{ "schemaVersion": "1.0", "item": { "slug": "claw-screener", "name": "Claw Screener", "source": "tencent", "type": "skill", "category": "数据分析", "sourceUrl": "https://clawhub.ai/rsoutar/claw-screener", "canonicalUrl": "https://clawhub.ai/rsoutar/claw-screener", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/claw-screener", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=claw-screener", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "package-lock.json", "package.json", "scripts/set.txt", "src/analyze.ts" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/claw-screener" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/claw-screener", "agentPageUrl": "https://openagent3.xyz/skills/claw-screener/agent", "manifestUrl": "https://openagent3.xyz/skills/claw-screener/agent.json", "briefUrl": "https://openagent3.xyz/skills/claw-screener/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Claw-Screener", "body": "A stock screener that combines technical analysis (Williams %R oversold signals) with Warren Buffett-style fundamental analysis using SEC data. Supports US (S&P 500) and Thai (SET) markets." }, { "title": "When to Use This Skill", "body": "Use this skill when you need to:\n\nFind oversold stocks with strong fundamentals\nScreen for quality stocks using Buffett's 10 formulas\nScreen for long-term compounders using Carlson filters (ROIC, growth, buybacks)\nAnalyze individual stocks for investment decisions\nGet daily stock screening results in text, JSON, or Telegram format" }, { "title": "Tools", "body": "This skill provides the following capabilities:" }, { "title": "1. Combined Screening", "body": "Finds stocks that are both technically oversold (Williams %R < -80) and fundamentally strong (Buffett score >= threshold).\n\nCommand:\n\nbun run src/screening.ts [options]\n\nOptions:\n\nFlagDescriptionDefault--marketMarket: us or bkus--min-scoreMinimum Buffett score (0-10)5--top-nNumber of results to show10--formatOutput: text, json, telegramtext\n\nExamples:\n\nbun run src/screening.ts\nbun run src/screening.ts --market us --min-score 7 --top-n 5\nbun run src/screening.ts --market bk\nbun run src/screening.ts --format json\nbun run src/screening.ts --format telegram" }, { "title": "2. Technical Only Scan", "body": "Fast oversold scan using Williams %R indicator only. No SEC data required. Works for both US and Thai markets.\n\nCommand:\n\nbun run src/technicalOnly.ts [options]\n\nOptions:\n\nFlagDescriptionDefault--marketMarket: us or bkus--thresholdWilliams %R threshold-80--top-nNumber of results to show20--formatOutput: text, json, telegramtext\n\nExamples:\n\nbun run src/technicalOnly.ts\nbun run src/technicalOnly.ts --threshold -70 --top-n 50\nbun run src/technicalOnly.ts --market bk" }, { "title": "3. Analyze Stock", "body": "Deep analysis of a single stock using Buffett's 10 formulas.\n\nCommand:\n\nbun run src/analyze.ts [options]\n\nOptions:\n\nFlagDescriptionDefault--formatOutput: text, json, telegramtext\n\nExamples:\n\nbun run src/analyze.ts AAPL\nbun run src/analyze.ts MSFT --format telegram\nbun run src/analyze.ts GOOGL --format json\nbun run src/analyze.ts PTT.BK" }, { "title": "4. Compounding Machine", "body": "Screens for \"compounders\" using Carlson-style filters:\n\nRevenue and net income YoY trend strength\nROIC threshold (default >15%)\nShare count reduction over 3 years (buyback signal)\nOperating margin threshold (default >20%)\nIncludes current yield vs 5-year average and a simple 10-year DCF context\n\nCommand:\n\nbun run src/compoundingMachine.ts [options]\n\nOptions:\n\nFlagDescriptionDefault--marketMarket universe: us or bkus--tickersComma-separated tickers (overrides market universe)---max-tickersLimit universe sizeall--top-nNumber of passing stocks to show25--concurrencyParallel fetch workers4--formatOutput: text or jsontext--db-pathSQLite cache pathsec_cache.db--ttl-daysCache TTL in days7--min-roicROIC threshold (%)15--min-op-marginOperating margin threshold (%)20--min-buybackRequired 3Y share reduction (%)2--show-rejectedInclude failed tickers with reasons in outputoff\n\nExamples:\n\nbun run src/compoundingMachine.ts\nbun run src/compoundingMachine.ts --tickers AAPL,MSFT,NVDA --top-n 10\nbun run src/compoundingMachine.ts --format json --max-tickers 100\nbun run src/compoundingMachine.ts --tickers PLTR --show-rejected\n\nRuntime / Caching Notes:\n\nFirst uncached run on full US universe can take ~20-30+ minutes.\nThis is expected: each ticker requires multiple Yahoo fundamentals/quote requests and retry backoff for rate-limit resilience.\nSubsequent runs are much faster due to SQLite caching (sec_cache.db, TTL default 7 days).\nFor quick checks, run smaller scans first (for example --max-tickers 50 or specific --tickers).\n\nAgent Guidance for User Messaging:\n\nIf user runs full-universe Compounding Machine scan, explicitly warn that initial run may take ~20-30 minutes.\nSuggest quick-test alternatives while waiting:\n\nbun run src/compoundingMachine.ts --max-tickers 50\nbun run src/compoundingMachine.ts --tickers AAPL,MSFT,NVDA" }, { "title": "5. Watchlist Management", "body": "Track stocks you're interested in and get alerts when they become oversold or overbought.\n\nCommand:\n\nbun run src/watchList.ts [options]\n\nCommands:\n\nCommandDescriptionadd Add a stock to your watchlistremove Remove a stock from your watchlistlistShow all watched stocks\n\nOptions:\n\nFlagDescriptionDefault--market us|thMarket: us (US) or th (Thai)us--notes '...'Optional notes for the stock---alert-thresholdWilliams %R threshold for alerts-\n\nExamples:\n\nbun run src/watchList.ts add AAPL\nbun run src/watchList.ts add AAPL --market us --notes 'Big tech'\nbun run src/watchList.ts add PTT.BK --market th\nbun run src/watchList.ts remove AAPL\nbun run src/watchList.ts list\nbun run src/watchList.ts list --market us\n\nStorage: Watchlist is saved to ~/.claw-screener-watchlist.json" }, { "title": "Buffett's 10 Formulas", "body": "The fundamental analysis evaluates stocks against Warren Buffett's criteria:\n\n#FormulaTargetDescription1Cash Test> Total DebtCash covers all debt2Debt-to-Equity< 0.5Low leverage3Return on Equity> 15%Efficient use of capital4Current Ratio> 1.5Short-term liquidity5Operating Margin> 12%Operational efficiency6Asset Turnover> 0.5Asset efficiency7Interest Coverage> 3xAbility to pay interest8Earnings StabilityPositiveConsistent profitability9Free Cash Flow> 0Cash generation10Capital Allocation> 15% ROEManagement effectiveness\n\nScoring: Each passing formula earns 1 point. Maximum score: 10/10." }, { "title": "Technical Indicator", "body": "Williams %R (Williams Percent Range)\n\nRange: -100 to 0\nOversold: < -80 (potential buy signal)\nOverbought: > -20 (potential sell signal)" }, { "title": "Combined Score Formula", "body": "Combined score = (Technical Score × 0.3) + (Fundamental Score × 0.7)\n\nTechnical Score: (Williams %R + 100) / 100\nFundamental Score: (Buffett Score / 10) × 100" }, { "title": "Data Sources", "body": "US Stocks: SEC EDGAR for fundamentals, Yahoo Finance for prices\nThai Stocks: Yahoo Finance only (no SEC data available)" }, { "title": "Runtime Requirements", "body": "Bun (>=1.3.1) - Required runtime for executing TypeScript scripts\nNode.js is NOT required as Bun provides all necessary runtime functionality" }, { "title": "Install Bun", "body": "If you don't have Bun installed, run:\n\n# macOS/Linux\ncurl -fsSL https://bun.sh/install | bash\n\n# Windows (PowerShell)\niwr https://bun.sh/install -outfile \"install.ps1\"; ./install.ps1" }, { "title": "Install Dependencies", "body": "bun install" }, { "title": "File Persistence", "body": "This skill creates and manages the following files:\n\nFileLocationPurposeTTLWatchlist~/.claw-screener-watchlist.jsonUser's stock watchlistPermanentSEC Cachesec_cache.dbCached SEC EDGAR financial data7 days (default)Price Cacheprice_cache.dbCached stock price data1 day (default)" }, { "title": "Cache Management", "body": "Cache files are automatically created on first run\nUse --ttl-days flag with compounding machine to adjust cache TTL\nCache files can be deleted to force fresh data fetch\nCache improves performance significantly on subsequent runs" }, { "title": "Notes", "body": "First run on full US universe can take ~20-30+ minutes (expected behavior)\nSubsequent runs are much faster due to caching\nFor quick tests, use --max-tickers 50 or specific --tickers" }, { "title": "Bun Scripts", "body": "bun run dev # Run screening (alias for bun run src/screening.ts)\nbun run screening # Run combined screening\nbun run technical # Run technical-only scan\nbun run analyze # Analyze a stock (requires ticker argument)\nbun run compounder # Run Compounding Machine screener\nbun run watchlist:add # Add stock to watchlist\nbun run watchlist:remove # Remove stock from watchlist\nbun run watchlist:list # List watched stocks" }, { "title": "Text (Default)", "body": "📊 Combined Quality Screening (US (S&P 500))\nTechnical: Oversold signals (Williams %R < -80)\nFundamental: Warren Buffett's 10 formulas on SEC data\nMinimum Buffett Score: 5/10\n\nResults:\n Total Scanned: 503\n Oversold Found: 42\n Quality Stocks: 8 (Buffett ≥5/10)\n\nTop 10 Opportunities:\n\n1. AAPL — Combined: 85.2% | Buffett: 8/10 | WR: -82.3\n2. MSFT — Combined: 79.1% | Buffett: 7/10 | WR: -85.1" }, { "title": "Telegram", "body": "📊 Combined Quality Screening (US (S&P 500))\nScanned: 503 stocks\nOversold: 42\nQuality (Buffett ≥5/10): 8\n\n🌟 Top 10 Quality Opportunities:\n\n1. **AAPL** — Combined: 85% | Buffett: 8/10 | WR: -82.3\n2. **MSFT** — Combined: 79% | Buffett: 7/10 | WR: -85.1" } ], "body": "Claw-Screener\n\nA stock screener that combines technical analysis (Williams %R oversold signals) with Warren Buffett-style fundamental analysis using SEC data. Supports US (S&P 500) and Thai (SET) markets.\n\nWhen to Use This Skill\n\nUse this skill when you need to:\n\nFind oversold stocks with strong fundamentals\nScreen for quality stocks using Buffett's 10 formulas\nScreen for long-term compounders using Carlson filters (ROIC, growth, buybacks)\nAnalyze individual stocks for investment decisions\nGet daily stock screening results in text, JSON, or Telegram format\nTools\n\nThis skill provides the following capabilities:\n\n1. Combined Screening\n\nFinds stocks that are both technically oversold (Williams %R < -80) and fundamentally strong (Buffett score >= threshold).\n\nCommand:\n\nbun run src/screening.ts [options]\n\n\nOptions:\n\nFlag\tDescription\tDefault\n--market\tMarket: us or bk\tus\n--min-score\tMinimum Buffett score (0-10)\t5\n--top-n\tNumber of results to show\t10\n--format\tOutput: text, json, telegram\ttext\n\nExamples:\n\nbun run src/screening.ts\nbun run src/screening.ts --market us --min-score 7 --top-n 5\nbun run src/screening.ts --market bk\nbun run src/screening.ts --format json\nbun run src/screening.ts --format telegram\n\n2. Technical Only Scan\n\nFast oversold scan using Williams %R indicator only. No SEC data required. Works for both US and Thai markets.\n\nCommand:\n\nbun run src/technicalOnly.ts [options]\n\n\nOptions:\n\nFlag\tDescription\tDefault\n--market\tMarket: us or bk\tus\n--threshold\tWilliams %R threshold\t-80\n--top-n\tNumber of results to show\t20\n--format\tOutput: text, json, telegram\ttext\n\nExamples:\n\nbun run src/technicalOnly.ts\nbun run src/technicalOnly.ts --threshold -70 --top-n 50\nbun run src/technicalOnly.ts --market bk\n\n3. Analyze Stock\n\nDeep analysis of a single stock using Buffett's 10 formulas.\n\nCommand:\n\nbun run src/analyze.ts [options]\n\n\nOptions:\n\nFlag\tDescription\tDefault\n--format\tOutput: text, json, telegram\ttext\n\nExamples:\n\nbun run src/analyze.ts AAPL\nbun run src/analyze.ts MSFT --format telegram\nbun run src/analyze.ts GOOGL --format json\nbun run src/analyze.ts PTT.BK\n\n4. Compounding Machine\n\nScreens for \"compounders\" using Carlson-style filters:\n\nRevenue and net income YoY trend strength\nROIC threshold (default >15%)\nShare count reduction over 3 years (buyback signal)\nOperating margin threshold (default >20%)\nIncludes current yield vs 5-year average and a simple 10-year DCF context\n\nCommand:\n\nbun run src/compoundingMachine.ts [options]\n\n\nOptions:\n\nFlag\tDescription\tDefault\n--market\tMarket universe: us or bk\tus\n--tickers\tComma-separated tickers (overrides market universe)\t-\n--max-tickers\tLimit universe size\tall\n--top-n\tNumber of passing stocks to show\t25\n--concurrency\tParallel fetch workers\t4\n--format\tOutput: text or json\ttext\n--db-path\tSQLite cache path\tsec_cache.db\n--ttl-days\tCache TTL in days\t7\n--min-roic\tROIC threshold (%)\t15\n--min-op-margin\tOperating margin threshold (%)\t20\n--min-buyback\tRequired 3Y share reduction (%)\t2\n--show-rejected\tInclude failed tickers with reasons in output\toff\n\nExamples:\n\nbun run src/compoundingMachine.ts\nbun run src/compoundingMachine.ts --tickers AAPL,MSFT,NVDA --top-n 10\nbun run src/compoundingMachine.ts --format json --max-tickers 100\nbun run src/compoundingMachine.ts --tickers PLTR --show-rejected\n\n\nRuntime / Caching Notes:\n\nFirst uncached run on full US universe can take ~20-30+ minutes.\nThis is expected: each ticker requires multiple Yahoo fundamentals/quote requests and retry backoff for rate-limit resilience.\nSubsequent runs are much faster due to SQLite caching (sec_cache.db, TTL default 7 days).\nFor quick checks, run smaller scans first (for example --max-tickers 50 or specific --tickers).\n\nAgent Guidance for User Messaging:\n\nIf user runs full-universe Compounding Machine scan, explicitly warn that initial run may take ~20-30 minutes.\nSuggest quick-test alternatives while waiting:\nbun run src/compoundingMachine.ts --max-tickers 50\nbun run src/compoundingMachine.ts --tickers AAPL,MSFT,NVDA\n5. Watchlist Management\n\nTrack stocks you're interested in and get alerts when they become oversold or overbought.\n\nCommand:\n\nbun run src/watchList.ts [options]\n\n\nCommands:\n\nCommand\tDescription\nadd \tAdd a stock to your watchlist\nremove \tRemove a stock from your watchlist\nlist\tShow all watched stocks\n\nOptions:\n\nFlag\tDescription\tDefault\n--market us|th\tMarket: us (US) or th (Thai)\tus\n--notes '...'\tOptional notes for the stock\t-\n--alert-threshold\tWilliams %R threshold for alerts\t-\n\nExamples:\n\nbun run src/watchList.ts add AAPL\nbun run src/watchList.ts add AAPL --market us --notes 'Big tech'\nbun run src/watchList.ts add PTT.BK --market th\nbun run src/watchList.ts remove AAPL\nbun run src/watchList.ts list\nbun run src/watchList.ts list --market us\n\n\nStorage: Watchlist is saved to ~/.claw-screener-watchlist.json\n\nBuffett's 10 Formulas\n\nThe fundamental analysis evaluates stocks against Warren Buffett's criteria:\n\n#\tFormula\tTarget\tDescription\n1\tCash Test\t> Total Debt\tCash covers all debt\n2\tDebt-to-Equity\t< 0.5\tLow leverage\n3\tReturn on Equity\t> 15%\tEfficient use of capital\n4\tCurrent Ratio\t> 1.5\tShort-term liquidity\n5\tOperating Margin\t> 12%\tOperational efficiency\n6\tAsset Turnover\t> 0.5\tAsset efficiency\n7\tInterest Coverage\t> 3x\tAbility to pay interest\n8\tEarnings Stability\tPositive\tConsistent profitability\n9\tFree Cash Flow\t> 0\tCash generation\n10\tCapital Allocation\t> 15% ROE\tManagement effectiveness\n\nScoring: Each passing formula earns 1 point. Maximum score: 10/10.\n\nTechnical Indicator\n\nWilliams %R (Williams Percent Range)\n\nRange: -100 to 0\nOversold: < -80 (potential buy signal)\nOverbought: > -20 (potential sell signal)\nCombined Score Formula\n\nCombined score = (Technical Score × 0.3) + (Fundamental Score × 0.7)\n\nTechnical Score: (Williams %R + 100) / 100\nFundamental Score: (Buffett Score / 10) × 100\nData Sources\nUS Stocks: SEC EDGAR for fundamentals, Yahoo Finance for prices\nThai Stocks: Yahoo Finance only (no SEC data available)\nInstallation\nRuntime Requirements\nBun (>=1.3.1) - Required runtime for executing TypeScript scripts\nNode.js is NOT required as Bun provides all necessary runtime functionality\nInstall Bun\n\nIf you don't have Bun installed, run:\n\n# macOS/Linux\ncurl -fsSL https://bun.sh/install | bash\n\n# Windows (PowerShell)\niwr https://bun.sh/install -outfile \"install.ps1\"; ./install.ps1\n\nInstall Dependencies\nbun install\n\nFile Persistence\n\nThis skill creates and manages the following files:\n\nFile\tLocation\tPurpose\tTTL\nWatchlist\t~/.claw-screener-watchlist.json\tUser's stock watchlist\tPermanent\nSEC Cache\tsec_cache.db\tCached SEC EDGAR financial data\t7 days (default)\nPrice Cache\tprice_cache.db\tCached stock price data\t1 day (default)\nCache Management\nCache files are automatically created on first run\nUse --ttl-days flag with compounding machine to adjust cache TTL\nCache files can be deleted to force fresh data fetch\nCache improves performance significantly on subsequent runs\nNotes\nFirst run on full US universe can take ~20-30+ minutes (expected behavior)\nSubsequent runs are much faster due to caching\nFor quick tests, use --max-tickers 50 or specific --tickers\nBun Scripts\nbun run dev # Run screening (alias for bun run src/screening.ts)\nbun run screening # Run combined screening\nbun run technical # Run technical-only scan\nbun run analyze # Analyze a stock (requires ticker argument)\nbun run compounder # Run Compounding Machine screener\nbun run watchlist:add # Add stock to watchlist\nbun run watchlist:remove # Remove stock from watchlist\nbun run watchlist:list # List watched stocks\n\nOutput Format Examples\nText (Default)\n📊 Combined Quality Screening (US (S&P 500))\nTechnical: Oversold signals (Williams %R < -80)\nFundamental: Warren Buffett's 10 formulas on SEC data\nMinimum Buffett Score: 5/10\n\nResults:\n Total Scanned: 503\n Oversold Found: 42\n Quality Stocks: 8 (Buffett ≥5/10)\n\nTop 10 Opportunities:\n\n1. AAPL — Combined: 85.2% | Buffett: 8/10 | WR: -82.3\n2. MSFT — Combined: 79.1% | Buffett: 7/10 | WR: -85.1\n\nTelegram\n📊 Combined Quality Screening (US (S&P 500))\nScanned: 503 stocks\nOversold: 42\nQuality (Buffett ≥5/10): 8\n\n🌟 Top 10 Quality Opportunities:\n\n1. **AAPL** — Combined: 85% | Buffett: 8/10 | WR: -82.3\n2. **MSFT** — Combined: 79% | Buffett: 7/10 | WR: -85.1" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/rsoutar/claw-screener", "publisherUrl": "https://clawhub.ai/rsoutar/claw-screener", "owner": "rsoutar", "version": "1.0.3", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/claw-screener", "downloadUrl": "https://openagent3.xyz/downloads/claw-screener", "agentUrl": "https://openagent3.xyz/skills/claw-screener/agent", "manifestUrl": "https://openagent3.xyz/skills/claw-screener/agent.json", "briefUrl": "https://openagent3.xyz/skills/claw-screener/agent.md" } }