Research & Data

lingyu9495-source/ai-image-watermark-removal-boss

github.com

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 生成角标、去"豆包/即梦/Kolors 生成"水印时使用。

$ npx skills add lingyu9495-source/agent-skills
Skill anzeigen→

lingyu9495-source/funding-fit-diagnosis

github.com

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 问项目画像采集(缺关键项就先追问,不猜)②双轨评分:市场化 VC 适配分与政府基金适配分**分开算、各自判定**(≥75 强匹配 / 60-74 可争取 / 45-59 需补短板 / <45 暂不建议,低分不许只说"不行",要给替代路径)③点名机构:按赛道/阶段/地域从 23 家头部 VC 与产业资本(CVC)、21 家政府基金的卡片里逐条对照"匹配信号/劝退信号",每家写清"为什么是你、你还缺什么、材料怎么准备、递送路径",并单列"不建议碰"的机构省时间④差距清单(差距|补齐动作|耗时|难度|优先级,只挑 3 个月内能推动的)+ 三线找钱路线图(市场化 / 政府 / 替代路径)+ 时间预期与现金流提醒。包内另附 30 个真实融资案例对标、TS 条款红线、估值倍数参考、BP 制作铁律,以及零依赖离线评分脚本(纯标准库、不联网、不调大模型 API)。输入:项目情况(照着 10 问答即可);输出:一份研判报告(评分 + 优先接触名单 + 差距清单 + 路线图 + 风险提示),脚本侧可另出 JSON 评分结果。评分是适配度不是成功率,不承诺融资结果。触发词:融资、找投资、融资研判、能不能融到钱、找哪家风投、风险投资、VC、产业资本、CVC、政府引导基金、政府基金申报、产业基金、招商返投、项目申报、补贴申报、商业计划书、BP、路演、估值、股权稀释、TS 条款、对赌、回购、FA、财务顾问、找钱、融资渠道、天使轮、Pre-A、A轮。

$ npx skills add lingyu9495-source/agent-skills
Skill anzeigen→

lingyu9495-source/company-law

github.com

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。

$ npx skills add lingyu9495-source/agent-skills
Skill anzeigen→

lingyu9495-source/investment-finance

github.com

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。

$ npx skills add lingyu9495-source/agent-skills
Skill anzeigen→

lingyu9495-source/cn-pdf-report-typeset

github.com

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。

$ npx skills add lingyu9495-source/agent-skills
Skill anzeigen→

lingyu9495-source/feasibility-report-engine

github.com

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。

$ npx skills add lingyu9495-source/agent-skills
Skill anzeigen→

lingyu9495-source/agent-responsiveness-delegation

github.com

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 把这套「重活外派 + 随时应答」机制做成可落地的东西:① 规则块(一页写清判级、派完立刻让出对话、工单四要素、只回收结论、自报≠事实、拍板留主脑、跨会话任务换机制)② 跨平台落地脚本 provision_agent_responsiveness.py:探测本机已有的 Agent 环境(Hermes 的 SOUL 置顶铁律块、Claude Code 的全局指令文件,这两条已实测),把规则块幂等写入(自动备份原文件、重复执行不重复写、绝不覆盖你已有内容);其余平台(Codex / Cursor / WorkBuddy / 任意 Agent)则导出一份可直接粘贴的规则块 markdown,你粘到系统提示或自定义指令里就生效 ③ 体检脚本 audit_agent_responsiveness.py:逐项核对规则块是否存在、是否被后续改动覆盖、探测到哪些平台——没检测到就如实报「未检测到支持的平台」,不假报通过。纯标准库、零依赖、Windows/macOS/Linux 通用。触发词:AI不回话、等太久、插话卡住、助手响应慢、主脑被占住、重活外派、子代理、多智能体、响应速度、落地配置、系统提示。

$ npx skills add lingyu9495-source/agent-skills
Skill anzeigen→

lingyu9495-source/financial-statement-adjustment

github.com

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、勾稽校验。

$ npx skills add lingyu9495-source/agent-skills
Skill anzeigen→

lingyu9495-source/excel-keep-format-edit

github.com

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。

$ npx skills add lingyu9495-source/agent-skills
Skill anzeigen→

lingyu9495-source/bank-scan-household-splitter

github.com

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**。

$ npx skills add lingyu9495-source/agent-skills
Skill anzeigen→

Shass27/stem-notes

github.com

Supplementary notes generation for STEM. Turns lecture slides, textbook chapters, scanned problem sheets, images (png/jpg) or PowerPoint/Word files into LaTeX formula/definition sheets, fully worked problem solutions, and summary notes. Use when the user asks for notes, a formula sheet, cheat sheet, worked solutions or revision material from reference/source files.

$ npx skills add Shass27/stem-notes
Skill anzeigen→

andreworia/cost-driver-analysis

github.com

Decomposes cost changes into volume, rate, and mix effects to identify the true root cause of cost escalation or decline.

$ npx skills add andreworia/claude-consulting-skills
Skill anzeigen→

andreworia/where-to-play-how-to-win

github.com

Builds a linked strategy choice cascade (winning aspiration, where to play, how to win, capabilities, management systems) so a direction is coherent and internally reinforcing, not a list of ideas.

$ npx skills add andreworia/claude-consulting-skills
Skill anzeigen→

andreworia/objection-handling

github.com

Prepares for a hostile room by pre-morteming the pushback, surfacing the hardest questions your recommendation will face, and drafting a tight, evidence-backed answer to each.

$ npx skills add andreworia/claude-consulting-skills
Skill anzeigen→

andreworia/problem-definition

github.com

Turns a vague symptom or an over-broad brief into a one-page SCQA problem statement and a single decision-shaped key question the work must answer.

$ npx skills add andreworia/claude-consulting-skills
Skill anzeigen→

andreworia/insight-synthesis

github.com

Turns raw findings into ranked insights by laddering each finding up the so-what chain from observation to implication to the action it demands.

$ npx skills add andreworia/claude-consulting-skills
Skill anzeigen→

andreworia/process-redesign

github.com

Maps a core process end to end with Lean value-stream analysis and redesigns it to remove waste and fix broken handoffs.

$ npx skills add andreworia/claude-consulting-skills
Skill anzeigen→

andreworia/issue-tree-builder

github.com

Decomposes one big question into a MECE issue tree or hypothesis tree of testable sub-questions, with branches ranked by impact so the team analyzes what matters first.

$ npx skills add andreworia/claude-consulting-skills
Skill anzeigen→

andreworia/pyramid-storyline

github.com

Structures an argument using the Pyramid Principle and SCQA so the recommendation lands in the first 60 seconds, with every supporting line grouped MECE beneath one governing thought.

$ npx skills add andreworia/claude-consulting-skills
Skill anzeigen→

andreworia/competitor-analysis

github.com

Reads industry structure with Porter's Five Forces and profiles rivals on capability and cost, giving a clear view of who you compete with and how attractive the industry really is.

$ npx skills add andreworia/claude-consulting-skills
Skill anzeigen→

andreworia/zero-based-budget-builder

github.com

Builds a zero-based budget for a cost center by requiring every line item to be justified from first principles rather than rolled forward from the prior year.

$ npx skills add andreworia/claude-consulting-skills
Skill anzeigen→

andreworia/hypothesis-design

github.com

Builds an answer-first plan by stating disprovable hypotheses and, for each, the "what would prove me wrong" test and the exact analysis that settles it, so the team tests instead of boiling the ocean.

$ npx skills add andreworia/claude-consulting-skills
Skill anzeigen→

boshu2/research

github.com

Trace code or test a recurring pattern to answer one cited question. Use when: uncertainty needs evidence. Not for external feature teardowns; use reverse-engineer.

$ npx skills add boshu2/agentops
Skill anzeigen→

DanMcInerney/social-search

github.com

Research bounded public source scopes, then return one independent ranked assessment.

$ npx skills add DanMcInerney/orchflows
Skill anzeigen→