execution-model

Trade execution modeling (backtest only) — slippage formulas (linear / square-root impact), VWAP/TWAP execution logic, market-impact cost estimation, and execution-assumption configuration.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./agent/src/skills/execution-model/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced reference skill with executable code and clear workflows, held back by some conceptual padding and a monolithic single-file structure with no progressive disclosure.

Suggestions

Trim the 'Why Slippage Models Are Needed' preamble and VWAP/TWAP goal explanations; assume the reader knows these concepts and keep only the domain-specific reference data.

Split the per-market reference tables (slippage bps, impact coefficients, trading costs) into a references/ file and link to it from SKILL.md so the main body stays a concise overview.

Fix the illustrative SignalEngine.generate snippet (undefined `signals` and `_compute_signal`) or mark it explicitly as pseudocode so it is not mistaken for executable code.

Dimension	Reasoning	Score
Conciseness	Mostly efficient reference material (per-market bps tables, impact coefficients, cost tables, executable functions), but it opens with a 'Why Slippage Models Are Needed' rationale and explains VWAP/TWAP goals that a capable model already knows, so it could be tightened.	2 / 3
Actionability	It provides fully executable Python (fixed_slippage, linear_impact, sqrt_impact, delayed_execution), concrete config JSON, a model-selection decision tree, and copy-paste-ready reference tables.	3 / 3
Workflow Clarity	A clear selection decision tree (capital vs ADV), a numbered 3-step Analysis Framework with a worked example, and a sensitivity-analysis table serving as a verification checkpoint give an explicit, sequenced workflow.	3 / 3
Progressive Disclosure	The ~340-line body is a single monolithic file with all models, tables, and code inline; section organization is good, but detailed reference content that could be split out is not separated into bundle files, and no external references are signaled.	2 / 3
	Total	10 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-scoped description with strong trigger terms and low conflict risk, weakened only by the absence of an explicit "Use when..." usage clause.

Suggestions

Add an explicit 'Use when ...' clause naming concrete triggering situations, e.g. 'Use when modeling backtest fills, estimating transaction costs, or configuring execution assumptions for strategy backtests.'

Confirm scope trigger language so the 'when' is as explicit as the 'what' is now.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete capabilities — "slippage formulas (linear / square-root impact)", "VWAP/TWAP execution logic", "market-impact cost estimation", and "execution-assumption configuration" — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	It clearly states what the skill does, but lacks any "Use when..." clause or equivalent explicit trigger guidance; "backtest only" is a constraint, not usage trigger, so per the guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	It surfaces natural domain terms a quant user would actually say — backtest, slippage, VWAP, TWAP, market impact, execution assumptions — giving good coverage rather than generic jargon.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply scoped to backtest execution modeling with distinct triggers (slippage models, VWAP/TWAP, market impact), making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/execution-model/SKILL.md
Commit: 8643fcd

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.