fund-flow-analyst

Analyze Polygon EVM fund-flow patterns from seed addresses, tx hashes, and Dune log outputs. Use fixed registered Dune queries only.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "fund-flow-analyst" with this command: npx skills add leon5876/evm-analyst

Fund Flow Analyst

Use this skill when the user provides Polygon seed addresses, transaction hashes, decoded logs, raw polygon.logs rows, or Dune query results and asks for fund-flow reconstruction, pattern annotation, or accounting classification.

Hard rules

  1. Use only registered Dune queries in references/dune_query_registry.md. Do not invent query IDs or URLs.
  2. Do not fabricate amounts, addresses, relationships, labels, or transaction counts.
  3. Do not hard-exclude a transaction merely because it contains a known pattern. Exclude only when all material logs are explained.
  4. Same address appears once in addresses; pattern differences belong in flow_edges and log_annotations.
  5. flow_edges contains only transfer-class events, including mint/burn. Swap, Sync, Approval, and custom events stay in log_annotations unless they directly transfer value.
  6. One transaction may match multiple patterns.
  7. Separate external_capital_inflow from protocol_token_recycle.
  8. If data is insufficient, output next_query_plan instead of guessing.
  9. For topic0 decoding, use references/topic0_dictionary.md when available. Unknown topic0 should be marked unknown_event_signature.
  10. Preserve raw evidence: include sample tx hash, log index, contract address, topic0, token address, and decoded from/to/amount where available.

Required output

Keep results concise and structured. Prefer these tables when relevant:

  • addresses: address, role_guess, evidence, confidence
  • patterns: pattern_id, pattern_name, description, confidence
  • pattern_steps: pattern_id, step_no, event_type, contract_address, topic0, meaning
  • flow_edges: tx_hash, log_index, from_address, to_address, token_contract, amount_raw, amount_normalized, edge_type
  • log_annotations: tx_hash, log_index, contract_address, topic0, decoded_signature, interpretation
  • tx_classification: tx_hash, classification, reason, unresolved_items
  • accounting_summary: bucket, token_contract, gross_in, gross_out, net, notes
  • discovered_addresses: address, first_seen_tx, reason_to_follow
  • next_query_plan: query_code, purpose, parameters_needed

Do not output prose-only analysis.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

Data Classification

用于数据分类、数据分级、数据分类分级任务。用户要求对单一数据字段名、字段列表、数据库表 SQL/DDL 文件进行数据分类、数据分级或数据分类分级时使用;支持普通数据分类分级、GB/T 43697-2024 通用数据分类分级、金融数据分类分级、JR/T 0197-2020 金融数据安全级别,以及“通用数据标签 +...

Registry SourceRecently Updated
General

Flight Disruption Compensation Kit

Guides air passengers through documenting flight disruptions, checking compensation and duty-of-care eligibility under major regulatory frameworks, and prepa...

Registry SourceRecently Updated
General

Job Offer Evaluation Kit

Compare job offers with structured compensation, benefits, risk, career-fit, and life-fit frameworks. Provides comparison tools only; no financial, tax, lega...

Registry SourceRecently Updated
General

Medical Bill Review Kit

Organizes medical bills and EOBs into a reviewable inventory, provides an error-spotting checklist for common billing mistakes, and prepares structured commu...

Registry SourceRecently Updated