Nft Analytics Guide

What it does

When your agent uses it

• Helping users research NFT markets
• Evaluate collections

Example prompts

• “/nft-analytics-guide”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Always check for wash trading — reported volume can be 50–90% fake
2. 2Floor price is the most honest metric — it's the actual cost to enter
3. 3Low listed % is usually bullish — holders aren't trying to sell
4. 4Whale concentration — if top 10 wallets hold >30%, they control the floor
5. 5Use aggregators for best prices — don't buy on just one marketplace
6. 6ERC-8004 NFTs are different — they represent AI agents with reputation, not art
7. 7Bear market NFTs — focus on utility and revenue, not hype

What it can do on your machine

Read from SKILL.md and the folder at commit 238ef60. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are sql).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • opensea.io
  • blur.io
  • reservoir.tools
  • nftgo.io
  • dune.com
  • eips.ethereum.org

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Nft Analytics Guide loads about 1.8k tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 717 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~76

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nirholas/three.ws at commit 238ef60, republished under its MIT licence (© nirholas). 717 words, ~1,840 tokens.

name

nft-analytics-guide

description

Guide to NFT analytics — floor price tracking, wash trading detection, rarity analysis, collection metrics, and marketplace comparison. Covers free tools and APIs for evaluating NFT collections and individual tokens. Use when helping users research NFT markets or evaluate collections.

license

MIT

metadata.category

analysis

metadata.difficulty

intermediate

metadata.author

clawhub

metadata.tags

analysis, nft-analytics-guide

Suspicious if:
- >50% of volume from <10 wallets
- Average holding time <1 hour
- Same NFTs traded repeatedly between same addresses
- Volume spikes without holder growth

SELECT
    date_trunc('day', block_time) as day,
    COUNT(*) as sales,
    SUM(amount_usd) as volume_usd
FROM nft.trades
WHERE nft_contract_address = 0x... -- collection address
  AND block_time > now() - interval '30 days'
GROUP BY 1
ORDER BY 1

SELECT
    COUNT(DISTINCT wallet) as unique_holders,
    SUM(CASE WHEN balance = 1 THEN 1 ELSE 0 END) as single_holders,
    SUM(CASE WHEN balance > 10 THEN 1 ELSE 0 END) as whales
FROM (
    SELECT to as wallet, COUNT(*) as balance
    FROM erc721_transfers
    WHERE contract_address = 0x...
    GROUP BY 1
)

© nirholas, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in data/skills/analysis/nft-analytics-guide of nirholas/three.ws.

Open the folder on GitHubat commit 238ef60