tdg-personal/evm-token-decimals
Prevent silent decimal mismatch bugs across EVM chains. Covers runtime decimal lookup, chain-aware caching, bridged-token precision drift, and safe normalization for bots, dashboards, and DeFi tools.
72
72%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
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 is technically specific and carves out a clear niche around EVM token decimal handling, making it highly distinctive. However, it lacks an explicit 'Use when...' clause, which caps completeness, and the trigger terms lean heavily technical, potentially missing how users naturally describe their problems (e.g., 'wrong token amounts', 'precision issues').
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when dealing with token decimal mismatches, wrong transfer amounts, or precision errors across EVM-compatible chains.'
Include more natural user-facing trigger terms such as 'token decimals', 'ERC-20', 'wrong amount', 'precision error', 'Ethereum', 'Polygon', 'multichain' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'runtime decimal lookup', 'chain-aware caching', 'bridged-token precision drift', and 'safe normalization'. Also specifies concrete use cases: 'bots, dashboards, and DeFi tools'. | 3 / 3 |
Completeness | The 'what' is well-covered (prevent decimal mismatch bugs, runtime lookup, caching, normalization), but there is no explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the mention of 'bots, dashboards, and DeFi tools'. | 2 / 3 |
Trigger Term Quality | Includes relevant domain terms like 'EVM chains', 'decimal', 'bridged-token', 'DeFi', 'normalization', and 'bots', but misses common user-facing variations like 'token decimals', 'ERC-20', 'wrong amount', 'precision error', 'Ethereum', or 'smart contract'. The terms lean technical and may not match how users naturally phrase their problems. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: EVM chain decimal mismatch bugs with bridged-token precision drift is a very specific domain unlikely to conflict with other skills. The combination of EVM, decimals, and bridged tokens creates a clear, unique trigger profile. | 3 / 3 |
Total | 10 / 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 excellent multi-language code examples that are immediately executable. Its main weaknesses are the lack of a clear sequential workflow with validation checkpoints (especially around bridging scenarios) and some mild verbosity in the introductory sections. The bridged-token precision drift topic promised in the description is underserved.
Suggestions
Add an explicit workflow sequence for the bridging scenario: check decimals on source chain → bridge → re-query on destination chain → compare → alert if mismatch, with a validation checkpoint.
Trim the 'When to Use' and 'How It Works' sections — Claude doesn't need to be told what portfolio trackers or bots are; a single sentence framing the core invariant ('always query decimals() at runtime') suffices.
Consider adding a brief verification step or assertion pattern (e.g., assert decimals <= 18 or log anomalies) to catch unexpected values, which would strengthen workflow clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 'When to Use' section and introductory explanation add some unnecessary context that Claude could infer. The 'How It Works' summary is somewhat redundant given the examples that follow. However, the code examples themselves are lean and purposeful. | 2 / 3 |
Actionability | Every section provides fully executable, copy-paste ready code across Python, Solidity, TypeScript, and bash. The examples cover the core task (querying decimals), caching, error handling, normalization, and a quick CLI check — all concrete and complete. | 3 / 3 |
Workflow Clarity | The examples are presented as independent patterns rather than a sequenced workflow. There are no explicit validation checkpoints or feedback loops — for instance, no step to verify that cached decimals match on-chain values after bridge events, despite the skill mentioning bridged-token precision drift as a use case. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and distinct sections, but everything is inline in a single file. The bridged-token precision drift topic mentioned in the description is barely covered and could warrant a separate reference. For a skill of this length (~100 lines of content), it's borderline acceptable but could benefit from splitting advanced topics. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
Reviewed
Table of Contents