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".
64
77%
Does it follow best practices?
Impact
—
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.
The description covers the 'what' and 'when' adequately and targets a distinct niche (blockchain data). Its main weakness is the vagueness of the actions described—'process query and analyze' is generic and doesn't convey specific capabilities. The trigger terms are well-chosen and natural.
Suggestions
Replace 'Process query and analyze' with more specific concrete actions, e.g., 'Decode transactions, inspect smart contract state, trace token transfers, and query block details'.
Add more trigger term variations such as 'wallet address', 'token balance', 'contract ABI', 'block explorer', or 'tx hash' to improve keyword coverage for common user queries.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (blockchain) and lists some data types (blocks, transactions, smart contracts), but the actions are vague—'process query and analyze' is generic. It doesn't list specific concrete actions like 'decode transaction logs', 'inspect contract ABIs', or 'trace token transfers'. | 2 / 3 |
Completeness | Explicitly answers both 'what' (process/analyze blockchain data including blocks, transactions, smart contracts) and 'when' (use when querying blockchain data, with explicit trigger phrases). The 'Use when...' and 'Trigger with...' clauses are present. | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases like 'explore blockchain', 'query transactions', 'check on-chain data', plus keywords like 'blocks', 'transactions', 'smart contracts', and 'blockchain data'. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Blockchain data analysis is a clear niche. The specific mention of blocks, transactions, smart contracts, and on-chain data makes it unlikely to conflict with other skills. The domain is well-defined and distinct. | 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 (especially in the Output and Error Handling sections) and a lack of explicit validation checkpoints in the workflow. The progressive disclosure is partially implemented with one reference file but the main body carries too much detail inline.
Suggestions
Move the detailed error handling table and output field descriptions to a separate reference file (e.g., references/errors.md and references/output-formats.md) to reduce the main SKILL.md length.
Add an explicit validation step early in the workflow, such as 'Run `python blockchain_explorer.py --version` to verify the CLI is installed and API key is configured correctly before proceeding.'
Trim the Examples section descriptions—Claude can infer what 'swapExactTokensForTokens' means and doesn't need explanations like 'Useful for whale watching or due diligence on a wallet.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably well-structured but includes some unnecessary verbosity—e.g., the Output section exhaustively lists every field in every output type, and the error handling table is quite extensive. Some descriptions could be tightened (e.g., the Examples section explains what each command does when the command itself is fairly self-explanatory to Claude). | 2 / 3 |
Actionability | The skill provides fully concrete, copy-paste-ready CLI commands with specific flags, real contract addresses (USDC), and clear expected outputs. Every instruction is a specific executable command rather than abstract guidance. | 3 / 3 |
Workflow Clarity | The instructions are a numbered list of independent commands rather than a coherent multi-step workflow with validation checkpoints. There's no explicit validation/verification step (e.g., confirming API key is working before proceeding, or verifying output correctness). The reference to 'the full four-step implementation workflow' in implementation.md suggests important workflow content is deferred but no bundle file is provided. | 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 structure. However, no bundle files are provided to verify this reference exists, and the main SKILL.md itself is quite long with detailed error tables and output descriptions that could be split into reference files. The Resources section with external links is helpful but the inline content is heavy. | 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
16dfbca
- 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.