exploring-blockchain-data
Process query and analyze blockchain data including blocks, transactions, and smart contracts. Use when querying blockchain data and transactions. Trigger with phrases like "explore blockchain", "query transactions", or "check on-chain data".
80
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/crypto/blockchain-explorer-cli/skills/exploring-blockchain-data/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description that clearly identifies its domain and provides explicit trigger guidance with natural user phrases. Its main weakness is that the capability actions ('process', 'analyze') are somewhat generic rather than listing specific concrete operations. The inclusion of both 'Use when' and 'Trigger with phrases like' clauses is a strength for completeness.
Suggestions
Replace generic verbs like 'process' and 'analyze' with more specific actions such as 'decode transaction logs', 'inspect smart contract state', 'trace token transfers', or 'retrieve block details' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (blockchain) and some actions (process query, analyze), and mentions specific data types (blocks, transactions, smart contracts), but the actions themselves are somewhat generic ('process', 'analyze') rather than listing concrete operations like 'decode transaction logs', 'inspect contract state', or 'trace token transfers'. | 2 / 3 |
Completeness | Clearly answers both 'what' (process query and analyze blockchain data including blocks, transactions, and smart contracts) and 'when' (explicit 'Use when' clause and 'Trigger with phrases like' clause providing concrete trigger guidance). | 3 / 3 |
Trigger Term Quality | Includes good natural trigger terms: 'explore blockchain', 'query transactions', 'check on-chain data', 'blocks', 'transactions', 'smart contracts', 'blockchain data'. These cover terms users would naturally say when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Blockchain data querying is a clear niche with distinct triggers like 'on-chain data', 'blockchain', 'transactions', and 'smart contracts'. Unlikely to conflict with other skills unless there are multiple blockchain-related skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with concrete CLI commands, real-world examples, and comprehensive error handling. Its main weaknesses are moderate verbosity (the Output section, Resources descriptions, and some example prose could be trimmed) and a lack of structured workflow with validation checkpoints—the instructions read more like a feature catalog than a guided process. The single external reference to implementation.md is appropriate but unverifiable without bundle files.
Suggestions
Restructure the numbered instructions into task-oriented workflows (e.g., 'Investigating a Transaction', 'Analyzing a Wallet') with explicit validation steps like verifying the API key works before running queries.
Trim the Output section significantly—Claude can infer what CLI output looks like from the command descriptions and examples. A brief note about supported formats (table, JSON, CSV) would suffice.
Move the detailed error handling table to a separate reference file (e.g., `references/troubleshooting.md`) and keep only the 2-3 most common errors inline.
Remove or significantly shorten the Resources section—Claude already knows about Etherscan, web3.py, and major RPC providers. A simple list of links without descriptions would be more token-efficient.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably well-structured but includes some unnecessary verbosity—e.g., the Resources section with descriptions of well-known services, overly detailed error handling table entries, and explanatory prose after examples that Claude could infer. The Output section is also quite detailed for what amounts to describing CLI output formats. | 2 / 3 |
Actionability | The instructions provide specific, executable CLI commands with concrete flags and arguments. Examples include real contract addresses (USDC), real wallet addresses (vitalik.eth), and exact command-line invocations with expected outputs described. The error handling table maps specific error messages to concrete solutions. | 3 / 3 |
Workflow Clarity | The instructions are presented as a numbered list of independent commands rather than a coherent multi-step workflow. There are no explicit validation checkpoints or feedback loops—for instance, no step to verify the API key is working before proceeding, no retry logic guidance embedded in the workflow, and the cross-chain fallback pattern is only shown in examples rather than as a structured decision flow. | 2 / 3 |
Progressive Disclosure | There is a reference to `${CLAUDE_SKILL_DIR}/references/implementation.md` for the full implementation workflow, which is good progressive disclosure. However, no bundle files are provided to verify this reference exists, the main SKILL.md is quite long (~100+ lines of detailed content), and sections like the comprehensive error handling table and detailed Output section could potentially be split into reference files. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
3a2d27d
- 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.