Claims
ruvnet/ruflo
Claims-based authorization for agents and operations. An agent skill from ruvnet/ruflo.
Analyze TokenJar profitability and optionally execute a Firepit burn-and-claim.
$ npx skills add LeoYeAI/openclaw-master-skills --skill seek-protocol-fees -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills seek-protocol-fees --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/seek-protocol-fees .claude/skills/seek-protocol-fees && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "seek-protocol-fees" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/seek-protocol-fees into .claude/skills/seek-protocol-fees/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seek-protocol-fees", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/seek-protocol-feesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill seek-protocol-fees -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills seek-protocol-fees --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/seek-protocol-fees .agents/skills/seek-protocol-fees && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "seek-protocol-fees" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/seek-protocol-fees into .agents/skills/seek-protocol-fees/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seek-protocol-fees", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill seek-protocol-fees -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills seek-protocol-fees --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/seek-protocol-fees .cursor/skills/seek-protocol-fees && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "seek-protocol-fees" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/seek-protocol-fees into .cursor/skills/seek-protocol-fees/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seek-protocol-fees", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/seek-protocol-fees--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill seek-protocol-fees -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills seek-protocol-fees --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/seek-protocol-fees .gemini/skills/seek-protocol-fees && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "seek-protocol-fees" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/seek-protocol-fees into .gemini/skills/seek-protocol-fees/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seek-protocol-fees", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills seek-protocol-feesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill seek-protocol-fees -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/seek-protocol-fees .github/skills/seek-protocol-fees && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "seek-protocol-fees" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/seek-protocol-fees into .github/skills/seek-protocol-fees/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seek-protocol-fees", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill seek-protocol-fees -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills seek-protocol-fees --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/seek-protocol-fees .opencode/skills/seek-protocol-fees && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "seek-protocol-fees" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/seek-protocol-fees into .opencode/skills/seek-protocol-fees/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seek-protocol-fees", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
seek-protocol-feesAnalyze TokenJar profitability and optionally execute a Firepit burn-and-claim.
Seek Protocol Fees is an agent skill from LeoYeAI/openclaw-master-skills. Analyze TokenJar profitability and optionally execute a Firepit burn-and-claim. Autonomous pipeline: checks balances, prices assets, calculates profit vs. 4,000 UNI burn cost, simulates, and executes if profitable. Default is preview-only. Use when user asks "Is the TokenJar profitable?", "Execute a burn", or "Claim protocol fees."
Its SKILL.md is about 4.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `README.md` and `_meta.json`).
The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
Task(subagent_type:protocol-fee-seeker)Task(subagent_type:safety-guardian)mcp__uniswap__get_tokenjar_balancesmcp__uniswap__get_firepit_statemcp__uniswap__get_agent_balanceFrom allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
etherscan.ioFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Seek Protocol Fees loads about 4.5k tokens when it runs. Until then it costs about 88 tokens; SKILL.md has 939 words of instructions outside code blocks.
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.
The automated check found no risky patterns in SKILL.md.
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.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 939 words, ~4,463 tokens.
.claude/skills/seek-protocol-fees/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.This is the autonomous burn-and-claim pipeline for Uniswap's protocol fee system. The TokenJar (0xf38521f130fcCF29dB1961597bc5d2B60F995f85) accumulates fees from V2, V3, V4, UniswapX, and Unichain. The Firepit (0x0D5Cd355e2aBEB8fb1552F56c965B867346d6721) allows anyone to burn 4,000 UNI to release those accumulated assets. When the jar's value exceeds the burn cost plus gas, a profit opportunity exists.
This skill runs the full pipeline in one command: check balances, price assets, calculate profitability, simulate the burn, and -- only if the user explicitly opts in -- execute it.
Why this is 10x better than calling tools individually:
auto-execute: false). Even when execution is enabled, the pipeline simulates first, validates through safety-guardian, and checks nonce freshness for race conditions -- protections that are easy to skip when calling tools manually.Activate when the user says anything like:
Do NOT use when the user just wants to monitor accumulation over time (use monitor-tokenjar instead) or wants historical burn analysis (use analyze-burn-economics instead).
| Parameter | Required | Default | How to Extract |
|---|---|---|---|
| chain | No | ethereum | Always Ethereum mainnet for TokenJar/Firepit |
| auto-execute | No | false | "execute the burn", "claim fees" implies true; "check", "preview" implies false |
| post-burn-swap | No | false | "convert to stables", "swap to USDC" implies true |
| recipient | No | connected wallet | Explicit address if provided, otherwise agent's wallet |
If the user's intent is ambiguous between preview and execution, default to preview and present the profitability report. Let the user explicitly confirm before any UNI is burned.
SEEK-PROTOCOL-FEES PIPELINE
┌─────────────────────────────────────────────────────────────────────┐
│ │
│ Step 1: PRE-FLIGHT (direct MCP calls) │
│ ├── get_tokenjar_balances — what's in the jar? │
│ ├── get_firepit_state — threshold, nonce, readiness │
│ ├── get_agent_balance — does agent have enough UNI? │
│ └── Gate: if jar empty or no UNI → STOP immediately │
│ │ │
│ ▼ (all pre-flight data feeds into Step 2) │
│ │
│ Step 2: PROFITABILITY ANALYSIS (protocol-fee-seeker) │
│ ├── Price all TokenJar assets in USD │
│ ├── Calculate: burn cost + gas cost vs. jar value │
│ ├── Select optimal assets to claim │
│ ├── Determine net profit and ROI │
│ └── Output: Profitability Report │
│ │ │
│ ▼ PROFITABILITY GATE │
│ ┌───────────────────────────────────────────────────┐ │
│ │ PROFITABLE → Present report, proceed │ │
│ │ NOT PROFITABLE → Present report, STOP │ │
│ │ MARGINAL → Present report, warn user │ │
│ └───────────────────────────────────────────────────┘ │
│ │ (only if profitable) │
│ ▼ │
│ │
│ Step 3: USER CONFIRMATION │
│ ├── If auto-execute: false → present report, ask user │
│ ├── If auto-execute: true → present report, proceed │
│ └── User must explicitly confirm before UNI is burned │
│ │ │
│ ▼ │
│ │
│ Step 4: SIMULATE + EXECUTE (protocol-fee-seeker) │
│ ├── execute_burn(simulate=true) — dry run │
│ ├── safety-guardian validates transaction │
│ ├── Nonce freshness check (race condition protection) │
│ ├── execute_burn(simulate=false) — broadcast │
│ └── Wait for confirmation │
│ │ │
│ ▼ │
│ │
│ Step 5: POST-BURN REPORT │
│ ├── Show received tokens with USD values │
│ ├── If post-burn-swap: convert to stablecoins │
│ ├── Calculate final net profit after all costs │
│ └── Recommend next burn timing │
│ │
└─────────────────────────────────────────────────────────────────────┘Make three parallel MCP calls to quickly assess feasibility before invoking the agent:
mcp__uniswap__get_tokenjar_balances to get current jar contents.mcp__uniswap__get_firepit_state to get threshold, nonce, and wallet readiness.mcp__uniswap__get_agent_balance to check the agent's UNI balance.Gate checks (stop immediately if any fail):
| Check | Condition | Action if Failed |
|---|---|---|
| TokenJar empty | All balances are zero | "TokenJar is empty. No fees to claim." |
| Agent lacks UNI | UNI balance < threshold (4,000 UNI) | "Insufficient UNI: have {X}, need {threshold}. Acquire UNI first." |
| Firepit not ready | Contract state indicates unavailability | "Firepit contract is not ready: {reason}." |
Present to user after pre-flight:
Step 1/5: Pre-Flight Complete
TokenJar: 6 tokens detected (WETH, USDC, USDT, DAI, WBTC, UNI)
Firepit: Threshold 4,000 UNI | Nonce: 42
Agent UNI Balance: 5,200 UNI (sufficient)
Analyzing profitability...Delegate to Task(subagent_type:protocol-fee-seeker) with all pre-flight data:
Analyze the profitability of a Firepit burn-and-claim.
Pre-flight data:
- TokenJar balances: {from Step 1 — full balance data}
- Firepit state: threshold={threshold} UNI, nonce={nonce}
- Agent UNI balance: {balance}
Tasks:
1. Price every TokenJar asset in USD using get_token_price.
2. Calculate UNI burn cost: {threshold} UNI * current UNI price.
3. Estimate gas cost for the burn transaction using get_gas_price.
4. Calculate net profit: total_jar_value - (UNI_cost + gas_cost).
5. Select optimal assets to claim (highest value, exclude LP tokens, up to maxReleaseLength).
6. Provide a clear PROFITABLE / NOT_PROFITABLE / MARGINAL verdict.
Return a structured profitability report with per-asset breakdown.Present to user after completion:
Step 2/5: Profitability Analysis Complete
TokenJar Value: $52,000
┌─────────────────────────────────────────────┐
│ WETH 7.20 $18,000 (34.6%) │
│ USDC 15,000 $15,000 (28.8%) │
│ USDT 8,500 $8,500 (16.3%) │
│ WBTC 0.08 $6,400 (12.3%) │
│ DAI 4,100 $4,100 (7.9%) │
└─────────────────────────────────────────────┘
Burn Cost:
UNI burn: 4,000 UNI ($28,000)
Gas: ~$45
Total: $28,045
Net Profit: $23,955
ROI: 85.4%
Verdict: PROFITABLEIf NOT_PROFITABLE:
Step 2/5: Profitability Analysis Complete
TokenJar Value: $18,000
Burn Cost: $28,045 (4,000 UNI + gas)
Net Profit: -$10,045
Verdict: NOT PROFITABLE
The TokenJar value ($18,000) does not cover the burn cost ($28,045).
Estimated time to profitability: ~1.4 days (at $7,400/day accumulation rate).
Pipeline stopped. No burn executed.If the burn is profitable and auto-execute is false (default), present the full profitability report and ask for explicit confirmation:
Burn Confirmation Required
TokenJar Value: $52,000 (5 assets)
Burn Cost: $28,045 (4,000 UNI + $45 gas)
Net Profit: $23,955 (85.4% ROI)
Assets to Claim: WETH, USDC, USDT, WBTC, DAI
Post-Burn Swap: {Yes — convert to USDC | No — keep as received}
This will permanently burn 4,000 UNI. Proceed? (yes/no)Only proceed to Step 4 if the user explicitly confirms. If auto-execute is true, still present the report but proceed without waiting.
Delegate to Task(subagent_type:protocol-fee-seeker) for the execution pipeline:
Execute the Firepit burn-and-claim.
Profitability analysis (from Step 2):
{Full profitability report}
Selected assets: {asset list from Step 2}
Nonce at analysis time: {nonce from Step 1}
Execute the following sequence:
1. Simulate: execute_burn(simulate=true) with the selected assets.
2. If simulation succeeds, delegate to safety-guardian for transaction validation.
3. Nonce freshness check: re-read Firepit state. If nonce has changed, ABORT (race condition).
4. Execute: execute_burn(simulate=false) to broadcast.
5. Wait for transaction confirmation.
If any step fails, report the failure point and do not proceed.Present to user during execution:
Step 4/5: Executing Burn
Simulation: SUCCESS
Safety Check: APPROVED by safety-guardian
Nonce Check: Fresh (42 — unchanged)
Broadcasting... confirmed in block 19,500,000
Tx: https://etherscan.io/tx/0xabcd...1234If race condition detected:
Step 4/5: Execution ABORTED — Race Condition
Nonce changed: was 42, now 43.
Another searcher burned before us. TokenJar balances have changed.
Returning to profitability analysis with fresh data...Present final result:
Step 5/5: Burn Complete
Burned: 4,000 UNI ($28,000)
Gas: $45
Received:
WETH 7.20 $18,000
USDC 15,000 $15,000
USDT 8,500 $8,500
WBTC 0.08 $6,400
DAI 4,100 $4,100
Gross Value: $52,000
Total Cost: $28,045
Net Profit: $23,955 (85.4% ROI)
Tx: https://etherscan.io/tx/0xabcd...1234
──────────────────────────────────────
Next Burn Estimate
──────────────────────────────────────
Accumulation Rate: ~$7,400/day
Est. Next Profitable Burn: ~3.8 daysIf post-burn-swap: true, append conversion details:
Post-Burn Conversions:
WETH → 17,950 USDC (0.28% slippage)
WBTC → 6,380 USDC (0.31% slippage)
USDT → 8,495 USDC (0.06% slippage)
DAI → 4,098 USDC (0.05% slippage)
Final USDC Balance: 51,923 USDC
Conversion Costs: $77
True Net Profit: $23,878 (after all costs)Protocol Fee Analysis
TokenJar Value: ${total_value} ({num_assets} assets)
┌──────────────────────────────────────┐
│ {token} {balance} ${value} ({%}) │
│ ... │
└──────────────────────────────────────┘
Burn Cost: ${uni_cost} ({threshold} UNI) + ${gas} gas = ${total_cost}
Net Profit: ${net_profit}
ROI: {roi}%
Verdict: {PROFITABLE | NOT_PROFITABLE | MARGINAL}
{if profitable: "Ready to execute. Say 'burn it' to proceed."}
{if not profitable: "Est. time to profitability: {days} days."}Protocol Fee Burn Complete
Burned: {threshold} UNI (${uni_cost})
Gas: ${gas_cost}
Received: {num_assets} assets worth ${gross_value}
Net Profit: ${net_profit} ({roi}% ROI)
Tx: {explorer_link}
Pipeline: Pre-flight -> Analysis -> Confirm -> Simulate -> Execute (all passed)chain parameter exists for forward compatibility but currently only ethereum is valid.| Error | User-Facing Message | Suggested Action |
|---|---|---|
| TokenJar empty | "TokenJar is empty. No fees to claim." | Wait for fees to accumulate |
| Insufficient UNI | "Insufficient UNI: have {X}, need {threshold}." | Acquire UNI or wait for price drop |
| Not profitable | "Burn is not profitable. Jar value ${X} < burn cost ${Y}." | Wait for more accumulation |
| Simulation failed | "Burn simulation failed: {reason}." | Check Firepit state, try again |
| Safety check failed | "Safety validation rejected the burn: {reason}." | Review safety configuration |
| Race condition | "Another searcher burned first. Nonce changed from {X} to {Y}." | Re-run to analyze with fresh data |
| Transaction reverted | "Burn transaction reverted: {reason}." | Check gas, nonce, and Firepit state |
| Wallet not configured | "No wallet configured. Cannot execute burns." | Set up wallet with setup-agent-wallet |
| Post-burn swap failed | "Burn succeeded but token conversion failed for {token}: {reason}." | Manually swap via execute-swap |
| Gas price spike | "Gas prices elevated (${gas}). Burn is marginally profitable." | Wait for lower gas or accept lower profit |
© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 2 other files in skills/seek-protocol-fees of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Seek Protocol Fees next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Seek Protocol Fees this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.5k | Automated safety check: Pass | MIT | |
| Claimsruvnet/ruflo | 74k | 1 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Optionsasgeirtj/system_prompts_leaks | 69k | — | ~918 | Automated safety check: Pass | CC0-1.0 | |
| Executealirezarezvani/claude-skills | 28k | — | ~831 | Automated safety check: Pass | MIT | |
| Debugging Executionsn8n-io/n8n | 207k | — | ~2.6k | Automated safety check: Pass | Custom licence | |
| Cost Burnruvnet/ruflo | 74k | — | ~824 | Automated safety check: Notes | MIT |
ruvnet/ruflo
Claims-based authorization for agents and operations. An agent skill from ruvnet/ruflo.
asgeirtj/system_prompts_leaks
Present multiple design options as a vertical stack of anchored turns
alirezarezvani/claude-skills
/cs:execute <decision — Generate a 90-day execution plan with weekly milestones, DRIs, and check-in cadence from an approved decision.
n8n-io/n8n
Debug failed or wrong-output workflow executions using executions tools.
ruvnet/ruflo
Burn-rate trend over time with optional drift-alert exit code.
code-yeongyu/oh-my-openagent
Executes a written ulw-plan work plan with Boulder state, evidence ledger, worktree discipline, and parallel subagents.
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Analyze TokenJar profitability and optionally execute a Firepit burn-and-claim. Seek Protocol Fees is an agent skill from LeoYeAI/openclaw-master-skills. Analyze TokenJar profitability and optionally execute a Firepit burn-and-claim.
Seek Protocol Fees fits situations like: user asks Is the TokenJar profitable?; claim protocol fees.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill seek-protocol-fees -a claude-code`. Or copy the skill folder (skills/seek-protocol-fees in LeoYeAI/openclaw-master-skills) into .claude/skills/seek-protocol-fees in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill seek-protocol-fees -a codex`. Or copy the skill folder (skills/seek-protocol-fees in LeoYeAI/openclaw-master-skills) into .agents/skills/seek-protocol-fees in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill seek-protocol-fees -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/seek-protocol-fees, .gemini/skills/seek-protocol-fees, .github/skills/seek-protocol-fees and .opencode/skills/seek-protocol-fees in your project.
SKILL.md names no scripts, command-line tools or credentials: Seek Protocol Fees is instructions for the agent only. Its frontmatter pre-approves these tools: Task(subagent_type:protocol-fee-seeker), Task(subagent_type:safety-guardian), mcp__uniswap__get_tokenjar_balances, mcp__uniswap__get_firepit_state, mcp__uniswap__get_agent_balance.
SKILL.md names 1 domain. In commands or code: etherscan.io; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Seek Protocol Fees is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.5k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Seek Protocol Fees: Claims (ruvnet/ruflo, 74k stars), Options (asgeirtj/system_prompts_leaks, 69k stars), Execute (alirezarezvani/claude-skills, 28k stars) and Debugging Executions (n8n-io/n8n, 207k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.