solana

Query Solana wallets, tokens, txs, and NFTs in USD.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%Weight 40%Scale 1-5

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

The body is a lean, fully executable reference: all 8 commands are documented with runnable invocations, flags, and expected outputs, reinforced by a setup check, a pitfalls section covering rate limits and heuristic limitations, and a verification step. The only real trimming opportunity is the repeated absolute script path and the duplicated stats command in the Verification section.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence — no blockchain/Solana concept tutorials, just command, flags, and expected output per section — matching anchor 4. Not anchor 5: the full script path "~/.hermes/skills/blockchain/solana/scripts/solana_client.py" is repeated verbatim ~10 times when Quick Reference already establishes it, and the closing Verification section repeats the `stats` command already shown twice.	4 / 5
Actionability	Every one of the 8 commands has a copy-paste-ready invocation with realistic arguments (e.g. `wallet 9WzDXwBbmkg8ZTbNMqUxvQRAyrZzDsGYdLVL9zYtAWWM`, `whales --min-sol 500`, `token DezXAZ8z7PnrnRJjz3wXBoRgixCa6xjnB7YaB1pPB263`), documented flags, described outputs, and a Quick Reference block listing the full CLI surface. Fully executable and covering common cases.	5 / 5
Workflow Clarity	The Procedure is numbered 0-8 with an explicit setup checkpoint ("Confirm connectivity" via `stats`), a Pitfalls section that doubles as error-recovery guidance (retry-on-429 with exponential backoff, `--no-prices` fallback, private RPC override), and a final Verification step stating the expected output. The operations are read-only so the destructive/batch cap does not apply, and each command's single action is unambiguous.	5 / 5
Progressive Disclosure	Clean overview-to-detail structure (When to Use → Prerequisites → Quick Reference → Procedure → Pitfalls → Verification) with a single one-level-deep bundle reference: all logic lives in `scripts/solana_client.py` (verified present, and its argparse subcommands match the documented CLI), while SKILL.md holds only usage. Nothing that belongs in a separate file is inlined, and navigation via section headers is easy.	5 / 5
	Total	19 / 20 Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise, concrete, third-person description that names a distinct domain and four capability areas, but it omits any explicit "use when" trigger guidance and abbreviates "transactions" as "txs" while missing natural synonyms like SOL, portfolio, and price. It reads well as a "what" statement yet under-serves trigger-time matching.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks about a Solana wallet balance, token price or holdings, a transaction signature, NFTs, or Solana network health."

Cover the documented commands the description omits — whale detection ("large SOL transfers"), network stats (TPS, epoch), and price lookup — so the description matches the skill's 8 commands.

Use natural phrasing users would actually say: spell out "transactions", and include "SOL" and "price" as keywords.

Dimension	Reasoning	Score
Specificity	"Query Solana wallets, tokens, txs, and NFTs in USD" names a domain plus four concrete queryable targets with USD enrichment — several specific capabilities rather than the 1-2 of anchor 3. It falls short of anchor 5 because coverage is not comprehensive: whale detection, network stats, and standalone price lookup (all documented commands in the skill) are absent.	4 / 5
Completeness	The "what" is clear (query wallets/tokens/txs/NFTs with USD pricing) but there is no "Use when..." clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 3. It is not anchor 2 because the "what" is specific rather than vague.	3 / 5
Trigger Term Quality	Natural user terms are present — "Solana", "wallets", "tokens", "NFTs", "USD" — matching anchor 4's "good keyword coverage; a few natural terms missing". Not anchor 5: common variations like "SOL", "portfolio", "price", and the spelled-out "transactions" (only the jargon-ish "txs" appears) are missing.	4 / 5
Distinctiveness Conflict Risk	"Solana" is a clearly distinct niche appearing in the domain itself, and the wallet/token/NFT triggers are specific to blockchain queries — minimal overlap risk with other skills. Matches anchor 5's clear-niche pattern.	5 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 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

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/blockchain/solana/SKILL.md
Commit: 68fa7e9

Reviewed: 3 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.