mantle-tx-simulator
Use when a Mantle transaction needs pre-signing simulation evidence, state-diff review, revert analysis, or a WYSIWYS explanation before execution.
What this skill does
# Mantle Tx Simulator ## Overview Prepare simulation handoff packages for external backends and translate returned technical diffs into user-readable expected outcomes before signing or execution. ## Workflow 1. Normalize simulation request: - network - from/to/value/data - optional bundle/multicall context 2. Select an external simulation backend using `references/simulation-backends.md`. 3. Capture pre-state: - relevant token balances - allowance values - nonce and gas context 4. Produce an external simulation handoff package: - tx payload and network - required pre-state context - requested outputs (status/gas/logs/diffs) 5. After external execution evidence is provided, collect: - success/revert - gas estimate - logs/events - state diffs 6. Convert technical result into WYSIWYS summary with `references/wysiwys-template.md`. - **ALWAYS produce a WYSIWYS section**, even before external simulation results arrive. - If no external evidence exists yet, produce a **preliminary WYSIWYS** based on the request parameters, clearly labeled: "PRELIMINARY — not yet verified by simulation." - Pre-simulation WYSIWYS must still populate `what_user_gives`, `what_user_gets_min` (mark as "pending simulation"), and `plain_language_outcome`. 7. If simulation evidence is missing, fails, or confidence is low, return `do_not_execute`. - Set `do_not_execute_reason` with a specific explanation (e.g., "No external simulation evidence provided", "Simulation reverted", "Incomplete calldata"). - **Still produce the full Simulation Report output format** even when returning `do_not_execute`. ## Guardrails - This skill is read-only: it cannot execute transaction simulations directly. Use `mantle-cli` commands for any on-chain reads. Do NOT enable or connect to the MCP server. - Never broadcast real transactions from this skill. - Never claim a simulation has run unless external backend output is provided. - Distinguish simulated estimate from guaranteed execution result. - If token decimals/pricing context is incomplete, state uncertainty explicitly. - For bundle flows, describe each step and net effect. - If asked to run simulation via CLI tools, explain that `mantle-cli` has no tx simulation execution tool and provide external handoff instructions. - **Always output the full Simulation Report format** for every response, regardless of whether simulation evidence exists, the request is incomplete, or execution is declined. Never respond with only prose — always include the structured report. ## Output Format ```text Mantle Simulation Report - execution_mode: external_simulator_handoff - backend: - environment: - simulated_at_utc: <external timestamp if available> - status: pending_external_simulation | success | revert | inconclusive - simulation_artifact: <external link/id if available> State Diff Summary - assets_debited: - assets_credited: - approvals_changed: - contract_state_changes: Execution Estimates (simulated — not guaranteed) - gas_estimate: - estimated_fee_native: - slippage_or_price_impact_note: WYSIWYS - plain_language_outcome: - what_user_gives: - what_user_gets_min: - do_not_execute_reason: <empty if safe> - disclaimer: Simulation results are estimates only and do not guarantee on-chain execution outcomes. ``` ## References - `references/simulation-backends.md` - `references/wysiwys-template.md`
Related in Code Review
gstack
IncludedFast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)
startup-due-diligence
IncludedLegal due diligence review for seed-stage and Series A startups (US, Delaware C-Corp focus). Supports both investor and founder perspectives. Capabilities include: (1) Interactive document review and issue spotting; (2) Document request list generation; (3) Cap table and SAFE/convertible note analysis; (4) Red flag identification with severity ratings; (5) Diligence report generation. TRIGGERS: due diligence, DD, startup investment, cap table review, Series A, seed round, investor diligence, legal review startup, SAFE analysis, convertible note, 409A, founder vesting.
interview-master
IncludedThis skill should be used when the user asks to "generate interview questions", "prepare for interview", "optimize resume", "conduct mock interview", "analyze git commits for resume", "generate resume from code", "review my resume", or mentions interview preparation, career assistance, or extracting project experience from git history. Provides comprehensive interview and career development guidance for both job seekers and interviewers.
fix-issue
IncludedFixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to avoid recurrence. Use when debugging errors, resolving regressions, fixing bugs, or triaging issues.
sf-apex
IncludedGenerates and reviews Salesforce Apex code with 150-point scoring. TRIGGER when: user writes, reviews, or fixes Apex classes, triggers, test classes, batch/queueable/schedulable jobs, or touches .cls/.trigger files. DO NOT TRIGGER when: LWC JavaScript (use sf-lwc), Flow XML (use sf-flow), SOQL-only queries (use sf-soql), or non-Salesforce code.
swift-development
IncludedComprehensive Swift development for building, testing, and deploying iOS/macOS applications. Use when Claude needs to: (1) Build Swift packages or Xcode projects from command line, (2) Run tests with XCTest or Swift Testing framework, (3) Manage iOS simulators with simctl, (4) Handle code signing, provisioning profiles, and app distribution, (5) Format or lint Swift code with SwiftFormat/SwiftLint, (6) Work with Swift Package Manager (SPM), (7) Implement Swift 6 concurrency patterns (async/await, actors, Sendable), (8) Create SwiftUI views with MVVM architecture, (9) Set up Core Data or SwiftData persistence, or any other Swift/iOS/macOS development tasks.