Research & Data

Agent skill 'ai-research-reproduction' from lllllllama/rigorpilot-skills.

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。

When a public rule, standard or statute changes, produce a brief that shows what changed, clause by clause, from the official texts, and says what each change does in plain language, without advising Use when a person asks for this kind of job from public sources; cite "regulation-change-brief" in the receipt you file.

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 ~/.codex/state_5.sqlite 索引到的 Codex rollout-*.jsonl，从用户消息、助手回复、工具调用和命令结果中还原工作主题，以「全天时间线」为主轴（含甘特图把几点在做哪个项目画出来）串联整天工作、以「各项目推进」为副轴讲清每个项目，直接组织成 HTML 文档（不生成中间 md），并通过 lark-cli 发送到本人飞书邮箱。当用户说「总结今天的工作」「根据对话整理日报」「输出每日总结」或类似诉求时使用。

Deep-analyze a specific related / competing / concurrent paper — reading the ACTUAL paper, not its abstract — to decide the "isn't this just X?" question before a reviewer asks it: what it really does, whether it's prior or concurrent work, the strongest scoop a reviewer could claim, whether your delta is REAL or merely cosmetic, and the exact cite + positioning clause (or a scoop escalation) to apply. Saves the analysis to the paper's research folder and surfaces action points. Use whenever a paper close enough to yours surfaces — via verify-citations' nearest-neighbor, a reviewer's "this was already done", your own lit search, or an arXiv alert. Distinct from verify-citations (confirms a cite is real + one-line delta) and study-accepted-papers (mines a venue's accepted corpus for levers); this one does the deep per-competitor overlap/scoop analysis. Compose with verify-citations (feeds it neighbors), harden-paper (its nearest-neighbor-scoop axis calls this), and extend-paper (a scooped angle can become the

Comprehensive legal document review specialist for contracts, litigation documents, and real estate agreements — summarizing documents, flagging risk clauses, comparing contract versions, and checking compliance across any law firm size or practice area

Use this skill for scene structure and game flow in melonJS — Stage subclasses, the state manager, transitions, pausing, the update loop, timers and tweens. Covers onResetEvent versus the constructor, state.set before state.change, the camera and world lifecycle per stage, and pause-aware timing. Triggers on: Stage, state, state.set, state.change, state.transition, state.pause, onResetEvent, onDestroyEvent, onActivateEvent, onDeactivateEvent, PLAY, MENU, LOADING, update loop, GAME_UPDATE, timer, setTimeout, setInterval, Tween, freeze.

Universal real-time CLI HUD & Statusline for Hermes, Claude Code, and Codex.

Universal real-time CLI HUD & Statusline for Hermes, Claude Code, and Codex.

Multi-persona structured debate orchestrator. Personas research via /dogpile, consult colleagues via /ask, and argue toward nuanced synthesis on complex questions.

Reverse-engineer features from ELF binaries. Extracts CLI commands, state machines, protocols, Zod schemas, and data models. Automatically generates a /create-walkthrough prosecution brief with Mermaid diagrams. Uses /treesitter for AST analysis of bundled JS/TS source.

Search arXiv for papers and extract knowledge into memory. Use `search` to find papers, `learn` to extract knowledge.

Anonymize supported CSV, JSON, UTF-8 text, and SQLite files using an explicit policy through the oai-trial project. Use for anonymize data, pseudonymize exports, redact policy literals, or discover and explicitly approve fuzzy name aliases. The skill is a thin CLI/Docker interface, not another engine.

Flexible data science analytics for any dataset. Auto-discovers schema, recommends charts, exports to create-figure. Works with JSONL, JSON, CSV from any source.

Investigate whether a project (or every repo on the machine) is exposed to known and actively-exploited dependency vulnerabilities. Combines a deterministic per-ecosystem audit (npm audit, govulncheck, pip-audit, osv-scanner) with live web research into recent/active supply-chain incidents, then checks each project's lockfiles directly — the leading-indicator check that `npm audit` misses. Use when the user asks to "investigate security", "check for vulnerable dependencies", "are we affected by <a named CVE / package compromise>", "scan the projects for supply-chain issues", or wants a recurring security sweep.

Transform transcript analysis findings into actionable improvements. Triggers on "generate hooks from findings", "improve agent", "fix anti-pattern", "kaizen improvement", "generate hook proposals", or "create improvement plan". Provides templates for hook generation, agent prompt refinement, skill patches, CLAUDE.md updates, and script automation from analysis data.

Use when extracting specific data points from large agent output transcripts, kaizen analysis reports, or JSONL session files — tool timings, query counts, error summaries, or any structured facts — without loading raw data into orchestrator context. Activates when the orchestrator needs targeted facts from large files and context pollution must be avoided.

Diagnose and fix an unreliable, expensive, or unsafe LLM agent by auditing its harness (golden set, judge, cost caps, data layer, action approvals, tracing) before blaming or swapping the model. Use when someone says an agent is "burning tokens", "hallucinating", "brittle", gives inconsistent answers, asks whether to switch to a cheaper/better model, or wants to ship an agent or prompt change to customers.

Look things up before you code. Use for features, bug fixes, or anything that touches more than trivial code.

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。

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 上真跑出来的配置与调参。

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。

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。

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。