[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M748GC78B1QJ79CK1BWWAD32":3,"skill-same:01M748GC78B1QJ79CK1BWWAD32":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},"01M748GC78B1QJ79CK1BWWAD32","edge-hint-extractor",null,"Extract edge hints from daily market observations and news reactions, with optional LLM ideation, and output canonical hints.yaml for downstream concept synthesis and auto detection.","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\u002Fedge-hint-extractor\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: edge-hint-extractor\ndescription: Extract edge hints from daily market observations and news reactions, with optional LLM ideation, and output canonical hints.yaml for downstream concept synthesis and auto detection.\n---\n\n# Edge Hint Extractor\n\n## Overview\n\nConvert raw observation signals (`market_summary`, `anomalies`, `news reactions`) into structured edge hints.\nThis skill is the first stage in the split workflow: `observe -> abstract -> design -> pipeline`.\n\n## When to Use\n\n- You want to turn daily market observations into reusable hint objects.\n- You want LLM-generated ideas constrained by current anomalies\u002Fnews context.\n- You need a clean `hints.yaml` input for concept synthesis or auto detection.\n\n## Prerequisites\n\n- Python 3.9+\n- `PyYAML`\n- Optional inputs from detector run:\n  - `market_summary.json`\n  - `anomalies.json`\n  - `news_reactions.csv` or `news_reactions.json`\n\n## Output\n\n- `hints.yaml` containing:\n  - `hints` list\n  - generation metadata\n  - rule\u002FLLM hint counts\n\n## Workflow\n\n1. Gather observation files (`market_summary`, `anomalies`, optional news reactions).\n2. Run `scripts\u002Fbuild_hints.py` to generate deterministic hints.\n3. Optionally augment hints with LLM ideas via one of two methods:\n   - a. `--llm-ideas-cmd` — pipe data to an external LLM CLI (subprocess).\n   - b. `--llm-ideas-file PATH` — load pre-written hints from a YAML file (for Claude Code workflows where Claude generates hints itself).\n4. Pass `hints.yaml` into concept synthesis or auto detection.\n\nNote: `--llm-ideas-cmd` and `--llm-ideas-file` are mutually exclusive.\n\n## Quick Commands\n\nRule-based only (default output to `reports\u002Fedge_hint_extractor\u002Fhints.yaml`):\n\n```bash\npython3 skills\u002Fedge-hint-extractor\u002Fscripts\u002Fbuild_hints.py \\\n  --market-summary \u002Ftmp\u002Fedge-auto\u002Fmarket_summary.json \\\n  --anomalies \u002Ftmp\u002Fedge-auto\u002Fanomalies.json \\\n  --news-reactions \u002Ftmp\u002Fnews_reactions.csv \\\n  --as-of 2026-02-20 \\\n  --output-dir reports\u002F\n```\n\nRule + LLM augmentation (external CLI):\n\n```bash\npython3 skills\u002Fedge-hint-extractor\u002Fscripts\u002Fbuild_hints.py \\\n  --market-summary \u002Ftmp\u002Fedge-auto\u002Fmarket_summary.json \\\n  --anomalies \u002Ftmp\u002Fedge-auto\u002Fanomalies.json \\\n  --llm-ideas-cmd \"python3 \u002Fpath\u002Fto\u002Fllm_ideas_cli.py\" \\\n  --output-dir reports\u002F\n```\n\nRule + LLM augmentation (pre-written file, for Claude Code):\n\n```bash\npython3 skills\u002Fedge-hint-extractor\u002Fscripts\u002Fbuild_hints.py \\\n  --market-summary \u002Ftmp\u002Fedge-auto\u002Fmarket_summary.json \\\n  --anomalies \u002Ftmp\u002Fedge-auto\u002Fanomalies.json \\\n  --llm-ideas-file \u002Ftmp\u002Fllm_hints.yaml \\\n  --output-dir reports\u002F\n```\n\n## Resources\n\n- `skills\u002Fedge-hint-extractor\u002Fscripts\u002Fbuild_hints.py`\n- `references\u002Fhints_schema.md`\n","# Edge Hint Extractor\n\n## Overview\n\nConvert raw observation signals (`market_summary`, `anomalies`, `news reactions`) into structured edge hints.\nThis skill is the first stage in the split workflow: `observe -> abstract -> design -> pipeline`.\n\n## When to Use\n\n- You want to turn daily market observations into reusable hint objects.\n- You want LLM-generated ideas constrained by current anomalies\u002Fnews context.\n- You need a clean `hints.yaml` input for concept synthesis or auto detection.\n\n## Prerequisites\n\n- Python 3.9+\n- `PyYAML`\n- Optional inputs from detector run:\n  - `market_summary.json`\n  - `anomalies.json`\n  - `news_reactions.csv` or `news_reactions.json`\n\n## Output\n\n- `hints.yaml` containing:\n  - `hints` list\n  - generation metadata\n  - rule\u002FLLM hint counts\n\n## Workflow\n\n1. Gather observation files (`market_summary`, `anomalies`, optional news reactions).\n2. Run `scripts\u002Fbuild_hints.py` to generate deterministic hints.\n3. Optionally augment hints with LLM ideas via one of two methods:\n   - a. `--llm-ideas-cmd` — pipe data to an external LLM CLI (subprocess).\n   - b. `--llm-ideas-file PATH` — load pre-written hints from a YAML file (for Claude Code workflows where Claude generates hints itself).\n4. Pass `hints.yaml` into concept synthesis or auto detection.\n\nNote: `--llm-ideas-cmd` and `--llm-ideas-file` are mutually exclusive.\n\n## Quick Commands\n\nRule-based only (default output to `reports\u002Fedge_hint_extractor\u002Fhints.yaml`):\n\n```bash\npython3 skills\u002Fedge-hint-extractor\u002Fscripts\u002Fbuild_hints.py \\\n  --market-summary \u002Ftmp\u002Fedge-auto\u002Fmarket_summary.json \\\n  --anomalies \u002Ftmp\u002Fedge-auto\u002Fanomalies.json \\\n  --news-reactions \u002Ftmp\u002Fnews_reactions.csv \\\n  --as-of 2026-02-20 \\\n  --output-dir reports\u002F\n```\n\nRule + LLM augmentation (external CLI):\n\n```bash\npython3 skills\u002Fedge-hint-extractor\u002Fscripts\u002Fbuild_hints.py \\\n  --market-summary \u002Ftmp\u002Fedge-auto\u002Fmarket_summary.json \\\n  --anomalies \u002Ftmp\u002Fedge-auto\u002Fanomalies.json \\\n  --llm-ideas-cmd \"python3 \u002Fpath\u002Fto\u002Fllm_ideas_cli.py\" \\\n  --output-dir reports\u002F\n```\n\nRule + LLM augmentation (pre-written file, for Claude Code):\n\n```bash\npython3 skills\u002Fedge-hint-extractor\u002Fscripts\u002Fbuild_hints.py \\\n  --market-summary \u002Ftmp\u002Fedge-auto\u002Fmarket_summary.json \\\n  --anomalies \u002Ftmp\u002Fedge-auto\u002Fanomalies.json \\\n  --llm-ideas-file \u002Ftmp\u002Fllm_hints.yaml \\\n  --output-dir reports\u002F\n```\n\n## Resources\n\n- `skills\u002Fedge-hint-extractor\u002Fscripts\u002Fbuild_hints.py`\n- `references\u002Fhints_schema.md`\n",{"name":5,"description":7},"main","78b6ee6816aca6e5660cc7f0382650e9e7687086","skills\u002Fedge-hint-extractor",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 edge-hint-extractor",{"tool":38,"command":39},"bunx","bunx skills add mphinance\u002Falpha-skills --skill edge-hint-extractor",{"tool":41,"command":42},"pnpm","pnpm dlx skills add mphinance\u002Falpha-skills --skill edge-hint-extractor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fedge-hint-extractor\u002FSKILL.md",true,[46,52,56,60,66,70],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",239,"https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fedge-hint-extractor\u002Fagents\u002Fopenai.yaml",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"README.md",2653,"https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fedge-hint-extractor\u002FREADME.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fhints_schema.md",1717,"https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fedge-hint-extractor\u002Freferences\u002Fhints_schema.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fbuild_hints.py","SCRIPT","脚本",19305,"https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fedge-hint-extractor\u002Fscripts\u002Fbuild_hints.py",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Ftests\u002Fconftest.py",147,"https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fedge-hint-extractor\u002Fscripts\u002Ftests\u002Fconftest.py",{"path":71,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Ftests\u002Ftest_build_hints.py",12897,"https:\u002F\u002Fgithub.com\u002Fmphinance\u002Falpha-skills\u002Fblob\u002Fmain\u002Fskills\u002Fedge-hint-extractor\u002Fscripts\u002Ftests\u002Ftest_build_hints.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",[],[]]