alchemy-web3

Interact with Alchemy's Web3 APIs for blockchain data, NFTs, tokens, transfers, and webhooks across 80+ chains.

1.04x

Quality

—

Does it follow best practices?

Impact

98%

1.04x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is rich with executable API examples but is over-long and promotional, leans on a CLI script that is missing from the bundle, and provides no validation feedback loops for its batch/agent workflows. Tightening the prose, shipping the referenced scripts and reference files, and adding verify steps would lift every dimension.

Suggestions

Provide the missing 'scripts/alchemy.sh' (and whale-tracker.sh) and the referenced 'references/*.md' files, or remove the dead references so navigation is not broken.

Delete the 'About'/GizmoLab marketing block and de-duplicate the curl, fetch, and SDK examples to cut the body well under its current length.

Add explicit validation/retry checkpoints to the multi-chain loop and cron agent jobs (e.g. check the response error code, retry on 429, verify non-empty results before acting).

Dimension	Reasoning	Score
Conciseness	The ~390-line body is mostly action-oriented but padded with promotional 'About'/GizmoLab agency sections and duplicate full curl/JS payloads that don't help Claude act, so it is 'mostly efficient but could be tightened' rather than lean at score 3.	2 / 3
Actionability	Raw curl/JSON-RPC and fetch examples are copy-paste ready, but the central CLI commands all invoke './alchemy.sh' (and scripts/whale-tracker.sh) which do not exist in the bundle, leaving the primary actionable path incomplete — between fully executable (3) and incomplete guidance (2).	2 / 3
Workflow Clarity	Setup and agent-pattern sequences are present, but there are no validation/verification checkpoints or error-recovery loops for batch and cron-driven operations, which the rubric says caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Sections are clearly signaled and a 'See Also' lists one-level-deep references, but those references/.md and scripts/.sh files are absent from the (empty) bundle, so the navigation is broken and bulky API content stays inline rather than being split out.	2 / 3
	Total	8 / 12 Passed

Description

82%

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 specific and distinctive with strong natural trigger terms, but it omits an explicit 'Use when...' clause, leaving the 'when to use' half of completeness only implied. Adding a trigger sentence would raise it to the top level across all dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when querying on-chain balances, NFTs, token holdings, or transaction history across EVM/Solana chains via Alchemy.'

Add common user-task phrasings ('wallet balances', 'on-chain data', 'Ethereum/Polygon transactions') to broaden natural trigger coverage.

Lead with the user task rather than the vendor ('Query wallet balances, NFTs, tokens, and transfers on-chain via Alchemy...') so the trigger reads as a user need.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete capabilities — 'blockchain data, NFTs, tokens, transfers, and webhooks' across named chains — matching the score-3 anchor for multiple specific actions rather than the partial coverage of score 2.	3 / 3
Completeness	It clearly states what the skill does but lacks any 'Use when...' or equivalent explicit trigger clause, so per the judging guideline a missing when-clause caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	It surfaces natural user terms ('blockchain data, NFTs, tokens, transfers, webhooks, chains') with good coverage, though it leans slightly API-framed; the breadth keeps it at the top anchor over the 'some relevant keywords' of score 2.	3 / 3
Distinctiveness Conflict Risk	'Alchemy's Web3 APIs... across 80+ chains' defines a clear niche with distinct triggers unlikely to fire for unrelated skills, matching the score-3 anchor.	3 / 3
	Total	11 / 12 Passed

Validation

75%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 12 / 16 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
referenced_paths_exist	Referenced path issues: 6 missing	Warning

	Total	12 / 16 Passed

Repository: NeverSight/skills_feed
Commit: 26d37ce

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.