ahmetenesdurahmetenesdur/starkfi/skills/batch/SKILL.md

batch

Skill2 starsChanged 8 months agoMITView on GitHub

Execute multiple different DeFi operations in a single Starknet transaction — combine swaps, staking, lending supply/borrow/repay/withdraw, token sends, DCA orders, and Troves vault deposits/withdrawals into one multicall. Use this skill when the user wants to batch, combine, bundle, or chain multiple diverse operations together in one atomic transaction, such as "swap ETH and then stake STRK" or "withdraw from lending and swap" or "repay debt and stake" or "swap and send in one go" or "create a DCA order and stake" or "deposit into vault and swap". Also trigger when the user mentions multicall, combining operations, doing multiple things at once, or wants to save gas by bundling actions — even if they don't use the word "batch".

13 other projects use a version of this.

Adopted by

Most recently taken up by

MikeyPetrillo/Agent402their own version, first seen Nov 8, 2026
KadirHarmanc/nazar-skilltheir own version, first seen Nov 8, 2026
codewhale-hq/codewhale-plugin-marketplacetheir own version, first seen Nov 8, 2026
HeshamFS/swarmweavertheir own version, first seen Nov 1, 2026
codebycorey/delta-spectheir own version, first seen Oct 15, 2026
unclejobs-ai/second-claude-codetheir own version, first seen Oct 13, 2026

Used with

Projects with it also use loop, simplify and 1 more.

Other files people use alongside this one.

HeshamFSSkill
loop
Run a command or check on a recurring interval
Also in 5 projects that use this
Hugging FaceSkill
simplify
Refactor code after tests pass. The "Refactor" phase of Red-Green-Refactor.
Also in 4 projects that use this
Microsoft AzureSkill
verify
End-to-end app testing pipeline for browser-based web apps on cloud browsers via Azure Playwright Workspaces: verify the live app, author tests for working flows, heal failing tests, then re-run with video and produce one consolidated report. Three phases (app verification, test authoring, test healing) plus a scoped final sanity run; each phase emits a sub-report. Use when asked to "verify my app", "make sure my app works and has good test coverage", "do a full QA pass", "add tests where I'm missing coverage", "fix failing tests and add new ones", "smoke test before deploy", "QA my deployment", or any combined verify-and-test ask. Requires Azure CLI (`az login`) and a Playwright Workspace resource ID — bootstraps configs on first invocation. Browser-based web apps with Playwright only — not for unit/API tests, native mobile/desktop, load/perf, or full accessibility audits.
Also in 3 projects that use this

Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
ww-w-ai/bkit-gemini★ 66same name
MikeyPetrillo/Agent402★ 51same name
unclejobs-ai/second-claude-code★ 41same name
woxiangyangzhimao/skills★ 14same name
codewhale-hq/codewhale-plugin-marketplace★ 5same name
codebycorey/delta-spec★ 4same name
HeshamFS/swarmweaver★ 4same name
jiaxuan030331/applyloop★ 2same name
angelgabrieljacintohuayllasco/clipboard-skills★ 0same name
beginnersinai/content-repurposer★ 0same name
3 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- authenticate-walletSkill
- balanceSkill
- confidentialSkill
- configSkill
- dcaSkill
- lendingSkill
- lstSkill
- multi-swapSkill
- portfolioSkill
- sendSkill
- stakingSkill
- tradeSkill
- trovesSkill

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 1 is distinctive, and 10 are very specific to this project.

0
Common
Most of the 10 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
10
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
BEFORE any batch, you MUST run npx starkfi@latest status and npx starkfi@latest balance to verify connectivity and funds.
line 30
Very specific:
If the batch includes a --send operation, you MUST confirm the recipient address with the user before executing.
line 33
Very specific:
AFTER a successful batch, verify with npx starkfi@latest tx-status <hash>.
line 35
Distinctive:
All operations in a batch are atomic — if any one fails, the entire transaction reverts.
line 36
Very specific:
Use trade for a single swap.
line 154
Very specific:
Use staking for standalone staking operations.
line 155
Very specific:
Use lending for standalone lending operations.
line 156
Very specific:
Use send for standalone token transfers.
line 157
Very specific:
Use dca for standalone DCA order management.
line 158
Very specific:
Use troves for standalone vault deposit/withdraw operations.
line 159
Very specific:
Use lst for liquid staking operations (not supported in batch).
line 160

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Batch Execute

Bundle multiple diverse DeFi operations into a single Starknet multicall transaction. Supports combining swaps, staking, lending supply/borrow/repay/withdraw, token sends, DCA orders, and Troves vault deposits/withdrawals — all executed atomically in one on-chain call.

Prerequisites

Active session required.
Sufficient balance for all operations + gas fees.
Minimum 2 operations required per batch.

Rules

BEFORE any batch, you MUST run npx starkfi@latest status and npx starkfi@latest balance to verify connectivity and funds.
A batch MUST include at least 2 operations. For single operations, use the dedicated skill (trade, send, staking, lending, or dca).
Each --swap, --stake, --supply, --send, --dca-create, and --dca-cancel flag can appear multiple times (repeatable).
If the batch includes a --send operation, you MUST confirm the recipient address with the user before executing.
Suggest using --simulate first to verify the entire batch would succeed.
AFTER a successful batch, verify with npx starkfi@latest tx-status <hash>.
All operations in a batch are atomic — if any one fails, the entire transaction reverts.

Commands

npx starkfi@latest batch [--simulate] [--json] \
  --swap "<amount> <from> <to>" \
  --stake "<amount> <token> <validator_or_pool>" \
  --supply "<amount> <token> <pool>" \
  --send "<amount> <token> <recipient>" \
  --borrow "<col_amt> <col_token> <bor_amt> <bor_token> <pool>" \
  --repay "<amount> <token> <col_token> <pool>" \
  --withdraw "<amount> <token> <pool>" \
  --dca-create "<amount> <sell> <buy> <perCycle> [frequency]" \
  --dca-cancel "<orderId>" \
  --troves-deposit "<amount> <token> <strategyId> [amount2 token2]" \
  --troves-withdraw "<amount> <token> <strategyId> [amount2 token2]"

Operation Formats

Flag	Format	Example
`--swap`	`"<amount> <from> <to>"`	`--swap "100 USDC ETH"`
`--stake`	`"<amount> <token> <validator_or_0xPool>"`	`--stake "500 STRK Karnot"`
`--supply`	`"<amount> <token> <pool>"`	`--supply "100 USDC Prime"`
`--send`	`"<amount> <token> <0xRecipient>"`	`--send "10 STRK 0x07b2..."`
`--borrow`	`"<col_amt> <col_token> <bor_amt> <bor_token> <pool>"`	`--borrow "0.5 ETH 500 USDC Prime"`
`--repay`	`"<amount> <token> <col_token> <pool>"`	`--repay "100 USDC ETH Prime"`
`--withdraw`	`"<amount> <token> <pool>"`	`--withdraw "200 USDC Prime"`
`--dca-create`	`"<amount> <sell> <buy> <perCycle> [freq]"`	`--dca-create "1000 USDC ETH 10 P1D"`
`--dca-cancel`	`"<orderId>"`	`--dca-cancel "abc123"`
`--troves-deposit`	`"<amount> <token> <strategyId> [amount2 token2]"`	`--troves-deposit "100 STRK evergreen_strk"` or `"100 STRK ekubo_cl_strketh 0.005 ETH"`
`--troves-withdraw`	`"<amount> <token> <strategyId> [amount2 token2]"`	`--troves-withdraw "50 STRK evergreen_strk"` or `"50 STRK ekubo_cl_strketh 0.005 ETH"`

Note: --stake accepts either a validator name (e.g. Karnot) or a pool contract address (starting with 0x). The CLI auto-detects the format.

Parameters

Parameter	Type	Description	Required
`--swap`	string	Swap operation (repeatable)	No*
`--stake`	string	Stake operation (repeatable)	No*
`--supply`	string	Lending supply operation (repeatable)	No*
`--send`	string	Token transfer operation (repeatable)	No*
`--borrow`	string	Borrow from lending pool (repeatable)	No*
`--repay`	string	Repay lending debt (repeatable)	No*
`--withdraw`	string	Withdraw from lending pool (repeatable)	No*
`--dca-create`	string	Create DCA order (repeatable)	No*
`--dca-cancel`	string	Cancel DCA order (repeatable)	No*
`--troves-deposit`	string	Troves vault deposit (repeatable)	No*
`--troves-withdraw`	string	Troves vault withdraw (repeatable)	No*
`--simulate`	flag	Estimate fees without broadcasting	No
`--json`	flag	Output as JSON	No

*At least 2 operations (of any type) are required.

Examples

User: "Swap 100 USDC to ETH and stake 500 STRK with Karnot in one transaction"

npx starkfi@latest status
npx starkfi@latest balance
npx starkfi@latest batch --swap "100 USDC ETH" --stake "500 STRK Karnot"
npx starkfi@latest tx-status <hash>

User: "Withdraw my USDC from Prime lending and swap it to ETH"

npx starkfi@latest status
npx starkfi@latest balance
npx starkfi@latest batch --withdraw "200 USDC Prime" --swap "200 USDC ETH"
npx starkfi@latest tx-status <hash>

User: "Repay my USDC debt on Prime and stake STRK"

npx starkfi@latest status
npx starkfi@latest balance
npx starkfi@latest batch --repay "100 USDC ETH Prime" --stake "50 STRK karnot"
npx starkfi@latest tx-status <hash>

User: "Borrow USDC using ETH as collateral and swap half to STRK"

npx starkfi@latest status
npx starkfi@latest balance
npx starkfi@latest batch \
  --borrow "0.5 ETH 500 USDC Prime" \
  --swap "250 USDC STRK"
npx starkfi@latest tx-status <hash>

User: "Simulate a batch of two swaps and a stake"

npx starkfi@latest batch --simulate \
  --swap "100 USDC ETH" \
  --swap "200 USDT STRK" \
  --stake "500 STRK Karnot"

Error Handling

Error	Action
`Too few operations`	At least 2 operations required. Use dedicated skills instead.
`Insufficient balance`	Check `balance` for all required tokens.
`Invalid validator/pool`	Run `validators`/`pools` to find valid names/addresses.
`Simulation failed`	One of the operations would revert. Check each individually.
`Not authenticated`	Run `authenticate-wallet` skill first.

Related Skills

Use trade for a single swap.
Use staking for standalone staking operations.
Use lending for standalone lending operations.
Use send for standalone token transfers.
Use dca for standalone DCA order management.
Use troves for standalone vault deposit/withdraw operations.
Use lst for liquid staking operations (not supported in batch).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free