CtrlK
BlogDocsLog inGet started
Tessl Logo

contracts-mev-sandwich

MEV sandwich attacks — front-run + back-run a victim swap on Uniswap V2/V3, Curve, Balancer; mempool monitoring via Flashbots / private RPC, slippage tolerance exploitation, JIT liquidity sandwich, multi-block MEV.

63

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/contracts/mev-sandwich/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

76%Weight 40%Scale 1-5

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

The content is concise, specific, and well-structured with genuinely executable Flashbots code, but the core sandwich Solidity is outline-only and the destructive multi-step bundle workflow lacks explicit validation/simulation checkpoints. Adding a simulate-then-submit verification step and a runnable contract example would raise both weak dimensions.

Suggestions

Add an explicit validation checkpoint before submission, e.g. 'Simulate the signed bundle via fb.simulate() or eth_call to confirm profitability and inclusion order before sending,' with a fix/retry loop.

Replace the comment-only Solidity sandwich bundle with an executable contract snippet (or a concrete function signature + entry point) so the core mechanic is copy-paste ready, not just the JS relay glue.

Flesh out the mempool filter code (a concrete decode of swap calldata and the slippage-vs-gas-cost check) instead of leaving it as a comment hint.

DimensionReasoningScore

Conciseness

The body is lean and code-forward, assuming Claude's competence without explaining basic DEX/MEV concepts; nearly every line (sections on JIT, multi-block, defenses, pitfalls, OPSEC) earns its place.

5 / 5

Actionability

Provides mostly executable guidance (web3 mempool streaming, a near copy-paste Flashbots bundle in JS), but the core sandwich construction is comment/outline-only Solidity and the Python mempool filter is an incomplete sketch, leaving minor gaps.

4 / 5

Workflow Clarity

The detect-construct-submit sequence is present as headed sections, but this destructive/financial operation lacks explicit validation checkpoints (e.g. simulate bundle profitability, verify bundle inclusion) and a feedback loop, which caps workflow_clarity at 3 per the rubric.

3 / 5

Progressive Disclosure

A single self-contained SKILL.md (~100 lines) with clearly headed, well-organized sections and one-level external references; good structure with no nesting, though the overview/recipe/ethics mix could be split for a cleaner overview.

4 / 5

Total

16

/

20

Passed

Description

75%Weight 40%Scale 1-5

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

The description is specific and distinctive with excellent keyword coverage for the MEV sandwich domain, but it lacks an explicit 'Use when...' trigger clause, capping its completeness. Adding a sentence stating when Claude should invoke the skill would lift it into the top band.

Suggestions

Append an explicit 'Use when...' clause naming the triggering scenarios (e.g. "Use when the user wants to execute or detect MEV sandwich attacks on Uniswap/Curve/Balancer, monitor the mempool for sandwichable swaps, or simulate sandwich profitability").

Add a couple of natural trigger synonyms users actually say, such as 'sandwich bot' and 'frontrun'/'backrun', to round out the keyword set.

Keep the concrete action list as-is; it is the strongest part of the description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (front-run + back-run, mempool monitoring via Flashbots/private RPC, slippage tolerance exploitation, JIT liquidity sandwich, multi-block MEV) across named DEXes (Uniswap V2/V3, Curve, Balancer), giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

The description gives a clear, detailed "what" but has no explicit "Use when..." / trigger guidance clause, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Includes strong natural terms a user would say ("MEV sandwich attacks", "front-run", "back-run", "slippage", "mempool", "Flashbots") with good synonym coverage, but a few common phrasings (e.g. "sandwich bot", "frontrun") are missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a highly specific niche (MEV sandwich attacks on named DEXes via Flashbots/private relays) with distinct trigger terms, creating minimal overlap risk with other skills.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
PurpleAILAB/Decepticon
Reviewed

Table of Contents

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.