agentleFS
ahmetenesdurahmetenesdur/starkfi/skills/staking/SKILL.md

staking

Skill2 starsChanged 8 months agoMITView on GitHub

Stake, unstake, claim, and compound rewards for STRK, WBTC, tBTC, SolvBTC, and LBTC on Starknet. View validators, pools, and staking positions. Use this skill when the user mentions staking, delegating, validators, staking pools, rewards, compounding, unstaking, earning yield, passive income on crypto, or wants to earn on their STRK or BTC tokens — even if they don't say "stake" explicitly.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 0 are distinctive, and 9 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 9

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    BEFORE staking, you MUST run npx starkfi@latest validators to list available validators, then npx starkfi@latest pools <validator> to see …

    line 46
  2. Very specific:

    BEFORE staking, check balance to confirm the user has enough tokens.

    line 47
  3. Very specific:

    AFTER any transactional operation (stake, unstake, rewards), verify with tx-status.

    line 50
  4. Very specific:

    Use stake-status to view the user's current staking positions across all validators.

    line 51
  5. Very specific:

    LST Disambiguation: If the user mentions "liquid staking", "xSTRK", or "Endur", redirect to the lst skill instead.

    line 53
  6. Very specific:

    Use balance to check available tokens before staking.

    line 188
  7. Very specific:

    Use portfolio for a full overview including staking positions with USD values.

    line 189
  8. Very specific:

    Use batch to combine staking with other operations in one transaction.

    line 190
  9. Very specific:

    Use lst for liquid staking via Endur (xSTRK — automatic yield, instant redemption).

    line 191

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Staking

Manage Starknet staking operations: delegate tokens to validators, claim or compound rewards, and unstake positions. Supports multiple token types across various validators and pools.

Prerequisites

  • Active session required.
  • Sufficient token balance for staking + gas fees.

Supported Tokens

TokenType
STRKNative
WBTCBitcoin
tBTCBitcoin
SolvBTCBitcoin
LBTCBitcoin

Rules

  1. BEFORE staking, you MUST run npx starkfi@latest validators to list available validators, then npx starkfi@latest pools <validator> to see available pools.
  2. BEFORE staking, check balance to confirm the user has enough tokens.
  3. Unstaking is a two-step process: first unstake intent starts a cooldown, then unstake exit finalizes after the cooldown period. The user must wait between these steps.
  4. rewards --compound atomically claims and restakes in one transaction.
  5. AFTER any transactional operation (stake, unstake, rewards), verify with tx-status.
  6. Use stake-status to view the user's current staking positions across all validators. When exit intents are active, unpooling amounts and cooldown dates are shown automatically.
  7. Token defaults to STRK if --token is not specified.
  8. LST Disambiguation: If the user mentions "liquid staking", "xSTRK", or "Endur", redirect to the lst skill instead. This skill handles delegation staking only. Do NOT use rewards --claim or rewards --compound for xSTRK positions.

Commands

# Discovery
npx starkfi@latest validators [--json]
npx starkfi@latest pools <validator> [--json]
npx starkfi@latest stake-status [validator] [--json]

# Stake tokens
npx starkfi@latest stake <amount> --validator <name> [--token <symbol>] [--simulate] [--json]

# Unstake (two-step)
npx starkfi@latest unstake intent --validator <name> --amount <amount> [--token <symbol>]
npx starkfi@latest unstake exit --validator <name> [--token <symbol>]

# Rewards
npx starkfi@latest rewards --claim --validator <name> [--token <symbol>]
npx starkfi@latest rewards --compound --validator <name> [--token <symbol>]

Parameters

stake

ParameterTypeDescriptionRequired
amountnumberAmount to stake (positional)Yes
--validatorstringValidator name (from validators list)Yes*
--poolstringPool contract address (alternative to validator)Yes*
--tokenstringToken symbol (default: STRK)No
--simulateflagEstimate fees without broadcastingNo
--jsonflagOutput raw JSONNo

*Provide either --validator or --pool.

unstake

ParameterTypeDescriptionRequired
actionstringintent or exit (positional)Yes
--validatorstringValidator nameYes*
--poolstringPool contract addressYes*
--amountnumberAmount to unstake (required for intent)For intent
--tokenstringToken symbol (default: STRK)No

rewards

ParameterTypeDescriptionRequired
--claimflagClaim pending rewardsYes*
--compoundflagClaim and immediately restakeYes*
--validatorstringValidator nameYes**
--poolstringPool contract addressYes**
--tokenstringToken symbol (default: STRK)No

*Provide either --claim or --compound. **Provide either --validator or --pool.

Examples

User: "Which validators can I stake with?"

npx starkfi@latest validators

User: "Show me pools for Karnot"

npx starkfi@latest pools Karnot

User: "Stake 1000 STRK with Karnot"

npx starkfi@latest status
npx starkfi@latest balance --token STRK
npx starkfi@latest stake 1000 --validator Karnot
npx starkfi@latest tx-status <hash>

User: "Stake 0.5 WBTC with Karnot"

npx starkfi@latest balance --token WBTC
npx starkfi@latest stake 0.5 --validator Karnot --token WBTC
npx starkfi@latest tx-status <hash>

User: "Compound my STRK rewards from Karnot"

npx starkfi@latest rewards --compound --validator Karnot
npx starkfi@latest tx-status <hash>

User: "Claim my rewards from Karnot"

npx starkfi@latest rewards --claim --validator Karnot
npx starkfi@latest tx-status <hash>

User: "I want to unstake my STRK from Karnot"

# Step 1: Start unstake cooldown
npx starkfi@latest unstake intent --validator Karnot --amount 1000
npx starkfi@latest tx-status <hash>
# Inform user about cooldown period
# Step 2: After cooldown, finalize
npx starkfi@latest unstake exit --validator Karnot
npx starkfi@latest tx-status <hash>

User: "Show me all my staking positions"

npx starkfi@latest stake-status

Error Handling

ErrorAction
Validator not foundRun validators to list valid names.
Pool not foundRun pools <validator> to list available pools.
Insufficient balanceCheck balance and suggest a smaller amount.
Cooldown not completeUser must wait before running unstake exit.
No rewards to claimPosition has no pending rewards.
Not authenticatedRun authenticate-wallet skill first.

Related Skills

  • Use balance to check available tokens before staking.
  • Use portfolio for a full overview including staking positions with USD values.
  • Use batch to combine staking with other operations in one transaction.
  • Use lst for liquid staking via Endur (xSTRK — automatic yield, instant redemption).

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.