alchemy-web3
Interact with Alchemy's Web3 APIs for blockchain data, NFTs, tokens, transfers, and webhooks across 80+ chains.
62
45%
Does it follow best practices?
Impact
98%
1.04xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xgizmolab/alchemy-web3-skill/alchemy-web3/SKILL.mdQuality
Discovery
40%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 identifies a clear niche (Alchemy Web3 APIs) and lists relevant data categories, making it reasonably distinctive. However, it lacks a 'Use when...' clause, which is critical for Claude to know when to select this skill, and the capabilities listed are categories rather than specific actions. Adding explicit trigger guidance and more concrete action verbs would significantly improve selection accuracy.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks about Alchemy APIs, querying blockchain data, fetching NFT metadata, tracking token transfers, or setting up webhooks for on-chain events.'
Replace category nouns with concrete actions, e.g., 'Query token balances, fetch NFT metadata and ownership, track wallet transfers, configure notification webhooks' instead of just listing 'NFTs, tokens, transfers, webhooks'.
Include common user-facing trigger terms like 'wallet', 'ERC-20', 'on-chain', 'Ethereum', 'smart contract', or 'crypto' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Alchemy Web3 APIs) and lists several areas (blockchain data, NFTs, tokens, transfers, webhooks), but these are categories rather than concrete actions like 'query token balances' or 'create webhooks'. The mention of '80+ chains' adds some specificity. | 2 / 3 |
Completeness | Describes what it does (interact with Alchemy APIs for various blockchain data) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' portion is also only moderately detailed, placing this at 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Alchemy', 'Web3', 'blockchain', 'NFTs', 'tokens', 'transfers', 'webhooks' which users might naturally say. However, it misses common variations like 'wallet', 'ERC-20', 'smart contract', 'on-chain data', 'Ethereum', or specific chain names that users would likely mention. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Alchemy' as a specific platform combined with 'Web3 APIs' creates a clear niche. This is unlikely to conflict with other skills unless there are multiple Alchemy-related skills, as the combination of the vendor name and blockchain domain is quite distinctive. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with concrete, executable examples across multiple formats (CLI, curl, JS), but suffers significantly from verbosity and promotional content. The same operations are shown 3-4 different ways inline when most should be in reference files, and the repeated GizmoLab marketing links waste tokens. Progressive disclosure structure exists but isn't leveraged — the main file should be a concise overview pointing to the detailed reference files it already has.
Suggestions
Remove all promotional/marketing content (GizmoLab mentions, tracking URLs, 'About' section) — this wastes significant tokens and adds no instructional value.
Move the Direct API Examples (curl), JavaScript/Node.js Examples, and Webhooks sections into their respective reference files, keeping only the CLI quick reference and one brief example in the main skill.
Add a validation step after setup (e.g., 'Verify your key works: `./alchemy.sh balance 0xd8dA...` — should return a numeric balance') and error recovery guidance for rate limiting.
Signal reference file links inline where relevant (e.g., next to the CLI NFT command, link to references/nft-api.md) rather than listing all references only at the bottom.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines. It includes redundant promotional content (GizmoLab mentioned 6+ times with tracking URLs), explains the same operations in CLI, curl, JavaScript fetch, AND Alchemy SDK forms, and includes an 'About' section that is pure marketing. The chain table, rate limits table, and webhook details could all be in reference files. | 1 / 3 |
Actionability | The skill provides fully executable curl commands, bash CLI examples, and JavaScript code with real endpoint URLs and realistic parameters. Commands are copy-paste ready with concrete addresses and expected outputs noted. | 3 / 3 |
Workflow Clarity | Setup steps are clear and sequenced. The 'Common Patterns' section shows multi-step workflows like portfolio tracking and multi-chain queries. However, there are no validation checkpoints or error recovery steps — e.g., no guidance on what to do when rate limited, no verification that the API key works before proceeding. | 2 / 3 |
Progressive Disclosure | The skill does reference external files (references/nft-api.md, references/agent-workflows.md, etc.) at the bottom, which is good. However, the main file is monolithic with extensive inline API examples (curl, JS, SDK) that should be in those reference files instead. The references are buried at the very end rather than signaled inline where relevant. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
- Repository
- NeverSight/skills_feed
- Commit
9f4534c
- 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.