Compétences de la communauté
Recherche et analyse de données
3960 skills
LeoYeAI/openclaw-marketing-skills
When the user wants help with revenue operations, lead lifecycle management, or marketing-to-sales…
github.com
LeoYeAI/openclaw-marketing-skills
Connect to Meta Marketing API to pull real Facebook and Instagram ad data — campaign performance,…
github.com
LeoYeAI/openclaw-marketing-skills
Connect to Google Ads API to pull real account data — campaign performance, keyword health, wasted…
github.com
LeoYeAI/openclaw-marketing-skills
When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when…
github.com
romankurnovskii/awesome-founder-skills
Founder agent skills: research-based startup framing screener (arXiv:2608.00045) + accelerator…
github.com
mission-zero-radar
Signal triage for AI agents — convert an external signal into a context-grounded decision, bounded…
github.com
pratie/youtube-transcript-skill
Give your AI agent YouTube transcripts, search, and channel research — agent skill for Claude Code,…
github.com
lllllllama/ai-research-explore
Agent skill 'ai-research-explore' from lllllllama/rigorpilot-skills.
github.com
lllllllama/ai-research-reproduction
Agent skill 'ai-research-reproduction' from lllllllama/rigorpilot-skills.
github.com
lllllllama/analyze-project
Agent skill 'analyze-project' from lllllllama/rigorpilot-skills.
github.com
ZhengFangrong/data-analysis-skill
面向决策的数据分析 skill。用户上传 Excel/CSV 并提出业务问题时触发，输出离线 HTML 可视化报告。
github.com
mandajayde/regulation-change-brief
When a public rule, standard or statute changes, produce a brief that shows what changed, clause by…
github.com
LJW0401/daily-summary
基于当天 Claude Code / Codex 活跃会话生成每日工作总结。扫描 ~/.claude/projects 下的 Claude Code .jsonl，以及…
github.com
imMamdouhaboammar/legal-document-review
Comprehensive legal document review specialist for contracts, litigation documents, and real estate…
github.com
zernie/analyze-sibling-paper
Deep-analyze a specific related / competing / concurrent paper — reading the ACTUAL paper, not its…
github.com
melonjs/melonjs-scenes-and-state
Use this skill for scene structure and game flow in melonJS — Stage subclasses, the state manager,…
github.com
TheOwlOps/oxhud
Universal real-time CLI HUD & Statusline for Hermes, Claude Code, and Codex.
github.com
TheOwlOps/oxhud
Universal real-time CLI HUD & Statusline for Hermes, Claude Code, and Codex.
github.com
grahama1970/analytics
Flexible data science analytics for any dataset. Auto-discovers schema, recommends charts, exports…
github.com
grahama1970/analyze-elf
Reverse-engineer features from ELF binaries. Extracts CLI commands, state machines, protocols, Zod…
github.com
grahama1970/anonymize-data
Anonymize supported CSV, JSON, UTF-8 text, and SQLite files using an explicit policy through the…
github.com
grahama1970/argue
Multi-persona structured debate orchestrator. Personas research via /dogpile, consult colleagues…
github.com
grahama1970/arxiv
Search arXiv for papers and extract knowledge into memory. Use `search` to find papers, `learn` to…
github.com
byteratio/security-sweep
Investigate whether a project (or every repo on the machine) is exposed to known and…
github.com
Jamie-BitFlight/kaizen-improvement
Transform transcript analysis findings into actionable improvements. Triggers on "generate hooks…
github.com
Jamie-BitFlight/meta-inspector
Use when extracting specific data points from large agent output transcripts, kaizen analysis…
github.com
getedgehq/harness-first
Diagnose and fix an unreliable, expensive, or unsafe LLM agent by auditing its harness (golden set,…
github.com
TheElephantCoder/research-first
Look things up before you code. Use for features, bug fixes, or anything that touches more than…
github.com
lingyu9495-source/agent-responsiveness-delegation
你给 AI 助手派了个重活，然后发现：发消息它不回、想插话只能排队、等十几分钟才回一句——等它抬头，需求早变了。根因不是模型慢，是主脑把重活放在前台跑，整个回合被占死。这个 Skill…
github.com
lingyu9495-source/ai-image-watermark-removal-boss
去除 AI 生成图角落的"XXAI生成"半透明/白色角标水印。像素级验证不自我欺骗、双信号交叉定位抗幻觉、多候选客观指标投票覆盖。当用户要求去除图片水印、清理 AI…
github.com
lingyu9495-source/cn-pdf-report-typeset
中文报告做成 PDF，常见翻车三件套：**字体乱码、表格错位、字号小到客户在手机上根本看不清**。这套是交付级的排版标准加可直接跑的模板。
github.com
lingyu9495-source/company-law
公司出事，十有八九出在**治理和控制权**上——股权结构一开始搭歪，后面融资、上市、分家全是坑。
github.com
lingyu9495-source/excel-keep-format-edit
客户拿来一张老报表说「就在原表上改个数，格式一点都不要动」——用 openpyxl 重建一次，字体、边框、合并单元格、条件格式、列宽全丢，客户一打开就知道这不是他原来那张表。
github.com
lingyu9495-source/feasibility-report-engine
做可研报告，卡住的往往不是不会写，是**不知道按哪版大纲、财务测算六表和正文对不上、交付前排版被退稿**。这套是从二十多万字、131 张表的真实交付里固化的流水线。
github.com
lingyu9495-source/feasibility-study-consultant
项目可行性论证与研究报告写作框架 —— 任何「这事能不能做、怎么做、值不值得做」的商业决策场景：可行性研究/立项论证/新项目评估/创业方向验证。10大论证模块 + 强制联网尽调 + 多源交叉验证 +…
github.com
lingyu9495-source/financial-statement-adjustment
存量财务报表在原表基础上改数字并保持三表勾稽关系。当用户要求「在原报表上改某些数字，其他数据跟着调整且格式完全不变」时使用：资产负债表/利润表/现金流量表的目标值调整、未分配利润与利润总额联动、勾稽校…
github.com
lingyu9495-source/funding-fit-diagnosis
项目想融资，卡住的往往不是不会写 BP，而是不知道够不够格、该找谁、还缺什么、多久能到钱——问 AI 只得到"建议加强团队"这类正确的废话。这套引擎把它拆成可执行的四步：①10…
github.com
lingyu9495-source/gov-fund-application
想拿政府的钱，最容易白跑半年——层级选错、赛道不在目录里、返投算不清，材料递上去才发现方向不对。这套参谋按可执行顺序走：①先判层级（国家级/省级/市级/区级，门槛与目的完全不同）②赛道对目录：不在目录…
github.com
lingyu9495-source/hermes-profile-browser-isolation
多个 AI 助手同时干活时，浏览器会互相抢占：弹窗抢焦点、任务互相打断、你正在用的 Chrome/Edge 被顶掉——**你连自己的网页都点不动了**。
github.com
lingyu9495-source/investment-finance
做投融资最容易踩的坑不是"不懂概念"，是**条款里的每一个字都在分钱**——估值方法选错、对赌触发条件写松、回购条款没兜底，签完才发现少拿几千万。
github.com
lingyu9495-source/lowvram-ai-video-comfyui
网上的 AI 视频教程开口就是 24G 显存，一看就把人劝退——**其实 8G 的 4060 也能跑**。这套是 RTX 4060 Laptop 8G 显存 / 32G 内存 / Win11…
github.com
lingyu9495-source/novel-deai-detector
写完的稿子发布前想知道会不会被判 AI 生成、平台审核会不会卡、读者会不会一眼看出机器味——这套是检测到清洗的完整闭环。
github.com
lingyu9495-source/npl
不良资产这行的钱，赚在**买入价**上——买贵了，后面怎么处置都白搭。
github.com
lingyu9495-source/subagent-first
AI 助手不是不够聪明，是被重活占住了：你让它整理 40…
github.com
lingyu9495-source/ts-term-review
拿到 TS 或投资协议，看半天不知道哪条能签哪条得改——风险全藏在具体条目里，一句"整体没大问题"最要命。这套审查按 15 条核心条款逐条过：估值…
github.com
lingyu9495-source/bank-scan-household-splitter
客户丢来一个压缩包，里面几百张身份证正反面、开卡申请书、合同——**人工一张张挑，一下午就没了，还容易漏**。
github.com
Shass27/stem-notes
Supplementary notes generation for STEM. Turns lecture slides, textbook chapters, scanned problem…
github.com
andreworia/competitor-analysis
Reads industry structure with Porter's Five Forces and profiles rivals on capability and cost,…
github.com
andreworia/cost-driver-analysis
Decomposes cost changes into volume, rate, and mix effects to identify the true root cause of cost…
github.com
andreworia/hypothesis-design
Builds an answer-first plan by stating disprovable hypotheses and, for each, the "what would prove…
github.com
andreworia/insight-synthesis
Turns raw findings into ranked insights by laddering each finding up the so-what chain from…
github.com
andreworia/issue-tree-builder
Decomposes one big question into a MECE issue tree or hypothesis tree of testable sub-questions,…
github.com
andreworia/objection-handling
Prepares for a hostile room by pre-morteming the pushback, surfacing the hardest questions your…
github.com
andreworia/problem-definition
Turns a vague symptom or an over-broad brief into a one-page SCQA problem statement and a single…
github.com
andreworia/process-redesign
Maps a core process end to end with Lean value-stream analysis and redesigns it to remove waste and…
github.com
andreworia/pyramid-storyline
Structures an argument using the Pyramid Principle and SCQA so the recommendation lands in the…
github.com
andreworia/where-to-play-how-to-win
Builds a linked strategy choice cascade (winning aspiration, where to play, how to win,…
github.com
andreworia/zero-based-budget-builder
Builds a zero-based budget for a cost center by requiring every line item to be justified from…
github.com
boshu2/research
Trace code or test a recurring pattern to answer one cited question. Use when: uncertainty needs…
github.com
DanMcInerney/social-search
Research bounded public source scopes, then return one independent ranked assessment.
github.com