Prediction Market Risk Review
affaan-m/ECC
Review prediction-market, basket, oracle, and trading-agent workflows for compliance, safety, data-quality, privacy, and execution risk.
Trade on prediction markets. An agent skill from LeoYeAI/openclaw-master-skills.
$ npx skills add LeoYeAI/openclaw-master-skills --skill precog -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills precog --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/opencog .claude/skills/precog && 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 "precog" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/opencog into .claude/skills/precog/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "precog", 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/opencogType 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 precog -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills precog --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/opencog .agents/skills/precog && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "precog" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/opencog into .agents/skills/precog/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "precog", 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 precog -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills precog --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/opencog .cursor/skills/precog && 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 "precog" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/opencog into .cursor/skills/precog/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "precog", 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/opencog--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 precog -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills precog --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/opencog .gemini/skills/precog && 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 "precog" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/opencog into .gemini/skills/precog/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "precog", 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 precogInstalls 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 precog -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/opencog .github/skills/precog && 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 "precog" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/opencog into .github/skills/precog/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "precog", 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 precog -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 precog --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/opencog .opencode/skills/precog && 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 "precog" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/opencog into .opencode/skills/precog/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "precog", 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.
precogTrade on prediction markets. An agent skill from LeoYeAI/openclaw-master-skills.
Precog is an agent skill from LeoYeAI/openclaw-master-skills. Trade on prediction markets. Create a local wallet, list markets, check prices, buy and sell outcome shares. Coming soon: create and fund markets directly from this skill.
Its SKILL.md is about 4.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 21 other files, including scripts (for example `LICENSE.md`, `PRECOG.md` and `README.md`).
The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
4 steps, taken from the first numbered list 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 nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 10 files in scripts/ (JavaScript, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
nodeFrom 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:
core.precog.marketsAlso links to:
matetoken.xyzFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
PRIVATE_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Precog loads about 4.1k tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 1,324 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 noted patterns worth knowing about, such as sudo or a known installer.
.mjs --generate and saved to ~/.openclaw/.env. Never transmitted over the network."- **`~/.openclaw/.env`** — created by `setup.mjs --generate`. Stores `PRIVATE_KEY` in plaintext. Treat it like a walletThe private key is saved to `~/.openclaw/.env` and **never printed**. Only the address is shown.enerated locally, stored in `~/.openclaw/.env`, never leaves the machine.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); the scripts in this folder are not scanned.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 1,324 words, ~4,086 tokens.
.claude/skills/precog/SKILL.md (or your agent's skills folder). This skill also uses 18 other files; get the full folder from GitHub.Precog is a fully onchain prediction market protocol on Base. Anyone can create a market around a real-world question, fund it with liquidity, and trade outcome shares. Prices equal implied probabilities (0–1). Every action is a signed onchain transaction — no custody, no central party.
MATE is a non-monetary practice token (no real economic value). Markets denominated in MATE are safe to use for learning and experimentation. MATE can be claimed at matetoken.xyz.
What you can do here:
🚧 Coming soon: Native market creation — submit and fund new markets directly from this skill without visiting the web UI.
For full protocol documentation see PRECOG.md — it covers prediction markets 101, the LS-LMSR pricing curve, resolution via Reality.eth + Kleros, LP mechanics, MATE markets, and more.
Contract addresses and RPCs are built in — no config needed.
The default network is Base Sepolia (testnet). No flag needed for testnet — scripts connect to sepolia unless told otherwise.
Two networks are supported. Pass --network <name> to any script, or set PRECOG_NETWORK in your environment.
| Network | --network value | Chain | Contract |
|---|---|---|---|
| Base Sepolia (testnet) | sepolia ← default | Base Sepolia (84532) | 0x61ec71F1Fd37ecc20d695E83F3D68e82bEfe8443 |
| Base Mainnet | mainnet | Base (8453) | 0x00000000000c109080dfa976923384b97165a57a |
⚠️ Mainnet uses real funds. Before running any mainnet command, confirm the network with the user and show the contract address. Do NOT default to mainnet — always require an explicit
--network mainnetflag or aPRECOG_NETWORK=mainnetenv var set by the user.
~/.openclaw/.env — created by setup.mjs --generate. Stores PRIVATE_KEY in plaintext. Treat it like a wallet key file: restrict permissions (chmod 600) and back it up. Losing it means losing access to any funds in that wallet.PRECOG_RPC_URL, use only a trusted endpoint. An untrusted RPC can observe signed transaction contents (but cannot extract your private key from them).⚠️ Run scripts sequentially. Parallel transactions share a nonce and will collide on-chain — run one script at a time.
⚠️ Do NOT create batch or automation scripts. Each transaction must be confirmed by the user individually; automated chains of trades bypass the confirmation step and can cause unintended financial loss.
⚠️ Do NOT edit skill scripts. The scripts are audited as a unit; silent edits could introduce bugs or security issues. If you find a bug, report it to the user so it can be fixed upstream.
⚠️ Always show script output verbatim in a fenced code block. The output contains exact amounts, prices, and suggested parameters that will be used in the next command — reformatting or summarizing it risks losing or distorting those values.
⚠️ Always run
quotebeforebuyorsell. The quote shows the exact cost/proceeds and the safe--max/--minslippage bounds. Show the full output to the user and wait for explicit confirmation before executing the trade.⚠️ Never modify trade parameters. If a script fails, show the exact error and stop. Do not retry with a different share count or workaround — incorrect parameters can result in unintended trades. Token approval is handled automatically inside the scripts.
Check status or create a new wallet:
node {baseDir}/scripts/setup.mjs [--network sepolia|mainnet]
node {baseDir}/scripts/setup.mjs --generateThe private key is saved to ~/.openclaw/.env and never printed. Only the address is shown.
After generating, ask the user to fund the address with ETH (for gas) and the market's collateral token (for trading).
Example output (wallet exists and funded):
Wallet: 0x77Ffa97c2dcDA0FF6c9393281993962FA633d9E1
ETH: 0.004210 ✓
MATE: 81.2300 ✓Example output (wallet exists, no funds):
Wallet: 0x77Ffa97c2dcDA0FF6c9393281993962FA633d9E1
ETH: 0.000000 ⚠️ needs gas
MATE: 0.0000 (no funds)node {baseDir}/scripts/markets.mjs [--network sepolia|mainnet]
node {baseDir}/scripts/markets.mjs --all [--network sepolia|mainnet]Example output:
Active Markets (2)
[4] Which AI model will be the top performer at the end of March?
📈 Claude 67.3% 💰 MATE 📅 Mar 31, 2026
[5] Will ETH hit $5k by Q2?
📈 YES 58.1% 💰 USDC 📅 Jun 30, 2026
When the user asks for more info / details about a specific market:
node {baseDir}/scripts/market.mjs --market <id> [--network sepolia|mainnet]Shows the title, category, status, end date, collateral, and all outcome probabilities ranked by price. After showing the output, ask the user: "Would you like to see the resolution criteria?" If they say yes:
node {baseDir}/scripts/market.mjs --market <id> --criteria [--network sepolia|mainnet]Example output (--market 4):
📊 Market 4 · AI / Leaderboard
Which AI model will be the top performer at the end of March?
🟢 Active 📅 Mar 31, 2026 💰 MATE
🥇 [1] Claude 16.3%
🥈 [2] Gemini 11.6%
🥉 [3] Grok 11.6%
[4] ChatGPT 11.6%
[5] Ernie 11.6%
[6] GLM 11.6%
[7] Kimi 11.6%
[8] Qwen 11.6%
[9] Other 11.6%
Example output (--market 4 --criteria):
📊 Market 4 · AI / Leaderboard
Which AI model will be the top performer at the end of March?
🟢 Active 📅 Mar 31, 2026 💰 MATE
🥇 [1] Claude 16.3%
🥈 [2] Gemini 11.6%
🥉 [3] Grok 11.6%
[4] ChatGPT 11.6%
[5] Ernie 11.6%
[6] GLM 11.6%
[7] Kimi 11.6%
[8] Qwen 11.6%
[9] Other 11.6%
📝 Resolution Criteria
This market will resolve based on the Text Arena AI Competition leaderboard
rankings at arena.ai as of March 31, 2026, 23:59:59 UTC.
Always run before buy or sell. Show the full output verbatim in a fenced code block. Ask the user to confirm before proceeding.
| What the user says | Flag to use | Example command |
|---|---|---|
| "buy N shares" | --shares N | --shares 50 |
| "spend $X" / "for $X" / "budget $X" | --cost X | --cost 50 |
| "reach X%" / "move to X%" / "push to X%" / "target X%" | --price 0.X | --price 0.25 |
| "use all my balance" / "all in" / "spend everything" | --all | --all |
Do NOT guess share counts manually. Use the correct flag — the script computes the exact answer.
node {baseDir}/scripts/quote.mjs --market <id> --outcome <n> --shares <amount> --buy [--network sepolia|mainnet]
node {baseDir}/scripts/quote.mjs --market <id> --outcome <n> --cost <usdc> --buy [--network sepolia|mainnet]
node {baseDir}/scripts/quote.mjs --market <id> --outcome <n> --price <0.0-1.0> --buy [--network sepolia|mainnet]
node {baseDir}/scripts/quote.mjs --market <id> --outcome <n> --all --buy [--network sepolia|mainnet]--outcome is 1-based (1 = first outcome, usually YES)--buy shows only the buy side; --sell shows only the sell side; omit both to show both sides--network — sepolia (default) or mainnet; must match the network used for the subsequent buy/sellExample output (--price 0.25 --buy):
📋 Quote — Market 4: Which AI model will be the top performer at the end of March?
─────────────────────────────────────────────────────────
🎯 Outcome : Claude
🔢 Shares : 312
📊 Current prob : 14.2%
🛒 Buy 312 shares
💵 Cost : ~98.4521 MATE
📏 Price / share : 0.3156 MATE
📈 Prob after buy : 25.0% (market moves up ↑)
🏆 Max return : 312.0000 MATE (+213.5479 profit if "Claude" wins)
⚡ Suggested --max for buy : 99.4366
─── Paste ALL lines above verbatim to the user before asking to confirm ───node {baseDir}/scripts/buy.mjs --market <id> --outcome <n> --shares <amount> --max <usdc> [--network sepolia|mainnet]--shares — number of shares (from the quote output)--max — maximum collateral to spend; use the Suggested --max value from the quote output--network — must match the network used in the preceding quote--max or --shares for allowance reasonsnode {baseDir}/scripts/sell.mjs --market <id> --outcome <n> --shares <amount> --min <usdc> [--network sepolia|mainnet]--shares — number of shares to sell (check positions.mjs if unsure)--min — minimum collateral to accept; use the Suggested --min value from the quote output--network — must match the network used in the preceding quotenode {baseDir}/scripts/positions.mjs --market <id> [--network sepolia|mainnet]Example output:
💼 Market 4
Which AI model will be the top performer at the end of March?
👛 0x77Ffa97c2dcDA0FF6c9393281993962FA633d9E1
💵 Net cost 19.03 MATE · 📥 8 buys 📤 7 sells
🎯 Shares held
🥇 [1] Claude 135 shares · 16.3%
When the user asks what they can do, what Precog is, or how to get started — answer in plain prose with emojis, no tables. Mention their current positions if you know them. Example:
With Precog you can trade on the probability of real-world outcomes using MATE (a safe practice token — no real money).
Here's what you can do:
🗂️ List markets — see what's open and the leading outcome for each 🔍 Market detail — outcomes, probabilities, category, and resolution criteria for a specific market 💸 Trade — quote first, then buy or sell outcome shares (by share count, budget, or target probability) 📋 Positions — see your shares, net cost, and trade history
You currently hold 100 Claude shares on Market 4. Want to check the latest prices or make a move?
Adapt the last line to whatever you actually know about the user's positions and active markets.
--network is omitted from these examples for brevity. Add it to every command when the user is on mainnet.
User: "What markets are open?"
→ node markets.mjs
User: "What mainnet markets are open?" / "Show me Base mainnet markets"
→ Confirm with the user: "This will connect to Base mainnet where real funds are used. Continue?"
→ node markets.mjs --network mainnet
User: "Tell me more about market 4" / "What are the outcomes on market 4?"
→ node market.mjs --market 4
→ After output, ask: "Would you like to see the resolution criteria?"
→ If yes: node market.mjs --market 4 --criteria
User: "What's my position on market 4?"
→ node positions.mjs --market 4
User: "Show all my positions" / "Do I have any shares?"
→ node markets.mjs --all (get list of all market IDs)
→ node positions.mjs --market <id> (repeat for each market)
User: "Use all my MATE to buy Claude on market 4"
→ node quote.mjs --market 4 --outcome 1 --all --buy
→ Paste full output verbatim. Ask: "Confirm buy?"
→ Wait for user to confirm
→ node buy.mjs --market 4 --outcome 1 --shares <n from quote> --max <suggested-max>
→ After trade: suggest checking positions or new market price
User: "Buy Claude for $50 on market 4"
→ node quote.mjs --market 4 --outcome 1 --cost 50 --buy
→ Paste full output verbatim. Ask: "Confirm buy?"
→ Wait for user to confirm
→ node buy.mjs --market 4 --outcome 1 --shares <n from quote> --max <suggested-max>
→ After trade: suggest checking positions or new market price
User: "Buy Claude to reach 25% on market 4"
→ node quote.mjs --market 4 --outcome 1 --price 0.25 --buy
→ Paste full output verbatim. Ask: "Confirm buy?"
→ Wait for user to confirm
→ node buy.mjs --market 4 --outcome 1 --shares <n from quote> --max <suggested-max>
→ After trade: suggest checking positions or new market price
User: "Sell my Claude shares on market 4"
→ node positions.mjs --market 4 (find share count)
→ node quote.mjs --market 4 --outcome 1 --shares <n> --sell
→ Paste full output verbatim. Ask: "Confirm sell?"
→ Wait for user to confirm
→ node sell.mjs --market 4 --outcome 1 --shares <n> --min <suggested-min>
→ After trade: suggest checking positions or remaining balance
User: "Create a market about X" / "Can you create a market for Y?"
→ Tell the user to go to https://core.precog.markets/84532/create-market
→ Explain briefly: log in with MetaMask, fill the form, submit for review
→ Remind them: after submission they need to fund the market at the launchpad
and wait for staff approval before it goes live
→ Do NOT attempt to automate this — no script can do it on this serverMarket creation must be done manually through the Precog web UI — no script can automate this from the server.
Steps:
0xC139C86de76DF41c041A30853C3958427fA7CEbD)After submission — two more steps required
⚠️ The market is NOT live yet after submitting the form.
Prerequisites
Features planned for future versions of this skill:
0x61ec71F1Fd37ecc20d695E83F3D68e82bEfe8443 (Base Sepolia, chain 84532)0x00000000000c109080dfa976923384b97165a57a (Base, chain 8453)sepolia. Pass --network mainnet or set PRECOG_NETWORK=mainnet for mainnet.PRECOG_RPC_URL to override (applies to whichever network is active).~/.openclaw/.env, never leaves the machine.© 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 18 other files (scripts) in skills/opencog of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Precog 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 |
|---|---|---|---|---|---|---|
| Precog this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.1k | Automated safety check: Notes | MIT | |
| Prediction Market Risk Reviewaffaan-m/ECC | 276k | 1 repos | ~471 | Automated safety check: Pass | MIT | |
| Prediction Market Oracle Researchaffaan-m/ECC | 276k | 1 repos | ~577 | Automated safety check: Pass | MIT | |
| Marketing Campaignaffaan-m/ECC | 276k | 1 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Market Researchalirezarezvani/claude-skills | 28k | — | ~2.6k | Automated safety check: Pass | MIT | |
| LLM Trading Agent Securityaffaan-m/ECC | 276k | 2 repos | ~1.2k | Automated safety check: Pass | MIT |
affaan-m/ECC
Review prediction-market, basket, oracle, and trading-agent workflows for compliance, safety, data-quality, privacy, and execution risk.
affaan-m/ECC
Research prediction markets as data sources or oracle signals for products, agents, dashboards, and corporate decision intelligence.
affaan-m/ECC
End-to-end marketing campaign planning and execution. An agent skill from affaan-m/ECC.
alirezarezvani/claude-skills
A skill your agent uses when doing upstream market-research methodology — sizing a market as TAM/SAM/SOM computed BOTH top-down and bottoms-up (never a single unsourced number), planning a survey…
affaan-m/ECC
Security patterns for autonomous trading agents with wallet or transaction authority.
gooseworks-ai/goose-skills
Prediction markets data - Polymarket, Kalshi markets, prices, positions, and trades
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.
Trade on prediction markets. An agent skill from LeoYeAI/openclaw-master-skills. Precog is an agent skill from LeoYeAI/openclaw-master-skills. Trade on prediction markets.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill precog -a claude-code`. Or copy the skill folder (skills/opencog in LeoYeAI/openclaw-master-skills) into .claude/skills/precog in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill precog -a codex`. Or copy the skill folder (skills/opencog in LeoYeAI/openclaw-master-skills) into .agents/skills/precog 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 precog -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/precog, .gemini/skills/precog, .github/skills/precog and .opencode/skills/precog in your project.
Going by SKILL.md and its folder, Precog needs JavaScript for the scripts in its folder, the command-line tools its instructions call (node) and credentials named PRIVATE_KEY. Our summary lists: Node.js; A credential in PRIVATE_KEY.
SKILL.md names 2 domains. In commands or code: core.precog.markets; the agent is likely to contact it when it follows the instructions. As links in the text: matetoken.xyz. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Precog is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.1k tokens (SKILL.md is roughly 16k 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 Precog: Prediction Market Risk Review (affaan-m/ECC, 276k stars), Prediction Market Oracle Research (affaan-m/ECC, 276k stars), Marketing Campaign (affaan-m/ECC, 276k stars) and Market Research (alirezarezvani/claude-skills, 28k 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 2,160 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.