analyzing-on-chain-data
Process perform on-chain analysis including whale tracking, token flows, and network activity. Use when performing crypto analysis. Trigger with phrases like "analyze crypto", "check blockchain", or "monitor market".
71
66%
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/on-chain-analytics/skills/analyzing-on-chain-data/SKILL.mdQuality
Discovery
67%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 basics with explicit 'what' and 'when' clauses, which is good for completeness. However, the capabilities listed are more like high-level categories than concrete actions, and the trigger terms could be broader to capture more natural user phrasings while also being more precise to avoid conflicts with adjacent skills like general market analysis or blockchain development.
Suggestions
Make capabilities more concrete by specifying exact actions, e.g., 'Track whale wallet movements, trace token transfer paths between addresses, analyze network transaction volume and gas fees'.
Expand and refine trigger terms to include more natural variations like 'whale alert', 'token transfers', 'wallet activity', 'on-chain data', 'DeFi flows' while narrowing overly broad terms like 'monitor market' to 'monitor crypto market activity'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (on-chain analysis) and lists some actions (whale tracking, token flows, network activity), but these are more like subcategories than concrete specific actions. It doesn't detail what specific operations are performed (e.g., 'track wallet addresses', 'visualize token transfer graphs'). | 2 / 3 |
Completeness | Explicitly answers both 'what' (on-chain analysis including whale tracking, token flows, network activity) and 'when' (Use when performing crypto analysis, with explicit trigger phrases). The 'when' clause and trigger phrases are clearly stated. | 3 / 3 |
Trigger Term Quality | Includes some relevant trigger phrases like 'analyze crypto', 'check blockchain', and 'monitor market', but misses many natural variations users might say such as 'whale alert', 'token transfers', 'on-chain data', 'wallet tracking', 'blockchain explorer', or specific chain names. | 2 / 3 |
Distinctiveness Conflict Risk | The 'monitor market' trigger is quite broad and could conflict with traditional financial market analysis skills. 'Analyze crypto' is somewhat distinct but 'check blockchain' could overlap with blockchain development skills. The on-chain analysis niche is reasonably specific but the trigger terms introduce overlap risk. | 2 / 3 |
Total | 9 / 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.
The skill provides highly actionable CLI commands with good examples and a thorough error handling table, making it practically useful. However, it suffers from a flat instruction structure lacking workflow sequencing and validation checkpoints, and the overview contains unnecessary audience-targeting language. The referenced implementation.md file is not provided in the bundle, leaving a gap in progressive disclosure.
Suggestions
Restructure the 10 flat instructions into sequenced workflows (e.g., 'Daily Overview', 'Protocol Deep Dive') with explicit validation steps like checking output before proceeding to exports.
Remove the audience description ('Designed for DeFi researchers, protocol analysts, and yield farmers...') from the overview — Claude doesn't need to know who the skill is for.
Provide the referenced `implementation.md` bundle file or inline the four-step workflow if it's essential to using the skill correctly.
Move the error handling table and detailed output descriptions to a reference file to reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The overview section explains what DeFi researchers and yield farmers need, which is unnecessary context for Claude. The error handling table and output section are somewhat verbose but contain useful specifics. The skill could be tightened by removing the audience description and some redundant explanations. | 2 / 3 |
Actionability | Every instruction is a concrete, copy-paste-ready CLI command with specific flags and arguments. The examples section provides realistic multi-command workflows with clear explanations of what each produces. Error handling includes specific solutions for each error type. | 3 / 3 |
Workflow Clarity | The instructions are a flat list of 10 independent commands rather than a sequenced workflow with validation checkpoints. There's no feedback loop for verifying results or handling failures mid-workflow. The reference to a 'full four-step implementation workflow' in implementation.md suggests the actual workflow lives elsewhere, but no bundle file is provided to confirm. | 2 / 3 |
Progressive Disclosure | There's a reference to `${CLAUDE_SKILL_DIR}/references/implementation.md` for the full workflow, which is good progressive disclosure intent, but no bundle files are provided to verify this exists. The main file is quite long (~100 lines of content) with the error handling table and extensive output descriptions that 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.