eli5
Explain a topic like I'm a 5 year old. Use when the user types /eli5 <topic> or asks for a…
Trigger on-chain data collection (a "Commit") in Tres Finance for wallets that have already been onboarded. Use this skill whenever the user wants to collect data, pull balances, sync wallets, refresh on-chain data, run a commit, trigger a commit, or "collect" anything in Tres.
$ npx -y skills add anthropics/claude-plugins-community --skill tres-data-collection-commit --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/tres-data-collection-commitContext preview
The summary Claude sees to decide when to auto-load this skill.
Trigger on-chain data collection (a "Commit") in Tres Finance for wallets that have already been onboarded. Use this skill whenever the user wants to collect data, pull balances, sync wallets, refresh on-chain data, run a commit, trigger a commit, or "collect" anything in Tres.
name: tres-data-collection-commit description: > Trigger on-chain data collection (a "Commit") in Tres Finance for wallets that have already been onboarded. Use this skill whenever the user wants to collect data, pull balances, sync wallets, refresh on-chain data, run a commit, trigger a commit, or "collect" anything in Tres. This is the second step of the Tres onboarding flow — it sits between wallet upload (tres-wallets-upload) and balance validation (tres-asset-balance-validation). Always trigger this skill for any request that mentions "commit", "collect", "data collection", "pull data", "fetch on-chain data", "sync wallets", "refresh balances", or anytime the user just finished uploading wallets and is ready to bring in their on-chain data. compatibility: "Requires TRES Finance MCP connected (https://ai.tres.finance/mcp)"
Commit is the step that pulls on-chain data into Tres Finance for the wallets already onboarded to the org. It runs the platform's data-collection pipeline for each wallet and either:
balances. Used for a complete onboarding or historical backfill.
Much faster; useful when the user just wants an up-to-date snapshot or is preparing for a quick balance validation.
This skill is the **second step** of the customer onboarding flow:
1. **Upload wallets** (`tres-wallets-upload`) — register the wallets in Tres. 2. **Collect data (this skill)** — run the commit so Tres actually fetches the on-chain state. 3. **Validate balances** (`tres-asset-balance-validation`) — cross-check the collected balances against DeBank.
Trigger this skill whenever the user wants to:
**Example phrases that must trigger this skill:**
---
| Requirement | Details | |---|---| | TRES Finance MCP connected | The TRES MCP tools (`get_viewer`, `execute`, `build_query`, `introspect`) must be available | | Authenticated org | `get_viewer` must succeed and return an `orgName` | | At least one wallet onboarded | If there are no wallets, commit has nothing to collect — point the user to `tres-wallets-upload` first |
---
Follow these steps in order. Do **not** skip the user-selection steps — the whole point of this skill is to capture the user's collection intent before firing the mutation.
Call `get_viewer` to verify the user is authenticated to Tres and note the `orgName`. Mention it in the confirmation summary later so the user knows which org the commit will run against.
If `get_viewer` fails: tell the user the TRES MCP is not connected and ask them to connect it before continuing.
This is the core choice of the skill. Ask the user **exactly** this (using the `AskUserQuestion` tool if available, otherwise plain text):
> **What do you want to collect?** > > 1. **Full data collection** — collects all transactions and current balances. > Slower, but produces a complete ledger. Use this for first-time onboarding > or historical backfill. > 2. **Balances only** — collects only current balances, no transactions. Fast. > Use this when you just want an up-to-date balance snapshot (for example, > before running balance validation).
Map the answer to the GraphQL parameter `balancesOnly`:
| User choice | `balancesOnly` | |---|---| | Full data collection | `false` | | Balances only | `true` |
If the user is unsure, recommend **Full data collection** as the default for first-time onboarding (because skipping transactions means the ledger will be empty even after commit succeeds).
Ask the user whether the commit should run on every wallet or a subset:
> **Which wallets should I collect data for?** > > 1. **All wallets** — run the commit across every wallet in the org. > 2. **Specific wallets** — only collect data for wallets I pick.
If the user chooses **All wallets**: set `internalAccountIds = null` (omit the field in the mutation variables, or pass `null`).
If the user chooses **Specific wallets**:
1. Fetch the list of wallets from Tres so the user can pick from real options:
query ListWalletsForCommit {
internalAccount {
totalCount
results {
id
name
identifier
parentPlatform
}
}
}2. Present the wallets as a numbered plain-text list (name + short address + platform). If there are more than ~25 wallets, show the first 25 and tell the user they can reply with wallet names, addresses, or IDs to narrow down. 3. Let the user respond conversationally ("the three Ethereum ones", "Treasury Hot and Cold Storage", "IDs 123, 456, 789", etc.). Resolve their response to a list of internal account `id` values. Never call the mutation with an unresolved name — always resolve to IDs first. 4. If you cannot confidently resolve a wallet the user named, ask them to clarify instead of guessing.
Show a short plain-text summary of exactly what is about to happen and ask for explicit confirmation. Example:
About to trigger a Commit in Tres Finance: Org: Acme Labs Mode: Full data collection (transactions + balances) Wallets: All wallets in
Community-contributed plugins for Claude Cowork and Claude Code.
Repo: anthropics/claude-plugins-community
Explain a topic like I'm a 5 year old. Use when the user types /eli5 <topic> or asks for a…
Write an implementation plan as one interactive HTML page - a tree of claims (why › what ›…
Use the `quickdesign` CLI to generate AI media — UGC promo videos, image edits, product…
Use only when the user explicitly asks for a TestDino audit of Playwright automated test…
Use when the user wants to check TestDino connection status, validate their PAT, discover…
Use when the user wants to manage a manual execution run or update case-level results inside…