Skip to content

charlieviettq/awesome-agent-skill / .claude/skills/algo-rank-bayesian

"algo-rank-bayesian"

Verified

"Apply Bayesian averaging to rank items by combining observed ratings with prior expectations. Use this skill when the user needs to rank items with varying review counts, build a 'top rated' list that handles low-sample items fairly, or implement IMDB-style weighted rating — even if they say 'weighted average rating', 'IMDB formula', or 'ranking with prior'.".

FileKindSize
SKILL.mdskill md4.4 KB
examples/sample_input.jsonconfig1.4 KB
references/imdb-formula.mdmarkdown7.6 KB
references/multi-dimensional.mdmarkdown9.1 KB
scripts/bayesian_avg.pyscript5.3 KB

examples/sample_input.json

View on GitHub
{
  "_comment": "台灣電影評分排行場景:混合高評分低評論數 vs 中等評分高評論數的項目,驗證貝葉斯平均對小樣本的縮合效果;confidence_C 設為 120 (接近評論數中位數)",
  "confidence_C": 120,
  "items": [
    {"name": "正常人",        "avg_rating": 9.2, "review_count": 18},
    {"name": "斯卡羅",        "avg_rating": 8.8, "review_count": 3420},
    {"name": "無聲",          "avg_rating": 9.5, "review_count": 4},
    {"name": "夜明け前",      "avg_rating": 6.1, "review_count": 890},
    {"name": "返校",          "avg_rating": 8.6, "review_count": 12400},
    {"name": "孤味",          "avg_rating": 8.3, "review_count": 5670},
    {"name": "瀑布",          "avg_rating": 8.9, "review_count": 2980},
    {"name": "一家子兒咕咕叫", "avg_rating": 7.4, "review_count": 1120},
    {"name": "親愛的房客",    "avg_rating": 8.7, "review_count": 4210},
    {"name": "新天堂樂園(台版重映)", "avg_rating": 9.1, "review_count": 67},
    {"name": "詭扯",          "avg_rating": 5.9, "review_count": 3300},
    {"name": "緝魂",          "avg_rating": 7.8, "review_count": 6800},
    {"name": "消失的情人節",  "avg_rating": 8.4, "review_count": 9150},
    {"name": "怪胎",          "avg_rating": 8.1, "review_count": 2430},
    {"name": "初戀慢半拍",    "avg_rating": 10.0, "review_count": 1}
  ]
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall