[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M748DFJAS9RBDH7Q09FHVC8M":3,"skill-same:01M748DFJAS9RBDH7Q09FHVC8M":74},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M748DFJAS9RBDH7Q09FHVC8M","backtest-expert",null,"Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers \"beating ideas to death\" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.","mphinance\u002Falpha-skills","mphinance","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F217996678?v=4","01M71VQC89A6CMFACD2J1CJW6E","Michael H","01M71VQC9B4C0BJ7XXKT8RWRV9",32,"MIT","https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbacktest-expert\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: backtest-expert\ndescription: Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers \"beating ideas to death\" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.\n---\n\n# Backtest Expert\n\nSystematic approach to backtesting trading strategies based on professional methodology that prioritizes robustness over optimistic results.\n\n## Core Philosophy\n\n**Goal**: Find strategies that \"break the least\", not strategies that \"profit the most\" on paper.\n\n**Principle**: Add friction, stress test assumptions, and see what survives. If a strategy holds up under pessimistic conditions, it's more likely to work in live trading.\n\n## When to Use This Skill\n\nUse this skill when:\n- Developing or validating systematic trading strategies\n- Evaluating whether a trading idea is robust enough for live implementation\n- Troubleshooting why a backtest might be misleading\n- Learning proper backtesting methodology\n- Avoiding common pitfalls (curve-fitting, look-ahead bias, survivorship bias)\n- Assessing parameter sensitivity and regime dependence\n- Setting realistic expectations for slippage and execution costs\n\n## Prerequisites\n\n- Python 3.9+ (for evaluation script)\n- No API keys required\n- No external data dependencies — metrics are user-provided\n\n## Workflow\n\n### 1. State the Hypothesis\n\nDefine the edge in one sentence.\n\n**Example**: \"Stocks that gap up >3% on earnings and pull back to previous day's close within first hour provide mean-reversion opportunity.\"\n\nIf you can't articulate the edge clearly, don't proceed to testing.\n\n### 2. Codify Rules with Zero Discretion\n\nDefine with complete specificity:\n- **Entry**: Exact conditions, timing, price type\n- **Exit**: Stop loss, profit target, time-based exit\n- **Position sizing**: Fixed $$, % of portfolio, volatility-adjusted\n- **Filters**: Market cap, volume, sector, volatility conditions\n- **Universe**: What instruments are eligible\n\n**Critical**: No subjective judgment allowed. Every decision must be rule-based and unambiguous.\n\n### 3. Run Initial Backtest\n\nTest over:\n- **Minimum 5 years** (preferably 10+)\n- **Multiple market regimes** (bull, bear, high\u002Flow volatility)\n- **Realistic costs**: Commissions + conservative slippage\n\nExamine initial results for basic viability. If fundamentally broken, iterate on hypothesis.\n\n### 4. Stress Test the Strategy\n\nThis is where 80% of testing time should be spent.\n\n**Parameter sensitivity**:\n- Test stop loss at 50%, 75%, 100%, 125%, 150% of baseline\n- Test profit target at 80%, 90%, 100%, 110%, 120% of baseline\n- Vary entry\u002Fexit timing by ±15-30 minutes\n- Look for \"plateaus\" of stable performance, not narrow spikes\n\n**Execution friction**:\n- Increase slippage to 1.5-2x typical estimates\n- Model worst-case fills (buy at ask+1 tick, sell at bid-1 tick)\n- Add realistic order rejection scenarios\n- Test with pessimistic commission structures\n\n**Time robustness**:\n- Analyze year-by-year performance\n- Require positive expectancy in majority of years\n- Ensure strategy doesn't rely on 1-2 exceptional periods\n- Test in different market regimes separately\n\n**Sample size**:\n- Absolute minimum: 30 trades\n- Preferred: 100+ trades\n- High confidence: 200+ trades\n\n### 5. Out-of-Sample Validation\n\n**Walk-forward analysis**:\n1. Optimize on training period (e.g., Year 1-3)\n2. Test on validation period (Year 4)\n3. Roll forward and repeat\n4. Compare in-sample vs out-of-sample performance\n\n**Warning signs**:\n- Out-of-sample \u003C50% of in-sample performance\n- Need frequent parameter re-optimization\n- Parameters change dramatically between periods\n\n### 6. Evaluate Results\n\n**Questions to answer**:\n- Does edge survive pessimistic assumptions?\n- Is performance stable across parameter variations?\n- Does strategy work in multiple market regimes?\n- Is sample size sufficient for statistical confidence?\n- Are results realistic, not \"too good to be true\"?\n\n**Decision criteria**:\n- ✅ **Deploy**: Survives all stress tests with acceptable performance\n- 🔄 **Refine**: Core logic sound but needs parameter adjustment\n- ❌ **Abandon**: Fails stress tests or relies on fragile assumptions\n\nUse the evaluation script for a structured, quantitative assessment:\n\n```bash\npython3 skills\u002Fbacktest-expert\u002Fscripts\u002Fevaluate_backtest.py \\\n  --total-trades 150 \\\n  --win-rate 62 \\\n  --avg-win-pct 1.8 \\\n  --avg-loss-pct 1.2 \\\n  --max-drawdown-pct 15 \\\n  --years-tested 8 \\\n  --num-parameters 3 \\\n  --slippage-tested \\\n  --output-dir reports\u002F\n```\n\nThe script scores across 5 dimensions (Sample Size, Expectancy, Risk Management, Robustness, Execution Realism), detects red flags, and outputs a Deploy\u002FRefine\u002FAbandon verdict.\n\n## Key Testing Principles\n\n### Punish the Strategy\n\nAdd friction everywhere:\n- Commissions higher than reality\n- Slippage 1.5-2x typical\n- Worst-case fills\n- Order rejections\n- Partial fills\n\n**Rationale**: Strategies that survive pessimistic assumptions often outperform in live trading.\n\n### Seek Plateaus, Not Peaks\n\nLook for parameter ranges where performance is stable, not optimal values that create performance spikes.\n\n**Good**: Strategy profitable with stop loss anywhere from 1.5% to 3.0%\n**Bad**: Strategy only works with stop loss at exactly 2.13%\n\nStable performance indicates genuine edge; narrow optima suggest curve-fitting.\n\n### Test All Cases, Not Cherry-Picked Examples\n\n**Wrong approach**: Study hand-picked \"market leaders\" that worked\n**Right approach**: Test every stock that met criteria, including those that failed\n\nSelective examples create survivorship bias and overestimate strategy quality.\n\n### Separate Idea Generation from Validation\n\n**Intuition**: Useful for generating hypotheses\n**Validation**: Must be purely data-driven\n\nNever let attachment to an idea influence interpretation of test results.\n\n## Common Failure Patterns\n\nRecognize these patterns early to save time:\n\n1. **Parameter sensitivity**: Only works with exact parameter values\n2. **Regime-specific**: Great in some years, terrible in others\n3. **Slippage sensitivity**: Unprofitable when realistic costs added\n4. **Small sample**: Too few trades for statistical confidence\n5. **Look-ahead bias**: \"Too good to be true\" results\n6. **Over-optimization**: Many parameters, poor out-of-sample results\n\nSee `references\u002Ffailed_tests.md` for detailed examples and diagnostic framework.\n\n## Output\n\n- `reports\u002Fbacktest_eval_\u003Ctimestamp>.json` — structured evaluation with per-dimension scores, red flags, and verdict\n- `reports\u002Fbacktest_eval_\u003Ctimestamp>.md` — human-readable report with dimension table, key metrics, and red flag details\n\n## Resources\n\n### Methodology Reference\n**File**: `references\u002Fmethodology.md`\n\n**When to read**: For detailed guidance on specific testing techniques.\n\n**Contents**:\n- Stress testing methods\n- Parameter sensitivity analysis\n- Slippage and friction modeling\n- Sample size requirements\n- Market regime classification\n- Common biases and pitfalls (survivorship, look-ahead, curve-fitting, etc.)\n\n### Failed Tests Reference\n**File**: `references\u002Ffailed_tests.md`\n\n**When to read**: When strategy fails tests, or learning from past mistakes.\n\n**Contents**:\n- Why failures are valuable\n- Common failure patterns with examples\n- Case study documentation framework\n- Red flags checklist for evaluating backtests\n\n## Critical Reminders\n\n**Time allocation**: Spend 20% generating ideas, 80% trying to break them.\n\n**Context-free requirement**: If strategy requires \"perfect context\" to work, it's not robust enough for systematic trading.\n\n**Red flag**: If backtest results look too good (>90% win rate, minimal drawdowns, perfect timing), audit carefully for look-ahead bias or data issues.\n\n**Tool limitations**: Understand your backtesting platform's quirks (interpolation methods, handling of low liquidity, data alignment issues).\n\n**Statistical significance**: Small edges require large sample sizes to prove. 5% edge per trade needs 100+ trades to distinguish from luck.\n\n## Discretionary vs Systematic Differences\n\nThis skill focuses on **systematic\u002Fquantitative** backtesting where:\n- All rules are codified in advance\n- No discretion or \"feel\" in execution\n- Testing happens on all historical examples, not cherry-picked cases\n- Context (news, macro) is deliberately stripped out\n\nDiscretionary traders study differently—this skill may not apply to setups requiring subjective judgment.\n","# Backtest Expert\n\nSystematic approach to backtesting trading strategies based on professional methodology that prioritizes robustness over optimistic results.\n\n## Core Philosophy\n\n**Goal**: Find strategies that \"break the least\", not strategies that \"profit the most\" on paper.\n\n**Principle**: Add friction, stress test assumptions, and see what survives. If a strategy holds up under pessimistic conditions, it's more likely to work in live trading.\n\n## When to Use This Skill\n\nUse this skill when:\n- Developing or validating systematic trading strategies\n- Evaluating whether a trading idea is robust enough for live implementation\n- Troubleshooting why a backtest might be misleading\n- Learning proper backtesting methodology\n- Avoiding common pitfalls (curve-fitting, look-ahead bias, survivorship bias)\n- Assessing parameter sensitivity and regime dependence\n- Setting realistic expectations for slippage and execution costs\n\n## Prerequisites\n\n- Python 3.9+ (for evaluation script)\n- No API keys required\n- No external data dependencies — metrics are user-provided\n\n## Workflow\n\n### 1. State the Hypothesis\n\nDefine the edge in one sentence.\n\n**Example**: \"Stocks that gap up >3% on earnings and pull back to previous day's close within first hour provide mean-reversion opportunity.\"\n\nIf you can't articulate the edge clearly, don't proceed to testing.\n\n### 2. Codify Rules with Zero Discretion\n\nDefine with complete specificity:\n- **Entry**: Exact conditions, timing, price type\n- **Exit**: Stop loss, profit target, time-based exit\n- **Position sizing**: Fixed $$, % of portfolio, volatility-adjusted\n- **Filters**: Market cap, volume, sector, volatility conditions\n- **Universe**: What instruments are eligible\n\n**Critical**: No subjective judgment allowed. Every decision must be rule-based and unambiguous.\n\n### 3. Run Initial Backtest\n\nTest over:\n- **Minimum 5 years** (preferably 10+)\n- **Multiple market regimes** (bull, bear, high\u002Flow volatility)\n- **Realistic costs**: Commissions + conservative slippage\n\nExamine initial results for basic viability. If fundamentally broken, iterate on hypothesis.\n\n### 4. Stress Test the Strategy\n\nThis is where 80% of testing time should be spent.\n\n**Parameter sensitivity**:\n- Test stop loss at 50%, 75%, 100%, 125%, 150% of baseline\n- Test profit target at 80%, 90%, 100%, 110%, 120% of baseline\n- Vary entry\u002Fexit timing by ±15-30 minutes\n- Look for \"plateaus\" of stable performance, not narrow spikes\n\n**Execution friction**:\n- Increase slippage to 1.5-2x typical estimates\n- Model worst-case fills (buy at ask+1 tick, sell at bid-1 tick)\n- Add realistic order rejection scenarios\n- Test with pessimistic commission structures\n\n**Time robustness**:\n- Analyze year-by-year performance\n- Require positive expectancy in majority of years\n- Ensure strategy doesn't rely on 1-2 exceptional periods\n- Test in different market regimes separately\n\n**Sample size**:\n- Absolute minimum: 30 trades\n- Preferred: 100+ trades\n- High confidence: 200+ trades\n\n### 5. Out-of-Sample Validation\n\n**Walk-forward analysis**:\n1. Optimize on training period (e.g., Year 1-3)\n2. Test on validation period (Year 4)\n3. Roll forward and repeat\n4. Compare in-sample vs out-of-sample performance\n\n**Warning signs**:\n- Out-of-sample \u003C50% of in-sample performance\n- Need frequent parameter re-optimization\n- Parameters change dramatically between periods\n\n### 6. Evaluate Results\n\n**Questions to answer**:\n- Does edge survive pessimistic assumptions?\n- Is performance stable across parameter variations?\n- Does strategy work in multiple market regimes?\n- Is sample size sufficient for statistical confidence?\n- Are results realistic, not \"too good to be true\"?\n\n**Decision criteria**:\n- ✅ **Deploy**: Survives all stress tests with acceptable performance\n- 🔄 **Refine**: Core logic sound but needs parameter adjustment\n- ❌ **Abandon**: Fails stress tests or relies on fragile assumptions\n\nUse the evaluation script for a structured, quantitative assessment:\n\n```bash\npython3 skills\u002Fbacktest-expert\u002Fscripts\u002Fevaluate_backtest.py \\\n  --total-trades 150 \\\n  --win-rate 62 \\\n  --avg-win-pct 1.8 \\\n  --avg-loss-pct 1.2 \\\n  --max-drawdown-pct 15 \\\n  --years-tested 8 \\\n  --num-parameters 3 \\\n  --slippage-tested \\\n  --output-dir reports\u002F\n```\n\nThe script scores across 5 dimensions (Sample Size, Expectancy, Risk Management, Robustness, Execution Realism), detects red flags, and outputs a Deploy\u002FRefine\u002FAbandon verdict.\n\n## Key Testing Principles\n\n### Punish the Strategy\n\nAdd friction everywhere:\n- Commissions higher than reality\n- Slippage 1.5-2x typical\n- Worst-case fills\n- Order rejections\n- Partial fills\n\n**Rationale**: Strategies that survive pessimistic assumptions often outperform in live trading.\n\n### Seek Plateaus, Not Peaks\n\nLook for parameter ranges where performance is stable, not optimal values that create performance spikes.\n\n**Good**: Strategy profitable with stop loss anywhere from 1.5% to 3.0%\n**Bad**: Strategy only works with stop loss at exactly 2.13%\n\nStable performance indicates genuine edge; narrow optima suggest curve-fitting.\n\n### Test All Cases, Not Cherry-Picked Examples\n\n**Wrong approach**: Study hand-picked \"market leaders\" that worked\n**Right approach**: Test every stock that met criteria, including those that failed\n\nSelective examples create survivorship bias and overestimate strategy quality.\n\n### Separate Idea Generation from Validation\n\n**Intuition**: Useful for generating hypotheses\n**Validation**: Must be purely data-driven\n\nNever let attachment to an idea influence interpretation of test results.\n\n## Common Failure Patterns\n\nRecognize these patterns early to save time:\n\n1. **Parameter sensitivity**: Only works with exact parameter values\n2. **Regime-specific**: Great in some years, terrible in others\n3. **Slippage sensitivity**: Unprofitable when realistic costs added\n4. **Small sample**: Too few trades for statistical confidence\n5. **Look-ahead bias**: \"Too good to be true\" results\n6. **Over-optimization**: Many parameters, poor out-of-sample results\n\nSee `references\u002Ffailed_tests.md` for detailed examples and diagnostic framework.\n\n## Output\n\n- `reports\u002Fbacktest_eval_\u003Ctimestamp>.json` — structured evaluation with per-dimension scores, red flags, and verdict\n- `reports\u002Fbacktest_eval_\u003Ctimestamp>.md` — human-readable report with dimension table, key metrics, and red flag details\n\n## Resources\n\n### Methodology Reference\n**File**: `references\u002Fmethodology.md`\n\n**When to read**: For detailed guidance on specific testing techniques.\n\n**Contents**:\n- Stress testing methods\n- Parameter sensitivity analysis\n- Slippage and friction modeling\n- Sample size requirements\n- Market regime classification\n- Common biases and pitfalls (survivorship, look-ahead, curve-fitting, etc.)\n\n### Failed Tests Reference\n**File**: `references\u002Ffailed_tests.md`\n\n**When to read**: When strategy fails tests, or learning from past mistakes.\n\n**Contents**:\n- Why failures are valuable\n- Common failure patterns with examples\n- Case study documentation framework\n- Red flags checklist for evaluating backtests\n\n## Critical Reminders\n\n**Time allocation**: Spend 20% generating ideas, 80% trying to break them.\n\n**Context-free requirement**: If strategy requires \"perfect context\" to work, it's not robust enough for systematic trading.\n\n**Red flag**: If backtest results look too good (>90% win rate, minimal drawdowns, perfect timing), audit carefully for look-ahead bias or data issues.\n\n**Tool limitations**: Understand your backtesting platform's quirks (interpolation methods, handling of low liquidity, data alignment issues).\n\n**Statistical significance**: Small edges require large sample sizes to prove. 5% edge per trade needs 100+ trades to distinguish from luck.\n\n## Discretionary vs Systematic Differences\n\nThis skill focuses on **systematic\u002Fquantitative** backtesting where:\n- All rules are codified in advance\n- No discretion or \"feel\" in execution\n- Testing happens on all historical examples, not cherry-picked cases\n- Context (news, macro) is deliberately stripped out\n\nDiscretionary traders study differently—this skill may not apply to setups requiring subjective judgment.\n",{"name":5,"description":7},"main","78b6ee6816aca6e5660cc7f0382650e9e7687086","skills\u002Fbacktest-expert",6,"https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills","https:\u002F\u002Fgithub.com\u002Fmphinance","https:\u002F\u002Fmphinance.com","2026-11-13 05:04:11",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add mphinance\u002Falpha-skills --skill backtest-expert",{"tool":38,"command":39},"bunx","bunx skills add mphinance\u002Falpha-skills --skill backtest-expert",{"tool":41,"command":42},"pnpm","pnpm dlx skills add mphinance\u002Falpha-skills --skill backtest-expert","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbacktest-expert\u002FSKILL.md",true,[46,52,56,60,66,70],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"README.md","REFERENCE","参考文档",8664,"https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbacktest-expert\u002FREADME.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ffailed_tests.md",7826,"https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbacktest-expert\u002Freferences\u002Ffailed_tests.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fmethodology.md",7251,"https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbacktest-expert\u002Freferences\u002Fmethodology.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fevaluate_backtest.py","SCRIPT","脚本",15336,"https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbacktest-expert\u002Fscripts\u002Fevaluate_backtest.py",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Ftests\u002Fconftest.py",690,"https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbacktest-expert\u002Fscripts\u002Ftests\u002Fconftest.py",{"path":71,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Ftests\u002Ftest_evaluate_backtest.py",21544,"https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbacktest-expert\u002Fscripts\u002Ftests\u002Ftest_evaluate_backtest.py",[75,83,88,95,102,109],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":82},"01M7BANC8ZXMVWWHSY3E31AAC3","order-lifecycle-safety","Idempotency, reconcile-before-retry, audit-before-forward and environment-proof preflight rules for any code or agent that places broker orders. Use when building or reviewing an order path, handling a timeout or unknown order outcome, adding client_order_id, deciding whether a retry is safe, or confirming paper vs live before sending an order.","https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Forder-lifecycle-safety\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":84,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":82},"01M7BAMZ37XP7XM8YDXWWSX0T9","https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fquant-skills\u002Fskills\u002Forder-lifecycle-safety\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M74928K9ZC74YQ1GMYB4N2Q0","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.","https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M749259PAEA22A891D0EJTKK","wireframe-sketch","A hand-drawn wireframe exploration — graph-paper background, marker \u002F\npencil tone, multiple tab labels for variants, sticky-note annotations,\nscribbled chart placeholders, hatched fills. Reads like a designer's\nwhiteboard before any pixels are committed. Use when the brief asks for\n\"wireframe\", \"sketch wireframe\", \"hand-drawn\", \"lo-fi\", \"whiteboard\",\n\"草稿\", or \"手绘原型\".","https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwireframe-sketch\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M74920ZWJS5Q1JRVJ8TSTQ5A","weekly-update","Single-file horizontal-swipe slide deck for a weekly team update —\nshipped, in flight, blocked, metrics, asks. 6–8 slides. Use when the\nbrief mentions \"weekly update\", \"team update slides\", \"weekly status\",\n\"周报演示\".","https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fweekly-update\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M7491YFRHYFV5QPS0MJ3DSNP","webull-openapi","Trade stocks, options, futures, crypto, and event contracts on Webull. Query real-time and historical market data. Manage accounts and positions. Supports US, HK, JP, SG, TH, MY, UK, MX, BR, EU, ZA, and AU regions with configurable risk controls.","https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwebull-openapi\u002FSKILL.md",[],[]]