spread/markout, participation rate, completion rate, time-to-completion, fill ratio, market impact proxy, fees/rebates, and distribution tails. Report sample sizes and confidence intervals.
Guardrails
- Never compare two algos on different order populations without controlling for selection and difficulty.
- Do not call VWAP outperformance “alpha” without a causal design.
- Avoid post-trade benchmark selection and survivorship of only completed orders.
- Do not infer permanent impact from a short markout alone.
- Include unfilled quantity; excluding it biases results toward easy fills.
Deliverable
Provide the benchmark definition, sample and exclusions, metric formulas, matched comparison, segment analysis, uncertainty, capacity assumptions, and a concise execution recommendation.
Further reading
- Almgren & Chriss, Optimal Execution of Portfolio Transactions: https://doi.org/10.21314/JOR.2001.041
- Nasdaq OUCH order-entry overview: https://nasdaqtrader.com/Trader.aspx?id=OUCH
- NautilusTrader fill/matching concepts: https://nautilustrader.io/docs/latest/concepts/backtesting/fill-prices-and-matching/
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

