Startup Validator
ailabs-393/ai-labs-claude-skills
Comprehensive startup idea validation and market analysis tool.
Monitor Polymarket prediction markets, spot mispricings between crowd probabilities and real-world evidence, track whale positioning from the top-50 leaderboard wallets, and detect fresh wallet…
$ npx skills add LeoYeAI/openclaw-master-skills --skill pkedge -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills pkedge --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/pkedge .claude/skills/pkedge && 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 "pkedge" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/pkedge into .claude/skills/pkedge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pkedge", 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/pkedgeType 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 pkedge -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills pkedge --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/pkedge .agents/skills/pkedge && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "pkedge" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/pkedge into .agents/skills/pkedge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pkedge", 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 pkedge -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills pkedge --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/pkedge .cursor/skills/pkedge && 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 "pkedge" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/pkedge into .cursor/skills/pkedge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pkedge", 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/pkedge--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 pkedge -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills pkedge --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/pkedge .gemini/skills/pkedge && 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 "pkedge" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/pkedge into .gemini/skills/pkedge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pkedge", 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 pkedgeInstalls 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 pkedge -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/pkedge .github/skills/pkedge && 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 "pkedge" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/pkedge into .github/skills/pkedge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pkedge", 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 pkedge -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 pkedge --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/pkedge .opencode/skills/pkedge && 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 "pkedge" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/pkedge into .opencode/skills/pkedge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pkedge", 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.
pkedgeMonitor Polymarket prediction markets, spot mispricings between crowd probabilities and real-world evidence, track whale positioning from the top-50 leaderboard wallets, and detect fresh wallet…
Pkedge is an agent skill from LeoYeAI/openclaw-master-skills. Monitor Polymarket prediction markets, spot mispricings between crowd probabilities and real-world evidence, track whale positioning from the top-50 leaderboard wallets, and detect fresh wallet insider signals. Supports four modes: SCAN (daily digest of flagged markets), DEEP DIVE (full single-market analysis with web search evidence), WHALE WATCH (consensus detection across top trader positions), and INSIDER WATCH (fresh wallet large-position detection).
Its SKILL.md is about 4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `_meta.json`).
It sits in Marketing & SEO, covering Market research, Web search and Positioning and messaging. It works with Polymarket and Telegram. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
3 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.
Shell commands in SKILL.md call:
npmnodeFrom 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:
clob.polymarket.comgamma-api.polymarket.comdata-api.polymarket.comFrom 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.
Pkedge loads about 4k tokens when it runs. Until then it costs about 117 tokens; SKILL.md has 1,524 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.
2. Create a `.env` file with your Telegram credentials: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). 1,524 words, ~3,989 tokens.
.claude/skills/pkedge/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.PKEdge is an OpenClaw skill that monitors Polymarket prediction markets, spots mispricings between crowd probabilities and real-world evidence, tracks whale positioning from top-50 leaderboard wallets, and detects fresh wallet insider signals. It operates in four modes: SCAN, DEEP DIVE, WHALE WATCH, and INSIDER WATCH.
Intel only. Never recommends trading. Always appends "Not financial advice. DYOR."
Schedule:
cd into the skill folder and run npm install.env file with your Telegram credentials:PKEDGE_TELEGRAM_TOKEN_FREE — bot token for the free channelPKEDGE_TELEGRAM_CHAT_FREE — chat ID for the free channelPKEDGE_TELEGRAM_TOKEN_TRADER — bot token for the trader channelPKEDGE_TELEGRAM_CHAT_TRADER — chat ID for the trader channelnode cron.js to start scheduled jobs, or configure launchd to run on bootClaude activates this skill when the user says anything matching these patterns:
~/Projects/pkedge/
fetch.js — all Polymarket API calls (no auth required)
analyze.js — scoring, flagging, conviction logic
formatter.js — Telegram message templates
deliver.js — sends to Telegram channels
cron.js — scheduled runnerPurpose: Fetch the top 200 active Polymarket markets by volume, flag anomalies, rank them, deliver the digest.
Step-by-step:
Call fetchActiveMarkets() from fetch.js
Call runScanFlags(markets) from analyze.js
For the top 5 flagged markets, call web search on each question to check for recent news
"[market question]" news todayCall formatScanDigest(flaggedMarkets, 5) from formatter.js for Trader channel
Call formatScanPreview(flaggedMarkets[0]) from formatter.js for Free channel
Deliver via deliver.js sendToTrader() and sendToFree()
Output shape:
🔍 PKEdge Morning Scan — Mon, Mar 9, 2026
_5 markets flagged from top 200 by volume_
──────────────────────
1. *Will the Fed cut rates at the March 2026 meeting?*
🔥 HIGH Crowd: YES 23.1% | 24h Vol: $142K | Score: 7
👀 Volume spike: 4.2x average daily volume — unusual activity
⏰ Resolves in 3.2 days
...Purpose: Full analysis of a single market. Claude reasons over crowd probability vs. real-world evidence, assesses fair value, and outputs a structured Crowd vs. Reality report.
Step-by-step:
Parse the market question from the user input
Call searchMarkets(query) from fetch.js to find the matching Polymarket market
Fetch enriched market data:
fetchPriceHistory(market.id, '1d') — get price history with daily candles (note: '1d' sets candle granularity, not lookback window; the API returns available history for the market)fetchBookDepth(market.clobTokenIds[0]) — get order book depth (YES token)Call analyzeMarket(market, bookDepth) from analyze.js
Web search × 3 to gather evidence:
"[market question]" news [current month year][core topic] forecast prediction [current year][core topic] expert analysis probabilityEstimate fair value:
Call computeConviction(crowdPct, fairPct) from analyze.js
Call formatDeepDive(analysis, conviction, evidenceLines) from formatter.js
Deliver via sendToTrader() (Deep Dive is Trader-only)
Output shape:
🧠 PKEdge Deep Dive
_Mar 9, 2026_
──────────────────────
*Will the Fed cut rates at the March 2026 meeting?*
CROWD PRICE
YES: 23.1% | NO: 76.9%
MARKET DATA
⏰ Resolves in 3.2 days
💰 All-time: $2.1M | 24h: $142K
👀 Spread: 1.2¢ (bid 0.229 / ask 0.241)
✅ Order book: DEEP ($340K within 10¢)
EVIDENCE
✅ Fed funds futures pricing ~18% probability of March cut as of today
✅ Powell speech last week signaled patience — no urgency to cut
✅ February CPI came in at 2.9%, above 2% target
✅ No emergency FOMC meeting called — standard meeting format
✅ Metaculus consensus: 15-22% YES
──────────────────────
PKEDGE ASSESSMENT
🔥 Conviction: HIGH
Direction: NO underpriced
Delta: 18 percentage points from crowd
_Crowd is 18 pts away from fair value — strong signal_
`Not financial advice. DYOR. Prediction markets carry risk.`Purpose: Monitor top-50 Polymarket traders by all-time profit for new positions. Detect consensus (3+ whales entering the same market) and fire real-time alerts.
Runs twice daily:
Step-by-step:
Call fetchLeaderboard(50) from fetch.js
Extract all wallet addresses and call fetchMultiWalletPositions(addresses)
Call buildWhaleReport(leaderboard, walletPositions, windowHours) from analyze.js
48 as windowHours — covers overnight + weekend24 as windowHours — covers the trading dayCall formatWhaleWatch(report) from formatter.js
Deliver via sendToTrader()
For any consensus markets not yet alerted today:
formatWhaleAlert(consensusMarket, latestPosition) from formatter.jsOutput shape:
🐋 PKEdge Whale Watch — Mon, Mar 9, 2026
_Top 50 traders scanned | Last 24h_
──────────────────────
🔥 CONSENSUS DETECTED (1 market)
1. *Will the Fed cut rates at the March 2026 meeting?*
🐋x4 whales | 💰$48K combined | Direction: *NO*
_PredictWiz, 0x4f2a…1b3c, MarketMaker99 +1 more_
──────────────────────
NEW POSITIONS (6 total)
🐋 *PredictWiz* → NO
_Will the Fed cut rates at the March 2026 meeting?_
$22K @ 77¢ | 2h ago
...Purpose: Detect fresh wallets placing unusually large positions — a classic signal of informed trading. Insiders often create new wallets specifically to avoid leaderboard detection. Two or more fresh wallets entering the same market within 6 hours is treated as a coordinated signal.
Fresh wallet definition:
Alert tiers:
$5K single position = 👀 WATCH (held for digest)
$25K single position = ⚠️ ALERT (held for digest)
$50K single position = 🚨 IMMEDIATE (fires real-time, does not wait for digest)
Runs twice daily:
Step-by-step:
Call fetchActiveMarkets() — sort by 24h volume, take top 30 as scan targets
Call fetchLeaderboard(50) — build a Set of known addresses to exclude
For each top market, call fetchRecentTrades(market.clobTokenIds[0], windowHours) from fetch.js
For each unknown address with a qualifying trade, call fetchWalletProfile(address) from fetch.js
Call buildInsiderReport(freshSignals, windowHours) from analyze.js
Call formatInsiderWatch(report) from formatter.js
Deliver via sendToTrader()
For IMMEDIATE-tier (>$50K) or COORDINATED signals not yet alerted today:
formatInsiderAlert(signal, isCoordinated) from formatter.jsOutput shape — daily digest:
🕵️ PKEdge Insider Watch — Mon, Mar 9, 2026
_Unknown wallets scanned | Last 24h_
──────────────────────
🚨 COORDINATED SIGNAL (1 market)
*Will the Fed cut rates at the March 2026 meeting?*
🆕x2 fresh wallets | 💰$61K combined | Direction: *NO*
_First two entered within 2h of each other_
Wallet: 0x7c3b…9a12 — Age: 4 days | 3 trades | $38K → NO
Wallet: 0x2d1f…4e87 — Age: 11 days | 7 trades | $23K → NO
──────────────────────
WATCH LIST (3 signals)
👀 *Fresh wallet — 0x9f4a…2c31*
_Will Trump win the 2026 midterms?_
$8K → YES @ 41¢ | 6h ago
Age: 18 days | 12 trades lifetime
`Not financial advice. DYOR. Fresh wallet signals are circumstantial.`Output shape — real-time alert:
🚨 PKEdge Insider Alert
_Fresh wallet just dropped big money_
*Will the Fed cut rates at the March 2026 meeting?*
Direction: NO | Size: $38K @ 77¢
Wallet: `0x7c3b…9a12`
Age: 4 days | 3 trades lifetime
`Not financial advice. DYOR. Circumstantial signal only.`| Endpoint | Purpose |
|---|---|
GET https://gamma-api.polymarket.com/markets?active=true&limit=200 | Market discovery |
GET https://gamma-api.polymarket.com/markets?slug={slug} | Single market by slug |
GET https://gamma-api.polymarket.com/prices-history?market={id}&interval=1d | Price history |
GET https://clob.polymarket.com/book?token_id={tokenId} | Order book |
GET https://clob.polymarket.com/midpoint?token_id={tokenId} | Midpoint price |
GET https://clob.polymarket.com/bbo?token_id={tokenId} | Best bid/offer |
GET https://clob.polymarket.com/trades?token_id={tokenId}&limit=500 | Recent market trades (Insider Watch) |
GET https://data-api.polymarket.com/v1/leaderboard?timePeriod=ALL&orderBy=PNL&limit=50 | Top traders |
GET https://data-api.polymarket.com/positions?user={address} | Wallet positions |
GET https://data-api.polymarket.com/trades?user={address}&limit=500 | Wallet trade history + profile |
PKEDGE_TELEGRAM_TOKEN_FREE=
PKEDGE_TELEGRAM_CHAT_FREE=
PKEDGE_TELEGRAM_TOKEN_TRADER=
PKEDGE_TELEGRAM_CHAT_TRADER=No market data API keys needed. Polymarket APIs are fully public.
| Tier | Price | What They Get |
|---|---|---|
| FREE EDGE | $0 | 1 market preview from daily SCAN |
| WATCHER | $9/mo | Full 5-market SCAN digest, @PKEdgeBot basic (3 lookups/day) |
| TRADER | $29/mo | Unlimited DEEP DIVE, WHALE WATCH, INSIDER WATCH, all real-time alerts |
| QUANT | $99/mo | Raw scoring API, Discord quant channel, historical accuracy log |
SCAN Score Flags:
| Flag | Points | Trigger |
|---|---|---|
| VOLUME_SPIKE | 3 | 24h volume >3× average daily |
| VOLUME_SURGE | 2 | >25% of all-time volume traded in last 24h |
| RESOLVING_SOON | 2 | Resolves within 7 days |
| SPREAD_ANOMALY | 1 | YES + NO gap >6¢ |
| EXTREME_LOW / HIGH | 1 | Price ≤10% or ≥90% on high volume |
Score thresholds: 2 = WATCH | 4 = ELEVATED | 6+ = HIGH
Conviction thresholds: <7 pts = LOW | 7-14 pts = MEDIUM | 15+ pts = HIGH
Insider Signal Score:
| Factor | Points |
|---|---|
| Position > $5K | 1 |
| Position > $25K | 3 |
| Position > $50K | 3 |
| Wallet age < 7 days | 3 |
| Wallet age 7–14 days | 2 |
| Wallet age 15–30 days | 1 |
| Trade count < 5 | 2 |
| Trade count 5–10 | 1 |
| Coordinated (2+ fresh wallets same market within 6h) | +5 bonus |
Insider alert thresholds: 3 = WATCH | 6 = ALERT | 9+ = COORDINATED / IMMEDIATE
Not financial advice. DYOR. Prediction markets carry risk.© 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 1 other file in skills/pkedge of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Pkedge 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 |
|---|---|---|---|---|---|---|
| Pkedge this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~4k | Automated safety check: Notes | MIT | |
| Startup Validatorailabs-393/ai-labs-claude-skills | 455 | 1 repos | ~2.8k | Automated safety check: Pass | MIT | |
| Omk ResearchKaimingWan/oh-my-kiro | 107 | — | ~827 | Automated safety check: Pass | MIT | |
| Competitor Intelgooseworks-ai/goose-skills | 1.2k | 1 repos | ~1.8k | Automated safety check: Pass | MIT | |
| Marketing OsYuzzyuk/marketing-os | 540 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Startup Designferdinandobons/startup-skill | 1.2k | — | ~8.1k | Automated safety check: Pass | MIT |
ailabs-393/ai-labs-claude-skills
Comprehensive startup idea validation and market analysis tool.
KaimingWan/oh-my-kiro
Multi-level research: built-in knowledge → web search → Tavily deep research API.
gooseworks-ai/goose-skills
Competitor intelligence system. An agent skill from gooseworks-ai/goose-skills.
Yuzzyuk/marketing-os
A complete marketing department in one skill. An agent skill from Yuzzyuk/marketing-os.
ferdinandobons/startup-skill
Design, validate, and plan a startup from scratch. An agent skill from ferdinandobons/startup-skill.
bear2u/my-skills
Use the user's already signed-in official ChatGPT website account, especially GPT-5.5 Pro / ChatGPT Pro, to perform product research, market research, competitor research, second-opinion research…
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.
Works with
Categories
Monitor Polymarket prediction markets, spot mispricings between crowd probabilities and real-world evidence, track whale positioning from the top-50 leaderboard wallets, and detect fresh wallet…. Pkedge is an agent skill from LeoYeAI/openclaw-master-skills. Monitor Polymarket prediction markets, spot mispricings between crowd probabilities and real-world evidence, track whale positioning from the top-50 leaderboard wallets, and detect fresh wallet insider signals.
Pkedge fits situations like: tasks that involve Market research; tasks that involve Web search; tasks that involve Positioning and messaging.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill pkedge -a claude-code`. Or copy the skill folder (skills/pkedge in LeoYeAI/openclaw-master-skills) into .claude/skills/pkedge in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill pkedge -a codex`. Or copy the skill folder (skills/pkedge in LeoYeAI/openclaw-master-skills) into .agents/skills/pkedge 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 pkedge -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pkedge, .gemini/skills/pkedge, .github/skills/pkedge and .opencode/skills/pkedge in your project.
Going by SKILL.md and its folder, Pkedge needs the command-line tools its instructions call (npm and node). Our summary lists: Node.js.
SKILL.md names 3 domains. In commands or code: clob.polymarket.com, gamma-api.polymarket.com and data-api.polymarket.com; the agent is likely to contact these when it follows the instructions. 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. Review the folder before installing.
Pkedge is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 4k 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 Pkedge: Startup Validator (ailabs-393/ai-labs-claude-skills, 455 stars), Omk Research (KaimingWan/oh-my-kiro, 107 stars), Competitor Intel (gooseworks-ai/goose-skills, 1.2k stars) and Marketing Os (Yuzzyuk/marketing-os, 540 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.